[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EHAX2AD8GFWDFDHKEE6TPC":3,"skill-same:01M7EHAX2AD8GFWDFDHKEE6TPC":305},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7EHAX2AD8GFWDFDHKEE6TPC","verify-sunstack-rule",null,"Use when verifying the Rust Sunstack engine, installed TypeScript SDK or sunstack runner, including lint, exec, hosted Jev, standalone builds and private release-install rehearsals. Not for Demistify or production hook installation.","ShravanSunder\u002Fsunstack-tools","ShravanSunder","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5294949?v=4","01M7EHAJQY0H013BR4QAEVHEJF","Shravan Sunder","01M7EHAJRFJNY38NQBBVDDH999",0,"MIT","https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: verify-sunstack-rule\ndescription: Use when verifying the Rust Sunstack engine, installed TypeScript SDK or sunstack runner, including lint, exec, hosted Jev, standalone builds and private release-install rehearsals. Not for Demistify or production hook installation.\n---\n\n# Verify Sunstack Rule\n\nVerify a named target against the adopted Specification, then report only the outcomes observed there. A passing build, an HTTP success or an unfavorable rule verdict each means something different.\n\nThe current runner is `sunstack`: `lint` calls the `sunstack-lint` library and the evidence\u002Frules\u002Fdecisions engine; `exec` carries the engine protocol. Evidence owns capture and selection, decisions owns Jev transport and answer admission, rules owns applicability\u002Fgrouping\u002Fverdicts, lint owns repository configuration and reporting, and the binary owns command dispatch, signals and exits. Historical routes below drive the earlier `sunstack-rule` process. There is no daemon; npm is an install\u002Flaunch channel.\n\n## Choose the target and journey\n\n1. From the monorepo root, record `git rev-parse --show-toplevel`, `git branch --show-current`, `git rev-parse HEAD` and `git status --short`. Record the declared product commit, build location, configuration and calling client. Confirm the driven checkout matches that product commit; the skill may be on a separate branch. Stop if the target changes during observation.\n2. For **historical replay of the legacy V\u002FUS routes**, the adopted oracle is design revision `f259d4b28f5131478e574e123335904c78b0d347`. Product target: `592293254239d301c53cd25fcb5b106f21cbfb59`. Read oracle files with `git show \u003Cdesign revision>:\u003Crepo-relative-path>`, except `docs\u002Fspecs\u002F2026-10-12-rust-rule-engine\u002Fschemas\u002Frule-invocation.schema.json` and `docs\u002Fspecs\u002F2026-10-12-rust-rule-engine\u002Fschema-inventory.md`, which use adopted schema revision `fc754c8335963bf809dad7472109a81dc29c3c2b`. Start with `git show f259d4b28f5131478e574e123335904c78b0d347:docs\u002Fspecs\u002F2026-10-12-rust-rule-engine\u002Fspecification.md`, especially the selected V rows; use the design revision for `program-design.md`, `program-design-contracts.md`, `program-design-connected-evidence.md`, referenced examples and other schemas. Product design copies may be older and a design working tree may have moved. If a pinned object is unavailable, return that source gap; resolve conflicting expectations with the commissioning Lead before driving the affected case. The Markdown-rule route below takes its product target and adopted design from its commission and reference instead.\n3. Select the route below and read it. A draft has an open target prerequisite and is not a passing observation; drive its first run only under a declared-target commission once its prerequisites are met.\n\nSKILL.md owns target policy. A historical replay is runnable only at its recorded product\u002Foracle contract and proves nothing about the current product. Keep its fixture vocabulary, source guards and receipts together. Current routes use `error`, `warn`, `warn_above_band` and `error_at_or_below`; old inputs occur only in refusal controls. Current U3 `exec` proof comes from the declared target's real workspace\u002Fprocess suite, not a historical replay. A shared transport helper has no severity policy.\n\n| Surface                                                                                                              | Route and driver                                                                                                                           | Product target                                                                                                   | Oracle                                                                                                      | Availability                                                                                                                                               |\n| -------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Selection candidate\u002Fshared cut fields | `references\u002Fselection-cuts.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fselection-cuts\u002Fselection-cuts.ts` | declared signed0.16 candidate and released0.15.1; headed P3 plus J1\u002Fai-tools | 0.16 selection-cut commission\u002FCorrection1; exact added vectors\u002Fhashes and unchanged rule reports | operable; candidate\u002Fshared metadata and rule parity exercised; repeat per target and join native\u002FSDK proof |\n| Native section heading labels and P3 paths | `references\u002Fheading-text.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fheading-text\u002Fheading-text.ts` | declared signed0.15.1 candidate and released0.15.0, fixed13HTML\u002F10Markdown pages | 0.15.1 heading-text commission Corrections1–5; source-derived labels\u002Fspans and version-only additive parity | operable; source paths, own headings and legacy parity exercised; repeat per target and join native\u002FSDK proof |\n| Configured conventions and standard defaults | `references\u002Fconfig-only.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fconfig-only\u002Fconfig-only.ts` | declared signed0.15 candidate and released0.14.1; fixed actual J1\u002FHTML\u002FMarkdown\u002Fai-tools inputs | 0.15 config-only commission Corrections1–7; exact config snapshot exception and parser-located released witness | operable; configured\u002Fdefault signed CLI exercised; repeat per target and join native\u002FSDK proof |\n| Installed SDK codec, direct inspection and examples | `references\u002Fsdk-journeys.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fsdk\u002Fsdk-verify.ts` (`codec`, `inspection`, `examples`) | declared quiescent candidate and fresh pinned installed package\u002Faddon | commission's agent-usability specification and verification design | operable; exercised on 0.19\u002Frevision 13 with partial receipts; repeat per target and retain provider, in-flight cancellation and fault limits |\n| Installed TypeScript SDK: load\u002Fedit, inline\u002Fnative parity, cancellation, six-cell installation and ordinary provider | `references\u002Fsdk-journeys.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fsdk\u002Fsdk-verify.ts`                                                             | declared quiescent integrated head, fresh installed package\u002Faddon\u002Ftarball hashes and exact Node\u002FOS\u002FCPU\u002Flibc cell | 11 Nov TypeScript SDK R1–R15 and O1–O6, including native 0.14 HTML\u002FMarkdown units and absolute checked root | draft; apparatus sensitivity tests are not SDK observations; missing native, CLI, install and provider joins remain explicit                               |\n| HTML asking, cross-document coverage and checked root                                                                | `references\u002Fhtml-evidence.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fhtml-evidence\u002F{html-evidence,markdown-parity,checked-root}.ts`                | declared signed0.13 candidate for asking\u002Fcoverage; companion targets and comparators explicitly commissioned     | 0.11 mechanics plus0.13 HTML asking projection; pinned real corpus and original consumer config             | asking\u002Fcoverage operable; declared-target pass and native joins required; companions need their own commissioned joins                                     |\n| HTML lexical sections and complete asking text                                                                       | `references\u002Fhtml-sections.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fhtml-sections\u002Fsections.ts`                                                    | declared signed0.13 candidate, full head\u002Fdigest; three fixed real HTML inputs                                    | 0.13 HTML-sections commission Proof1–3\u002FCorrections1–7; lexical h1–h6 outline                                | operable; recovered headings, original outlines and exact asking text exercised; repeat per target                                                         |\n| HTML asking text and truthful incomplete fields | `references\u002Fhtml-sections.md`0.14.1; `scripts\u002Fverify\u002Fsunstack-rule\u002Fhtml-sections\u002Ferror-text.ts` | declared signed0.14.1 candidate and released0.14.0 comparator; frozen source tables and original projects | 0.14.1 commission Corrections1–13; source-derived text and exact report boundary | operable;43J1 cases, real arrow\u002Fampersand pages,114sections,499requests, Markdown parity and unsafe cuts exercised; repeat per target |\n| Markdown fragment anchors and section fields                                                                         | `references\u002Fmarkdown-sections.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fmarkdown\u002F{capture,anchors,github-samples}.ts`                             | declared signed0.14 candidate, full head\u002Fdigest; fixed two-repository corpus                                     | 0.14 commission\u002FCorrections1–9; independent264link and74section oracle, actual GitHub IDs                   | operable; original corpus, sections, image-heading\u002Fordinary raw-asking controls exercised; native\u002Fparity joins stay separate                               |\n| Deferred document admission                                                                                          | `references\u002Fhtml-evidence.md` admission section; `scripts\u002Fverify\u002Fsunstack-rule\u002Fhtml-evidence\u002Fdocument-admission.ts`                        | declared signed admission correction, full head and digest                                                       | Correction7; preserve existing Target diagnostics and local\u002Fplain Document positives                        | operable; keyless --check only, no selected dispatch                                                                                                       |\n| Public exec Choice255\u002F256 boundary                                                                                   | `references\u002Flocator-limits.md` public exec section; `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Fexec-choice-limits.ts`                          | declared signed F1–F3 correction candidate, full head and binary SHA256                                          | Lead correction disposition; decisions-owned Choice cap255                                                  | operable; both public decision API and filter native joins checked per target                                                                              |\n| Locator Choice cap and omission evidence                                                                             | `references\u002Flocator-limits.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Flocator-limits.ts`                                                  | declared signed locator-limit candidate, full head and binary SHA256                                             | 6 Nov locator-limit commission\u002FLead disposition; nudge R2\u002FC2; provider Choice maximum255                    | operable; direct-SDK refusal\u002Fschema joins checked per target                                                                                               |\n| Filters: tree routes and shared gates (O4)                                                                           | `references\u002Frulebook-lint.md` filters section; `rulebook-lint.ts --case filters` and `rulebook-filters.ts`                                 | declared signed decision-trees candidate, full source commit and binary SHA256                                   | decision-trees Specification\u002FPD\u002FVD at `0567445`, O4                                                         | operable; confirm target and native joins per run                                                                                                          |\n| Changed-only capture, original input and raw-identity edges                                                          | `references\u002Fgit-first.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fgit-first\u002F{git-first-original,git-first-edges}.ts`                                | declared signed0.12 main\u002Ftest artifacts, full source head and digests; released0.11.1 comparator                 | 0.12 commission Proof1–4\u002FCorrection2 raw identity, prepared success6                                        | operable at5b4965ba; original\u002Ffull oracle, declared native consumer and owned edges observed; repeat per target                                            |\n| --since beside equal binary assets                                                                                   | `references\u002Fsince-encoding.md`; current route uses `git-first-edges.ts`; legacy `rulebook-since-encoding.ts` is0.10.1-only                 | current declared0.12 artifacts or separately commissioned historical0.10.1\u002F0.10.0 replay                         | raw binary\u002Fsymlink\u002Fbyte-budget contracts; Full versus ChangedOnly context is explicit                       | current coverage joins candidate-identity route; historical replay remains pinned                                                                          |\n| Rule-author usability and keyless empty scope                                                                        | `references\u002Flint-usability.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fusability\u002Fprobe.ts`                                                          | declared signed0.12.1 candidate, full head\u002Fdigest; released0.12.0 and detached probe input                       | 0.12.1 usability commission U1–U6\u002FCorrections1–4                                                            | operable at245eb9c3;8probe rows\u002F28CLI children,10native boundary controls and exact prepare-report parity observed; repeat per target                      |\n| Human unsure summaries and output preservation                                                                       | `references\u002Funsure-summary.md`; `rulebook-unsure-summary.ts`                                                                               | declared signed candidate and immutable comparator bytes\u002Fversion\u002Fprovenance                                      | 8 Nov 0.10 unsure-summary commission; current CLI human-output contract                                     | operable; strict same-version and released-version comparison are separate runs                                                                            |\n| Short output, saved report and cases (O5\u002FO6)                                                                         | `references\u002Fdecision-trees.md`; `rulebook-report.ts` and `rulebook-cases.ts`                                                               | declared decision-trees source commit and signed binary SHA256                                                   | decision-trees Specification\u002FPD\u002FVD at `2fea595` (exact ranges and distinct owner-ruling)                    | operable; scripted journey, keyed run separate                                                                                                             |\n| Completed cases readback and change-scope error paths                                                                | `references\u002Fcli-report-errors.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fcli-reports\u002F{show-reports,change-scope-errors}.ts`                        | declared signed0.11.1 candidate, full head and SHA256; frozen real R03 report                                    | 0.11.1 commission Outcomes1–3\u002FCorrections1–2; completed candidate union versus preserved prepared ordinals  | C1 observed6fd3aaaa (37 CLI invocations); C2 show observeda59cf64e (22); unchanged scope reused with explicit dependency comparison and fresh native joins |\n| Current nudge admission refusals                                                                                     | `references\u002Frulebook-check-refusals.md`; `rulebook-check-refusals.ts --case nudge`                                                         | declared signed current source commit and binary SHA256                                                          | 31 Oct S2 plus decision-trees `2fea595` and Lead identical-versus-conflicting locator disposition           | operable; two acceptance controls and ten zero-request refusals; join native identical-reuse positive                                                      |\n| Rules-as-nudges report: U1-U10                                                                                       | `references\u002Frulebook-lint.md` and `rulebook-check-refusals.md`, both `--case nudge`; `rulebook-nudge-compatibility.ts` for U10             | declared signed 0.6.0 release build; signed 0.5.0 artifact for comparison                                        | 31 Oct engine Specification\u002FVD accepted at `a69fe47`; locator-order clarification `6328647`                 | S1\u002FS2\u002FU10 observed at `ffd86f5`; native S3 joins required; keyed S4 separate                                                                               |\n| Prepare exact requests without dispatch                                                                              | `references\u002Fprepare-requests.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fprepare\u002Fprepare-requests.ts`                                               | declared 0.9 source and immutable binary SHA256                                                                  | 7 Nov prepare commission, Admission, Addition 2, F1\u002FF2 and whole-view pending policy                        | historical fixture observation at `73d7fc78`; every current target must drive F1\u002FF2\u002Fprojection\u002Freplay-allowance controls; paid comparison separate         |\n| Rust quality\u002Fnative consumers                                                                                        | `references\u002Flibrary-gates.md`                                                                                                              | commission-declared committed source                                                                             | commission-declared contract                                                                                | scoped source\u002Ftest proof; historical receipts need applicability                                                                                           |\n| Within a union of kinds: amended U14\u002FU16, W6                                                                         | `references\u002Fwithin-kinds.md`; selection-mode lint\u002Frefusal entries and `scripts\u002Fverify\u002Fsunstack-rule\u002Fselection\u002Fwithin-kinds-equivalence.ts` | declared within-kinds frozen source\u002Fbinary; frozen v0.3.0 for one-item comparison                                | amended R30\u002FR40 and U14\u002FU16 at `9dfdb10` + `a4696af` + `2198c47`, W1–W6 and path-policy amendments          | c3 WI2\u002Flocal paths observed at `4086bcc1`; c1 union\u002FW6 reused with applicability                                                                           |\n| Evidence selection: U13–U17, R42                                                                                     | `references\u002Fevidence-selection.md`; rulebook lint and check-refusal entries with `--case selection`; temporary compatibility probe         | commission-declared S3 source\u002Fbinary; npm 0.2.0 plus frozen kit for R42                                          | 30 Oct evidence-selection Specification and Verification Design                                             | observed locally at `7315762`, native concurrency addendum `5d7c070`; live V21 separate                                                                    |\n| Rulebook lint: U2\u002FU5\u002FU8\u002FU10\u002FU12                                                                                      | `references\u002Frulebook-lint.md`, repo `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Frulebook-lint.ts` and `rulebook-boundaries.ts`                  | declared stable S3 head and local binary                                                                         | 29 Oct skill-rules Specification and Verification Design, including Lead's F1–F3 proof clarifications       | observed locally at `42f40e6`; native joins required at each target                                                                                        |\n| Rulebook check refusals: U9                                                                                          | `references\u002Frulebook-check-refusals.md`, repo `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Frulebook-check-refusals.ts`                           | same declared stable S3 head and local binary                                                                    | same 29 Oct rulebook oracle, R24 inventory                                                                  | observed locally at `42f40e6`; structural check call-path join required at each target                                                                     |\n| Historical V11 \u002F V22 \u002F V34 hosted                                                                                    | `references\u002Fhosted-decisions.md` native sections                                                                                           | historical product pin above                                                                                     | historical design\u002Fschema pins above                                                                         | historical replay; explicit hosted grant still required                                                                                                    |\n| Historical executable V2\u002FV13                                                                                         | `references\u002Fexecutable-operations.md`                                                                                                      | historical product pin above                                                                                     | historical design\u002Fschema pins above                                                                         | historical replay only                                                                                                                                     |\n| Historical skill\u002Fhandoff V14\u002FV29\u002FV30                                                                                 | `references\u002Fmilestone-1.md`                                                                                                                | historical product pin above                                                                                     | historical design\u002Fschema pins above                                                                         | historical replay; proof remains verbatim                                                                                                                  |\n| Historical Git\u002Fconnected V rows                                                                                      | `references\u002Fmilestone-2.md`                                                                                                                | historical product pin above                                                                                     | historical design\u002Fschema pins above                                                                         | historical replay only                                                                                                                                     |\n| Historical usage US routes                                                                                           | `references\u002Fusage-scenarios.md`, `scripts\u002Fusage_scenarios.py`                                                                              | historical product pin above; enforced by driver                                                                 | historical design\u002Fschema pins above                                                                         | local replay; genuine slots remain disabled                                                                                                                |\n| Historical Markdown U1–U9                                                                                            | `references\u002Fmarkdown-skill-rules.md`, repo `scripts\u002Fverify\u002Fsunstack-rule\u002F`                                                                 | reference's declared S2 `7c529b4b` \u002F S4 `bdca8d9a`                                                               | reference's adopted Markdown revisions                                                                      | pre-runner replay, old binary\u002Freadiness; no current `exec` claim                                                                                           |\n| S1 lint runner                                                                                                       | `references\u002Flint-runner.md`, repo `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Flint-runner-rulebook.ts`                                          | declared local S3 rulebook binary                                                                                | 29 Oct rulebook oracle, retained runner formats\u002Fexits\u002Fscopes                                                | observed locally at `42f40e6`; legacy RuleSet fixture\u002Fschema helpers are historical proof                                                                  |\n| S2 standalone containers, U8\u002FU9                                                                                      | `references\u002Fcontainer-matrix.md`, `scripts\u002Fcontainer_matrix.py`                                                                            | declared four release artifacts and SHA256s                                                                      | same runner oracle                                                                                          | historical fixture shape; rulebook upkeep and a declared artifact are required before a current offline matrix                                             |\n| S3 genuine static Linux Jev, rulebook U6                                                                             | `references\u002Fhosted-decisions.md` S3, repo `scripts\u002Fverify\u002Fsunstack-rule\u002Fhosted\u002Fhosted-lint.ts`                                             | declared static Linux arm64 release artifact\u002FSHA256\u002Fversion\u002Fcommit                                               | 29 Oct rulebook U6 plus retained no-CA runner contract                                                      | draft; separately commissioned paid command                                                                                                                |\n| S4 private release installs, U2\u002FU8\u002FU10\u002FU11                                                                           | `references\u002Frelease-rehearsal.md`, `scripts\u002Frelease_assets.py` and repo `scripts\u002Fverify\u002Fsunstack-rule\u002Frelease\u002F` drivers                    | two declared normal-version private releases; exact scoped package\u002Fsource\u002Fbytes                                  | all-channel stream\u002Fstop oracle `8cf9c51` or commission-declared successor                                   | draft until every channel\u002Fplatform cell observed; private registry\u002FCI tap, public npm publishing excluded                                                  |\n\nIF source\u002Fnative tests or Rust quality gates are in scope, load `references\u002Flibrary-gates.md` and return the scoped commands, results and remaining coverage. Artifact-only observations do not launch an unrelated Cargo suite.\nIF installed TypeScript SDK behavior is commissioned, load `references\u002Fsdk-journeys.md` and return each selected O row's installed consumer, exact artifact\u002Fcell identity, actual requests\u002Foutcomes and required native\u002FCLI\u002Finstall joins. Do not claim SDK coverage from the existing CLI npm channel, source-only prototype, apparatus tests or a cross-compiled addon. Provider execution needs its own explicit grant.\n\nCurrent rulebook journeys run directly with `node \u003Cdriver>.ts`; Zod validates external data. No Python wrapper or runtime is used for these routes. Their apparatus checks, from the monorepo root, are `pnpm exec tsc -p scripts\u002Fverify\u002Fsunstack-rule\u002Ftsconfig.json`, `pnpm exec oxlint --type-aware --type-check --tsconfig scripts\u002Fverify\u002Fsunstack-rule\u002Ftsconfig.json --max-warnings 0 scripts\u002Fverify\u002Fsunstack-rule\u002F**\u002F*.ts`, `pnpm exec oxfmt --check scripts\u002Fverify\u002Fsunstack-rule\u002F**\u002F*.ts scripts\u002Fverify\u002Fsunstack-rule\u002Ftsconfig.json`, and `pnpm exec vitest run scripts\u002Fverify\u002Fsunstack-rule\u002F**\u002F*.test.ts`, and `node --test scripts\u002Fverify\u002Fsunstack-rule\u002Frelease\u002F*-test.ts`. Historical Python drivers below are retained for their separate migration phase.\nIF historical hosted V11 replay is in scope, load `references\u002Fhosted-decisions.md` and return its run identity, validated completion and receipt, or its access\u002Fsetup gap.\nIF historical genuine V22 or V34 replay is in scope, load `references\u002Fhosted-decisions.md` and return the hosted-rules observation or applicable reused evidence, native answer\u002Freceipt checks and any remaining gap.\nIF historical executable V2\u002FV13 replay is in scope, load `references\u002Fexecutable-operations.md` and return the operation coverage, process evidence and remaining proof limits.\nIF historical milestone 1 replay is in scope, load `references\u002Fmilestone-1.md` and return each local\u002Fhosted journey's report, measurement or named prerequisite.\nIF historical change-scope or connected-evidence replay is in scope, load `references\u002Fmilestone-2.md` and return each scoped V5\u002FV7\u002FV16–V18 claim and the V20 related-units portion as **supported**, **unsupported** or **unknown**, with observed\u002Freused\u002Fdraft coverage, target and evidence path, per the Evidence, cleanup and return rule below.\nIF historical usage-scenario replay is in scope, load `references\u002Fusage-scenarios.md` and return each selected US ID's supported\u002Funsupported\u002Funknown verdict, observed\u002Freused coverage, relevant V rows, target, process\u002FHTTP evidence and remaining gap, using the return rule below.\nIF retained Markdown\u002Fnative proof or reconstruction of a historical marker replay is commissioned, load `references\u002Fmarkdown-skill-rules.md` and return each retained proof home and applicable current-target run, or the historical source\u002Ftarget prerequisite. Retired marker drivers do not run against the current rulebook target.\n\nIF current changed-only `--since` or default uncommitted capture is in scope, load `references\u002Fgit-first.md`; return original-command preparation, exact full-oracle owners\u002Frequests, public-API raw paths\u002Facquisition counts, edge\u002Fdefault controls and readonly-input guards or named gaps.\nIF `lint --since` capture or unchanged binary assets are in scope, load `references\u002Fsince-encoding.md` and return changed-piece selection, selected-encoding refusals, binary-free byte parity, native budget\u002Fsnapshot joins and original-input observations or named gaps.\nIF HTML asking ERROR recovery is commissioned, load `references\u002Fhtml-sections.md`'s0.14.1 route and run `html-sections\u002Ferror-text.ts`; return the43-case real source scan, original114-section, Markdown-anchor and ai-tools499-request parity, ampersand preservation, unsafe cuts, exact allowed diffs and native joins or named gaps.\nIF HTML heading sections, own\u002Fenclosing text, diagram attributes or element boundaries are commissioned, load `references\u002Fhtml-sections.md`; return the three pinned outline comparisons, prepared\u002Fcut controls and native parity\u002Fadmission joins or named gaps.\nIF Markdown fragment anchors or markdown_units section fields are commissioned, load `references\u002Fmarkdown-sections.md`; return every original link state, actual rendered GitHub samples, real\u002Fcontainer section spans, admission refusals and native\u002Fparity joins or named gaps.\nIF HTML evidence, cross-document ID checks or explicit checked-root behavior is commissioned, load `references\u002Fhtml-evidence.md`; return each real R\u002FE owner, prepared text\u002Fraw span, fragment result, root refusal and absolute-path control, exact Markdown comparator\u002Finput identities and remaining native or provider gaps.\nIF keyless empty-scope lint, config-open diagnostics, status summaries, named scope, help or prepared-output usability is commissioned, load `references\u002Flint-usability.md`; return the8real probe outcomes, zero\u002Fdirty eligibility controls, prepared request\u002Fpath summaries, unchanged JSON reports and native no-evidence joins or named gaps.\nIF current lint behavior is commissioned, load `references\u002Flint-runner.md` and return the selected case counts, finding\u002Fexit comparisons, target identity, native-proof joins and remaining gaps.\nIF locator option limits or omitted-location reporting are commissioned, load `references\u002Flocator-limits.md` and return exact255-boundary, wire criteria, reached-result evidence and native refusal\u002Fschema joins at the declared target.\nIF default human unsure summaries or cross-version output preservation are commissioned, load `references\u002Funsure-summary.md`; report per-rule counts\u002Fpointers, all-format\u002Freport byte comparisons, every result ID readback, exact version exceptions and comparator provenance.\nIF completed cases-report readback or change-scope refusal paths\u002Flimits are commissioned, load `references\u002Fcli-report-errors.md`; return real R03 unique\u002Fcase\u002Fambiguous lookups, preserved ordinary\u002Fprepared details, offending path fields in human\u002FJSON\u002FSARIF, configured limit values and native SourceChanged joins or named gaps.\nIF decision-trees output, saved reports or case runs are commissioned, load `references\u002Fdecision-trees.md`; report each O row with its declared target, actual output and open gaps. Keyed\u002Fmodel calls need a separate commission.\nIF filters or `only_when` are commissioned, load the filters section of `references\u002Frulebook-lint.md` and return the exact folder\u002Frequest\u002Fresult\u002Fskip comparisons, process exits, candidate identity and native joins or gaps. The scripted answers establish mechanics, not classification accuracy.\nIF evidence selection, containment, candidate reports or 0.2.0 compatibility is commissioned, load `references\u002Fevidence-selection.md` and return U13–U17 plus R42 coverage, exact candidate\u002Frequest\u002Fcount comparisons, native joins and remaining live\u002Ftarget gaps.\nIF amended R30 list containment is commissioned, load `references\u002Fwithin-kinds.md` and return union\u002Fonce-only and not-selected fallback, every new R40 refusal\u002Flisting, W6 equality with planted rejection, and native schema\u002Fplan proof or gaps.\nIF the 29 Oct rulebook evidence, decision or change-scope journey is commissioned, load `references\u002Frulebook-lint.md` and return each scoped U row's observed\u002Freused evidence, exact target and native joins or gaps.\nIF the 29 Oct rulebook check\u002Frefusal journey is commissioned, load `references\u002Frulebook-check-refusals.md` and return clean acceptance, every executed refusal's diagnostic\u002Fexit, zero-request\u002FFIFO observations and structural check call-path join or gaps.\nIF standalone portability is commissioned, load `references\u002Fcontainer-matrix.md` and return each distro\u002Farchitecture cell, exact binary linkage\u002Fhash, command exits and remaining macOS\u002FCargo-feature proof.\nIF the current no-CA hosted judgment is commissioned, load `references\u002Fhosted-decisions.md` S3 and return its genuine verdict, typed answers\u002Fevidence\u002Fusage, exact target and safe evidence or setup gap.\nIF private install\u002Frelease behavior is commissioned, load `references\u002Frelease-rehearsal.md` and return two normal-tag artifact\u002Fjob\u002Ftap evidence, registry-resolved local-bin\u002Fexec-script\u002Fglobal\u002Fbare-npx\u002Fexec-npx\u002Fpnpm-dlx and native-channel bytes\u002Fversion\u002Freport\u002Fexit\u002Fsignal transcripts, fresh-runner coverage, real Actions exec\u002Fplain cancellation records and unobserved cells.\n\nFor every selected route, check its prerequisites and readiness, drive only commissioned actions, compare the deciding outcome, preserve evidence, stop owned resources and report supported\u002Funsupported\u002Funknown. A prepared fixture or missing binary is never a product pass. A draft route may be driven in a separately commissioned first observation; it becomes observed only for the target and cases actually run.\n\nFor the historical selected usage scenario, run the selector from the monorepo root. The reference owns the inventory and prerequisites; repeat `--journey` only for requested IDs:\n\n```sh\nenv -u PYTHONOPTIMIZE -u UV_INDEX -u UV_EXTRA_INDEX_URL -u UV_INDEX_URL -u UV_FIND_LINKS -u PIP_INDEX_URL -u PIP_EXTRA_INDEX_URL -u UV_DEFAULT_INDEX -u UV_CONFIG_FILE -u UV_ENV_FILE \\\n  UV_CACHE_DIR=\u003Cauthorized-evidence>\u002Fuv-cache PYTHONDONTWRITEBYTECODE=1 \\\n  uv run --no-config --no-env-file --no-python-downloads --default-index https:\u002F\u002Fpypi.org\u002Fsimple --locked --script \\\n  .agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fusage_scenarios.py \\\n  --binary \u003Cdeclared-binary> --evidence \u003Cauthorized-evidence> --journey \u003CUS-ID>\n```\n\n## Build and readiness\n\nRun Cargo from the monorepo root with the pinned toolchain in `rust-toolchain.toml`. On macOS this host needs a command-local SDK correction for C dependencies:\n\n```sh\nSDKROOT=\"$(xcrun --show-sdk-path)\" CC=\u002Fusr\u002Fbin\u002Fclang CFLAGS=\"-isysroot $(xcrun --show-sdk-path)\" cargo build --workspace\n```\n\nUse that same prefix on **every Cargo command** shown in the references on this host. Do not change global compiler settings. Other platforms use their declared native toolchain; they are separate, unobserved targets.\n\nOn Apple Silicon, `.cargo\u002Fconfig.toml` routes Cargo\u002Fnextest execution through `scripts\u002Fcargo-debug-signing-runner.sh`. It gives the app and tests stable, separate debug identities. Signing is best effort: a warning means the original binary still runs and LuLu may require approval. Record that condition; do not replace the runner or relax gates.\n\nFor current lint, usable readiness is a validated fixture `lint --check` followed by the expected real finding\u002Fexit; `--version` alone proves identity only. The current process registers signals with `sunstack: ready`. For historical routes, keep their old readiness string.\n\nRead-only health check: compare the target identity again, confirm the selected harness and fixtures exist, and check prerequisites without displaying credentials. The local test result must contain nonzero executed tests. For historical protocol replay, the CLI's `sunstack-rule: ready` line witnesses signal registration; usable readiness requires a completed `operation_result` envelope with the expected outcome and actual exit, not `--help` or the ready line alone. V11 requires a completed validated public-API decision run with receipt. Before historical hosted CLI replay, run the signing preflight in `references\u002Fmilestone-1.md`; afterwards inspect every hosted child's `stderr.log` for the runner's `runs unsigned` warning and apply that route's host signing\u002Fegress classification. That warning cannot stop the child's dispatch, and `--fail-fast` does not act on it.\n\n## Evidence, cleanup and return\n\nKeep run evidence in an assignment-authorized directory under system temp, conventionally `yyyy-mm-rule-engine-verify-\u003Crun-id>\u002F`. Record the absolute directory on the work thread. Store the exact command, working directory, product\u002Fdesign revisions, configuration, exit code, test counts\u002Frun ID, raw output and safe receipts. For process runs keep stdin fixtures, stdout JSON and stderr separately, plus report\u002Fcursor readbacks. Use synthetic\u002Fpublic fixtures: results may contain selected evidence.\n\nSupply `OPENROUTER_API_KEY` from the owner's secret store only for the hosted command. Keep the value in process memory; disable shell tracing. Never put a credential value, its location or a secret reference into this skill, artifacts or reports. A missing credential or a skipped hosted test leaves the claim **unknown**. Controlled HTTP proves transport behavior and leaves hosted inference open.\n\nPreserve failures and LEAK counts before any rerun. Interpret LEAK markers only through the disposition in `references\u002Flibrary-gates.md`; the gate remains nextest exit 0. Product failures go to the paired Implementer; disputed expectations and target changes go to the Lead. Repair only assigned verification apparatus.\n\nThese commands start no persistent service. Await each owned test\u002Fprocess; its harness owns fixture\u002Fserver teardown. Stop only a process this run started, using its recorded PID\u002Fsession, and never by name. Leave shared Cargo caches and other sessions alone. Retain evidence; delete only owned disposable files when authorized, with directory removal requiring explicit permission. After cleanup, reopen the receipt\u002Flog and verify it survived.\n\nReturn each scoped V\u002FU claim as **supported**, **unsupported** or **unknown**, with observed\u002Freused\u002Fdraft coverage, target, command\u002Fresults and evidence path. Reuse earlier evidence only when its product source, dependencies, configuration and exercised route still match. Name all stand-ins, unobserved entry points and draft prerequisites. This recipe reports evidence; the Lead owns acceptance, and no release or production hook claim follows.\n","# Verify Sunstack Rule\n\nVerify a named target against the adopted Specification, then report only the outcomes observed there. A passing build, an HTTP success or an unfavorable rule verdict each means something different.\n\nThe current runner is `sunstack`: `lint` calls the `sunstack-lint` library and the evidence\u002Frules\u002Fdecisions engine; `exec` carries the engine protocol. Evidence owns capture and selection, decisions owns Jev transport and answer admission, rules owns applicability\u002Fgrouping\u002Fverdicts, lint owns repository configuration and reporting, and the binary owns command dispatch, signals and exits. Historical routes below drive the earlier `sunstack-rule` process. There is no daemon; npm is an install\u002Flaunch channel.\n\n## Choose the target and journey\n\n1. From the monorepo root, record `git rev-parse --show-toplevel`, `git branch --show-current`, `git rev-parse HEAD` and `git status --short`. Record the declared product commit, build location, configuration and calling client. Confirm the driven checkout matches that product commit; the skill may be on a separate branch. Stop if the target changes during observation.\n2. For **historical replay of the legacy V\u002FUS routes**, the adopted oracle is design revision `f259d4b28f5131478e574e123335904c78b0d347`. Product target: `592293254239d301c53cd25fcb5b106f21cbfb59`. Read oracle files with `git show \u003Cdesign revision>:\u003Crepo-relative-path>`, except `docs\u002Fspecs\u002F2026-10-12-rust-rule-engine\u002Fschemas\u002Frule-invocation.schema.json` and `docs\u002Fspecs\u002F2026-10-12-rust-rule-engine\u002Fschema-inventory.md`, which use adopted schema revision `fc754c8335963bf809dad7472109a81dc29c3c2b`. Start with `git show f259d4b28f5131478e574e123335904c78b0d347:docs\u002Fspecs\u002F2026-10-12-rust-rule-engine\u002Fspecification.md`, especially the selected V rows; use the design revision for `program-design.md`, `program-design-contracts.md`, `program-design-connected-evidence.md`, referenced examples and other schemas. Product design copies may be older and a design working tree may have moved. If a pinned object is unavailable, return that source gap; resolve conflicting expectations with the commissioning Lead before driving the affected case. The Markdown-rule route below takes its product target and adopted design from its commission and reference instead.\n3. Select the route below and read it. A draft has an open target prerequisite and is not a passing observation; drive its first run only under a declared-target commission once its prerequisites are met.\n\nSKILL.md owns target policy. A historical replay is runnable only at its recorded product\u002Foracle contract and proves nothing about the current product. Keep its fixture vocabulary, source guards and receipts together. Current routes use `error`, `warn`, `warn_above_band` and `error_at_or_below`; old inputs occur only in refusal controls. Current U3 `exec` proof comes from the declared target's real workspace\u002Fprocess suite, not a historical replay. A shared transport helper has no severity policy.\n\n| Surface                                                                                                              | Route and driver                                                                                                                           | Product target                                                                                                   | Oracle                                                                                                      | Availability                                                                                                                                               |\n| -------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Selection candidate\u002Fshared cut fields | `references\u002Fselection-cuts.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fselection-cuts\u002Fselection-cuts.ts` | declared signed0.16 candidate and released0.15.1; headed P3 plus J1\u002Fai-tools | 0.16 selection-cut commission\u002FCorrection1; exact added vectors\u002Fhashes and unchanged rule reports | operable; candidate\u002Fshared metadata and rule parity exercised; repeat per target and join native\u002FSDK proof |\n| Native section heading labels and P3 paths | `references\u002Fheading-text.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fheading-text\u002Fheading-text.ts` | declared signed0.15.1 candidate and released0.15.0, fixed13HTML\u002F10Markdown pages | 0.15.1 heading-text commission Corrections1–5; source-derived labels\u002Fspans and version-only additive parity | operable; source paths, own headings and legacy parity exercised; repeat per target and join native\u002FSDK proof |\n| Configured conventions and standard defaults | `references\u002Fconfig-only.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fconfig-only\u002Fconfig-only.ts` | declared signed0.15 candidate and released0.14.1; fixed actual J1\u002FHTML\u002FMarkdown\u002Fai-tools inputs | 0.15 config-only commission Corrections1–7; exact config snapshot exception and parser-located released witness | operable; configured\u002Fdefault signed CLI exercised; repeat per target and join native\u002FSDK proof |\n| Installed SDK codec, direct inspection and examples | `references\u002Fsdk-journeys.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fsdk\u002Fsdk-verify.ts` (`codec`, `inspection`, `examples`) | declared quiescent candidate and fresh pinned installed package\u002Faddon | commission's agent-usability specification and verification design | operable; exercised on 0.19\u002Frevision 13 with partial receipts; repeat per target and retain provider, in-flight cancellation and fault limits |\n| Installed TypeScript SDK: load\u002Fedit, inline\u002Fnative parity, cancellation, six-cell installation and ordinary provider | `references\u002Fsdk-journeys.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fsdk\u002Fsdk-verify.ts`                                                             | declared quiescent integrated head, fresh installed package\u002Faddon\u002Ftarball hashes and exact Node\u002FOS\u002FCPU\u002Flibc cell | 11 Nov TypeScript SDK R1–R15 and O1–O6, including native 0.14 HTML\u002FMarkdown units and absolute checked root | draft; apparatus sensitivity tests are not SDK observations; missing native, CLI, install and provider joins remain explicit                               |\n| HTML asking, cross-document coverage and checked root                                                                | `references\u002Fhtml-evidence.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fhtml-evidence\u002F{html-evidence,markdown-parity,checked-root}.ts`                | declared signed0.13 candidate for asking\u002Fcoverage; companion targets and comparators explicitly commissioned     | 0.11 mechanics plus0.13 HTML asking projection; pinned real corpus and original consumer config             | asking\u002Fcoverage operable; declared-target pass and native joins required; companions need their own commissioned joins                                     |\n| HTML lexical sections and complete asking text                                                                       | `references\u002Fhtml-sections.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fhtml-sections\u002Fsections.ts`                                                    | declared signed0.13 candidate, full head\u002Fdigest; three fixed real HTML inputs                                    | 0.13 HTML-sections commission Proof1–3\u002FCorrections1–7; lexical h1–h6 outline                                | operable; recovered headings, original outlines and exact asking text exercised; repeat per target                                                         |\n| HTML asking text and truthful incomplete fields | `references\u002Fhtml-sections.md`0.14.1; `scripts\u002Fverify\u002Fsunstack-rule\u002Fhtml-sections\u002Ferror-text.ts` | declared signed0.14.1 candidate and released0.14.0 comparator; frozen source tables and original projects | 0.14.1 commission Corrections1–13; source-derived text and exact report boundary | operable;43J1 cases, real arrow\u002Fampersand pages,114sections,499requests, Markdown parity and unsafe cuts exercised; repeat per target |\n| Markdown fragment anchors and section fields                                                                         | `references\u002Fmarkdown-sections.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fmarkdown\u002F{capture,anchors,github-samples}.ts`                             | declared signed0.14 candidate, full head\u002Fdigest; fixed two-repository corpus                                     | 0.14 commission\u002FCorrections1–9; independent264link and74section oracle, actual GitHub IDs                   | operable; original corpus, sections, image-heading\u002Fordinary raw-asking controls exercised; native\u002Fparity joins stay separate                               |\n| Deferred document admission                                                                                          | `references\u002Fhtml-evidence.md` admission section; `scripts\u002Fverify\u002Fsunstack-rule\u002Fhtml-evidence\u002Fdocument-admission.ts`                        | declared signed admission correction, full head and digest                                                       | Correction7; preserve existing Target diagnostics and local\u002Fplain Document positives                        | operable; keyless --check only, no selected dispatch                                                                                                       |\n| Public exec Choice255\u002F256 boundary                                                                                   | `references\u002Flocator-limits.md` public exec section; `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Fexec-choice-limits.ts`                          | declared signed F1–F3 correction candidate, full head and binary SHA256                                          | Lead correction disposition; decisions-owned Choice cap255                                                  | operable; both public decision API and filter native joins checked per target                                                                              |\n| Locator Choice cap and omission evidence                                                                             | `references\u002Flocator-limits.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Flocator-limits.ts`                                                  | declared signed locator-limit candidate, full head and binary SHA256                                             | 6 Nov locator-limit commission\u002FLead disposition; nudge R2\u002FC2; provider Choice maximum255                    | operable; direct-SDK refusal\u002Fschema joins checked per target                                                                                               |\n| Filters: tree routes and shared gates (O4)                                                                           | `references\u002Frulebook-lint.md` filters section; `rulebook-lint.ts --case filters` and `rulebook-filters.ts`                                 | declared signed decision-trees candidate, full source commit and binary SHA256                                   | decision-trees Specification\u002FPD\u002FVD at `0567445`, O4                                                         | operable; confirm target and native joins per run                                                                                                          |\n| Changed-only capture, original input and raw-identity edges                                                          | `references\u002Fgit-first.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fgit-first\u002F{git-first-original,git-first-edges}.ts`                                | declared signed0.12 main\u002Ftest artifacts, full source head and digests; released0.11.1 comparator                 | 0.12 commission Proof1–4\u002FCorrection2 raw identity, prepared success6                                        | operable at5b4965ba; original\u002Ffull oracle, declared native consumer and owned edges observed; repeat per target                                            |\n| --since beside equal binary assets                                                                                   | `references\u002Fsince-encoding.md`; current route uses `git-first-edges.ts`; legacy `rulebook-since-encoding.ts` is0.10.1-only                 | current declared0.12 artifacts or separately commissioned historical0.10.1\u002F0.10.0 replay                         | raw binary\u002Fsymlink\u002Fbyte-budget contracts; Full versus ChangedOnly context is explicit                       | current coverage joins candidate-identity route; historical replay remains pinned                                                                          |\n| Rule-author usability and keyless empty scope                                                                        | `references\u002Flint-usability.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fusability\u002Fprobe.ts`                                                          | declared signed0.12.1 candidate, full head\u002Fdigest; released0.12.0 and detached probe input                       | 0.12.1 usability commission U1–U6\u002FCorrections1–4                                                            | operable at245eb9c3;8probe rows\u002F28CLI children,10native boundary controls and exact prepare-report parity observed; repeat per target                      |\n| Human unsure summaries and output preservation                                                                       | `references\u002Funsure-summary.md`; `rulebook-unsure-summary.ts`                                                                               | declared signed candidate and immutable comparator bytes\u002Fversion\u002Fprovenance                                      | 8 Nov 0.10 unsure-summary commission; current CLI human-output contract                                     | operable; strict same-version and released-version comparison are separate runs                                                                            |\n| Short output, saved report and cases (O5\u002FO6)                                                                         | `references\u002Fdecision-trees.md`; `rulebook-report.ts` and `rulebook-cases.ts`                                                               | declared decision-trees source commit and signed binary SHA256                                                   | decision-trees Specification\u002FPD\u002FVD at `2fea595` (exact ranges and distinct owner-ruling)                    | operable; scripted journey, keyed run separate                                                                                                             |\n| Completed cases readback and change-scope error paths                                                                | `references\u002Fcli-report-errors.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fcli-reports\u002F{show-reports,change-scope-errors}.ts`                        | declared signed0.11.1 candidate, full head and SHA256; frozen real R03 report                                    | 0.11.1 commission Outcomes1–3\u002FCorrections1–2; completed candidate union versus preserved prepared ordinals  | C1 observed6fd3aaaa (37 CLI invocations); C2 show observeda59cf64e (22); unchanged scope reused with explicit dependency comparison and fresh native joins |\n| Current nudge admission refusals                                                                                     | `references\u002Frulebook-check-refusals.md`; `rulebook-check-refusals.ts --case nudge`                                                         | declared signed current source commit and binary SHA256                                                          | 31 Oct S2 plus decision-trees `2fea595` and Lead identical-versus-conflicting locator disposition           | operable; two acceptance controls and ten zero-request refusals; join native identical-reuse positive                                                      |\n| Rules-as-nudges report: U1-U10                                                                                       | `references\u002Frulebook-lint.md` and `rulebook-check-refusals.md`, both `--case nudge`; `rulebook-nudge-compatibility.ts` for U10             | declared signed 0.6.0 release build; signed 0.5.0 artifact for comparison                                        | 31 Oct engine Specification\u002FVD accepted at `a69fe47`; locator-order clarification `6328647`                 | S1\u002FS2\u002FU10 observed at `ffd86f5`; native S3 joins required; keyed S4 separate                                                                               |\n| Prepare exact requests without dispatch                                                                              | `references\u002Fprepare-requests.md`; `scripts\u002Fverify\u002Fsunstack-rule\u002Fprepare\u002Fprepare-requests.ts`                                               | declared 0.9 source and immutable binary SHA256                                                                  | 7 Nov prepare commission, Admission, Addition 2, F1\u002FF2 and whole-view pending policy                        | historical fixture observation at `73d7fc78`; every current target must drive F1\u002FF2\u002Fprojection\u002Freplay-allowance controls; paid comparison separate         |\n| Rust quality\u002Fnative consumers                                                                                        | `references\u002Flibrary-gates.md`                                                                                                              | commission-declared committed source                                                                             | commission-declared contract                                                                                | scoped source\u002Ftest proof; historical receipts need applicability                                                                                           |\n| Within a union of kinds: amended U14\u002FU16, W6                                                                         | `references\u002Fwithin-kinds.md`; selection-mode lint\u002Frefusal entries and `scripts\u002Fverify\u002Fsunstack-rule\u002Fselection\u002Fwithin-kinds-equivalence.ts` | declared within-kinds frozen source\u002Fbinary; frozen v0.3.0 for one-item comparison                                | amended R30\u002FR40 and U14\u002FU16 at `9dfdb10` + `a4696af` + `2198c47`, W1–W6 and path-policy amendments          | c3 WI2\u002Flocal paths observed at `4086bcc1`; c1 union\u002FW6 reused with applicability                                                                           |\n| Evidence selection: U13–U17, R42                                                                                     | `references\u002Fevidence-selection.md`; rulebook lint and check-refusal entries with `--case selection`; temporary compatibility probe         | commission-declared S3 source\u002Fbinary; npm 0.2.0 plus frozen kit for R42                                          | 30 Oct evidence-selection Specification and Verification Design                                             | observed locally at `7315762`, native concurrency addendum `5d7c070`; live V21 separate                                                                    |\n| Rulebook lint: U2\u002FU5\u002FU8\u002FU10\u002FU12                                                                                      | `references\u002Frulebook-lint.md`, repo `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Frulebook-lint.ts` and `rulebook-boundaries.ts`                  | declared stable S3 head and local binary                                                                         | 29 Oct skill-rules Specification and Verification Design, including Lead's F1–F3 proof clarifications       | observed locally at `42f40e6`; native joins required at each target                                                                                        |\n| Rulebook check refusals: U9                                                                                          | `references\u002Frulebook-check-refusals.md`, repo `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Frulebook-check-refusals.ts`                           | same declared stable S3 head and local binary                                                                    | same 29 Oct rulebook oracle, R24 inventory                                                                  | observed locally at `42f40e6`; structural check call-path join required at each target                                                                     |\n| Historical V11 \u002F V22 \u002F V34 hosted                                                                                    | `references\u002Fhosted-decisions.md` native sections                                                                                           | historical product pin above                                                                                     | historical design\u002Fschema pins above                                                                         | historical replay; explicit hosted grant still required                                                                                                    |\n| Historical executable V2\u002FV13                                                                                         | `references\u002Fexecutable-operations.md`                                                                                                      | historical product pin above                                                                                     | historical design\u002Fschema pins above                                                                         | historical replay only                                                                                                                                     |\n| Historical skill\u002Fhandoff V14\u002FV29\u002FV30                                                                                 | `references\u002Fmilestone-1.md`                                                                                                                | historical product pin above                                                                                     | historical design\u002Fschema pins above                                                                         | historical replay; proof remains verbatim                                                                                                                  |\n| Historical Git\u002Fconnected V rows                                                                                      | `references\u002Fmilestone-2.md`                                                                                                                | historical product pin above                                                                                     | historical design\u002Fschema pins above                                                                         | historical replay only                                                                                                                                     |\n| Historical usage US routes                                                                                           | `references\u002Fusage-scenarios.md`, `scripts\u002Fusage_scenarios.py`                                                                              | historical product pin above; enforced by driver                                                                 | historical design\u002Fschema pins above                                                                         | local replay; genuine slots remain disabled                                                                                                                |\n| Historical Markdown U1–U9                                                                                            | `references\u002Fmarkdown-skill-rules.md`, repo `scripts\u002Fverify\u002Fsunstack-rule\u002F`                                                                 | reference's declared S2 `7c529b4b` \u002F S4 `bdca8d9a`                                                               | reference's adopted Markdown revisions                                                                      | pre-runner replay, old binary\u002Freadiness; no current `exec` claim                                                                                           |\n| S1 lint runner                                                                                                       | `references\u002Flint-runner.md`, repo `scripts\u002Fverify\u002Fsunstack-rule\u002Frulebook\u002Flint-runner-rulebook.ts`                                          | declared local S3 rulebook binary                                                                                | 29 Oct rulebook oracle, retained runner formats\u002Fexits\u002Fscopes                                                | observed locally at `42f40e6`; legacy RuleSet fixture\u002Fschema helpers are historical proof                                                                  |\n| S2 standalone containers, U8\u002FU9                                                                                      | `references\u002Fcontainer-matrix.md`, `scripts\u002Fcontainer_matrix.py`                                                                            | declared four release artifacts and SHA256s                                                                      | same runner oracle                                                                                          | historical fixture shape; rulebook upkeep and a declared artifact are required before a current offline matrix                                             |\n| S3 genuine static Linux Jev, rulebook U6                                                                             | `references\u002Fhosted-decisions.md` S3, repo `scripts\u002Fverify\u002Fsunstack-rule\u002Fhosted\u002Fhosted-lint.ts`                                             | declared static Linux arm64 release artifact\u002FSHA256\u002Fversion\u002Fcommit                                               | 29 Oct rulebook U6 plus retained no-CA runner contract                                                      | draft; separately commissioned paid command                                                                                                                |\n| S4 private release installs, U2\u002FU8\u002FU10\u002FU11                                                                           | `references\u002Frelease-rehearsal.md`, `scripts\u002Frelease_assets.py` and repo `scripts\u002Fverify\u002Fsunstack-rule\u002Frelease\u002F` drivers                    | two declared normal-version private releases; exact scoped package\u002Fsource\u002Fbytes                                  | all-channel stream\u002Fstop oracle `8cf9c51` or commission-declared successor                                   | draft until every channel\u002Fplatform cell observed; private registry\u002FCI tap, public npm publishing excluded                                                  |\n\nIF source\u002Fnative tests or Rust quality gates are in scope, load `references\u002Flibrary-gates.md` and return the scoped commands, results and remaining coverage. Artifact-only observations do not launch an unrelated Cargo suite.\nIF installed TypeScript SDK behavior is commissioned, load `references\u002Fsdk-journeys.md` and return each selected O row's installed consumer, exact artifact\u002Fcell identity, actual requests\u002Foutcomes and required native\u002FCLI\u002Finstall joins. Do not claim SDK coverage from the existing CLI npm channel, source-only prototype, apparatus tests or a cross-compiled addon. Provider execution needs its own explicit grant.\n\nCurrent rulebook journeys run directly with `node \u003Cdriver>.ts`; Zod validates external data. No Python wrapper or runtime is used for these routes. Their apparatus checks, from the monorepo root, are `pnpm exec tsc -p scripts\u002Fverify\u002Fsunstack-rule\u002Ftsconfig.json`, `pnpm exec oxlint --type-aware --type-check --tsconfig scripts\u002Fverify\u002Fsunstack-rule\u002Ftsconfig.json --max-warnings 0 scripts\u002Fverify\u002Fsunstack-rule\u002F**\u002F*.ts`, `pnpm exec oxfmt --check scripts\u002Fverify\u002Fsunstack-rule\u002F**\u002F*.ts scripts\u002Fverify\u002Fsunstack-rule\u002Ftsconfig.json`, and `pnpm exec vitest run scripts\u002Fverify\u002Fsunstack-rule\u002F**\u002F*.test.ts`, and `node --test scripts\u002Fverify\u002Fsunstack-rule\u002Frelease\u002F*-test.ts`. Historical Python drivers below are retained for their separate migration phase.\nIF historical hosted V11 replay is in scope, load `references\u002Fhosted-decisions.md` and return its run identity, validated completion and receipt, or its access\u002Fsetup gap.\nIF historical genuine V22 or V34 replay is in scope, load `references\u002Fhosted-decisions.md` and return the hosted-rules observation or applicable reused evidence, native answer\u002Freceipt checks and any remaining gap.\nIF historical executable V2\u002FV13 replay is in scope, load `references\u002Fexecutable-operations.md` and return the operation coverage, process evidence and remaining proof limits.\nIF historical milestone 1 replay is in scope, load `references\u002Fmilestone-1.md` and return each local\u002Fhosted journey's report, measurement or named prerequisite.\nIF historical change-scope or connected-evidence replay is in scope, load `references\u002Fmilestone-2.md` and return each scoped V5\u002FV7\u002FV16–V18 claim and the V20 related-units portion as **supported**, **unsupported** or **unknown**, with observed\u002Freused\u002Fdraft coverage, target and evidence path, per the Evidence, cleanup and return rule below.\nIF historical usage-scenario replay is in scope, load `references\u002Fusage-scenarios.md` and return each selected US ID's supported\u002Funsupported\u002Funknown verdict, observed\u002Freused coverage, relevant V rows, target, process\u002FHTTP evidence and remaining gap, using the return rule below.\nIF retained Markdown\u002Fnative proof or reconstruction of a historical marker replay is commissioned, load `references\u002Fmarkdown-skill-rules.md` and return each retained proof home and applicable current-target run, or the historical source\u002Ftarget prerequisite. Retired marker drivers do not run against the current rulebook target.\n\nIF current changed-only `--since` or default uncommitted capture is in scope, load `references\u002Fgit-first.md`; return original-command preparation, exact full-oracle owners\u002Frequests, public-API raw paths\u002Facquisition counts, edge\u002Fdefault controls and readonly-input guards or named gaps.\nIF `lint --since` capture or unchanged binary assets are in scope, load `references\u002Fsince-encoding.md` and return changed-piece selection, selected-encoding refusals, binary-free byte parity, native budget\u002Fsnapshot joins and original-input observations or named gaps.\nIF HTML asking ERROR recovery is commissioned, load `references\u002Fhtml-sections.md`'s0.14.1 route and run `html-sections\u002Ferror-text.ts`; return the43-case real source scan, original114-section, Markdown-anchor and ai-tools499-request parity, ampersand preservation, unsafe cuts, exact allowed diffs and native joins or named gaps.\nIF HTML heading sections, own\u002Fenclosing text, diagram attributes or element boundaries are commissioned, load `references\u002Fhtml-sections.md`; return the three pinned outline comparisons, prepared\u002Fcut controls and native parity\u002Fadmission joins or named gaps.\nIF Markdown fragment anchors or markdown_units section fields are commissioned, load `references\u002Fmarkdown-sections.md`; return every original link state, actual rendered GitHub samples, real\u002Fcontainer section spans, admission refusals and native\u002Fparity joins or named gaps.\nIF HTML evidence, cross-document ID checks or explicit checked-root behavior is commissioned, load `references\u002Fhtml-evidence.md`; return each real R\u002FE owner, prepared text\u002Fraw span, fragment result, root refusal and absolute-path control, exact Markdown comparator\u002Finput identities and remaining native or provider gaps.\nIF keyless empty-scope lint, config-open diagnostics, status summaries, named scope, help or prepared-output usability is commissioned, load `references\u002Flint-usability.md`; return the8real probe outcomes, zero\u002Fdirty eligibility controls, prepared request\u002Fpath summaries, unchanged JSON reports and native no-evidence joins or named gaps.\nIF current lint behavior is commissioned, load `references\u002Flint-runner.md` and return the selected case counts, finding\u002Fexit comparisons, target identity, native-proof joins and remaining gaps.\nIF locator option limits or omitted-location reporting are commissioned, load `references\u002Flocator-limits.md` and return exact255-boundary, wire criteria, reached-result evidence and native refusal\u002Fschema joins at the declared target.\nIF default human unsure summaries or cross-version output preservation are commissioned, load `references\u002Funsure-summary.md`; report per-rule counts\u002Fpointers, all-format\u002Freport byte comparisons, every result ID readback, exact version exceptions and comparator provenance.\nIF completed cases-report readback or change-scope refusal paths\u002Flimits are commissioned, load `references\u002Fcli-report-errors.md`; return real R03 unique\u002Fcase\u002Fambiguous lookups, preserved ordinary\u002Fprepared details, offending path fields in human\u002FJSON\u002FSARIF, configured limit values and native SourceChanged joins or named gaps.\nIF decision-trees output, saved reports or case runs are commissioned, load `references\u002Fdecision-trees.md`; report each O row with its declared target, actual output and open gaps. Keyed\u002Fmodel calls need a separate commission.\nIF filters or `only_when` are commissioned, load the filters section of `references\u002Frulebook-lint.md` and return the exact folder\u002Frequest\u002Fresult\u002Fskip comparisons, process exits, candidate identity and native joins or gaps. The scripted answers establish mechanics, not classification accuracy.\nIF evidence selection, containment, candidate reports or 0.2.0 compatibility is commissioned, load `references\u002Fevidence-selection.md` and return U13–U17 plus R42 coverage, exact candidate\u002Frequest\u002Fcount comparisons, native joins and remaining live\u002Ftarget gaps.\nIF amended R30 list containment is commissioned, load `references\u002Fwithin-kinds.md` and return union\u002Fonce-only and not-selected fallback, every new R40 refusal\u002Flisting, W6 equality with planted rejection, and native schema\u002Fplan proof or gaps.\nIF the 29 Oct rulebook evidence, decision or change-scope journey is commissioned, load `references\u002Frulebook-lint.md` and return each scoped U row's observed\u002Freused evidence, exact target and native joins or gaps.\nIF the 29 Oct rulebook check\u002Frefusal journey is commissioned, load `references\u002Frulebook-check-refusals.md` and return clean acceptance, every executed refusal's diagnostic\u002Fexit, zero-request\u002FFIFO observations and structural check call-path join or gaps.\nIF standalone portability is commissioned, load `references\u002Fcontainer-matrix.md` and return each distro\u002Farchitecture cell, exact binary linkage\u002Fhash, command exits and remaining macOS\u002FCargo-feature proof.\nIF the current no-CA hosted judgment is commissioned, load `references\u002Fhosted-decisions.md` S3 and return its genuine verdict, typed answers\u002Fevidence\u002Fusage, exact target and safe evidence or setup gap.\nIF private install\u002Frelease behavior is commissioned, load `references\u002Frelease-rehearsal.md` and return two normal-tag artifact\u002Fjob\u002Ftap evidence, registry-resolved local-bin\u002Fexec-script\u002Fglobal\u002Fbare-npx\u002Fexec-npx\u002Fpnpm-dlx and native-channel bytes\u002Fversion\u002Freport\u002Fexit\u002Fsignal transcripts, fresh-runner coverage, real Actions exec\u002Fplain cancellation records and unobserved cells.\n\nFor every selected route, check its prerequisites and readiness, drive only commissioned actions, compare the deciding outcome, preserve evidence, stop owned resources and report supported\u002Funsupported\u002Funknown. A prepared fixture or missing binary is never a product pass. A draft route may be driven in a separately commissioned first observation; it becomes observed only for the target and cases actually run.\n\nFor the historical selected usage scenario, run the selector from the monorepo root. The reference owns the inventory and prerequisites; repeat `--journey` only for requested IDs:\n\n```sh\nenv -u PYTHONOPTIMIZE -u UV_INDEX -u UV_EXTRA_INDEX_URL -u UV_INDEX_URL -u UV_FIND_LINKS -u PIP_INDEX_URL -u PIP_EXTRA_INDEX_URL -u UV_DEFAULT_INDEX -u UV_CONFIG_FILE -u UV_ENV_FILE \\\n  UV_CACHE_DIR=\u003Cauthorized-evidence>\u002Fuv-cache PYTHONDONTWRITEBYTECODE=1 \\\n  uv run --no-config --no-env-file --no-python-downloads --default-index https:\u002F\u002Fpypi.org\u002Fsimple --locked --script \\\n  .agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fusage_scenarios.py \\\n  --binary \u003Cdeclared-binary> --evidence \u003Cauthorized-evidence> --journey \u003CUS-ID>\n```\n\n## Build and readiness\n\nRun Cargo from the monorepo root with the pinned toolchain in `rust-toolchain.toml`. On macOS this host needs a command-local SDK correction for C dependencies:\n\n```sh\nSDKROOT=\"$(xcrun --show-sdk-path)\" CC=\u002Fusr\u002Fbin\u002Fclang CFLAGS=\"-isysroot $(xcrun --show-sdk-path)\" cargo build --workspace\n```\n\nUse that same prefix on **every Cargo command** shown in the references on this host. Do not change global compiler settings. Other platforms use their declared native toolchain; they are separate, unobserved targets.\n\nOn Apple Silicon, `.cargo\u002Fconfig.toml` routes Cargo\u002Fnextest execution through `scripts\u002Fcargo-debug-signing-runner.sh`. It gives the app and tests stable, separate debug identities. Signing is best effort: a warning means the original binary still runs and LuLu may require approval. Record that condition; do not replace the runner or relax gates.\n\nFor current lint, usable readiness is a validated fixture `lint --check` followed by the expected real finding\u002Fexit; `--version` alone proves identity only. The current process registers signals with `sunstack: ready`. For historical routes, keep their old readiness string.\n\nRead-only health check: compare the target identity again, confirm the selected harness and fixtures exist, and check prerequisites without displaying credentials. The local test result must contain nonzero executed tests. For historical protocol replay, the CLI's `sunstack-rule: ready` line witnesses signal registration; usable readiness requires a completed `operation_result` envelope with the expected outcome and actual exit, not `--help` or the ready line alone. V11 requires a completed validated public-API decision run with receipt. Before historical hosted CLI replay, run the signing preflight in `references\u002Fmilestone-1.md`; afterwards inspect every hosted child's `stderr.log` for the runner's `runs unsigned` warning and apply that route's host signing\u002Fegress classification. That warning cannot stop the child's dispatch, and `--fail-fast` does not act on it.\n\n## Evidence, cleanup and return\n\nKeep run evidence in an assignment-authorized directory under system temp, conventionally `yyyy-mm-rule-engine-verify-\u003Crun-id>\u002F`. Record the absolute directory on the work thread. Store the exact command, working directory, product\u002Fdesign revisions, configuration, exit code, test counts\u002Frun ID, raw output and safe receipts. For process runs keep stdin fixtures, stdout JSON and stderr separately, plus report\u002Fcursor readbacks. Use synthetic\u002Fpublic fixtures: results may contain selected evidence.\n\nSupply `OPENROUTER_API_KEY` from the owner's secret store only for the hosted command. Keep the value in process memory; disable shell tracing. Never put a credential value, its location or a secret reference into this skill, artifacts or reports. A missing credential or a skipped hosted test leaves the claim **unknown**. Controlled HTTP proves transport behavior and leaves hosted inference open.\n\nPreserve failures and LEAK counts before any rerun. Interpret LEAK markers only through the disposition in `references\u002Flibrary-gates.md`; the gate remains nextest exit 0. Product failures go to the paired Implementer; disputed expectations and target changes go to the Lead. Repair only assigned verification apparatus.\n\nThese commands start no persistent service. Await each owned test\u002Fprocess; its harness owns fixture\u002Fserver teardown. Stop only a process this run started, using its recorded PID\u002Fsession, and never by name. Leave shared Cargo caches and other sessions alone. Retain evidence; delete only owned disposable files when authorized, with directory removal requiring explicit permission. After cleanup, reopen the receipt\u002Flog and verify it survived.\n\nReturn each scoped V\u002FU claim as **supported**, **unsupported** or **unknown**, with observed\u002Freused\u002Fdraft coverage, target, command\u002Fresults and evidence path. Reuse earlier evidence only when its product source, dependencies, configuration and exercised route still match. Name all stand-ins, unobserved entry points and draft prerequisites. This recipe reports evidence; the Lead owns acceptance, and no release or production hook claim follows.\n",{"name":5,"description":7},"main","dd78d12c5562758ae581f1dedccb0e09d2290154",".agents\u002Fskills\u002Fverify-sunstack-rule","https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools","https:\u002F\u002Fgithub.com\u002FShravanSunder","💻 Staff AI Engineer @ Relay Financial;   \r\n🪙 Exploring AI Agents","2026-11-15 01:43:51",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add ShravanSunder\u002Fsunstack-tools --skill verify-sunstack-rule",{"tool":37,"command":38},"bunx","bunx skills add ShravanSunder\u002Fsunstack-tools --skill verify-sunstack-rule",{"tool":40,"command":41},"pnpm","pnpm dlx skills add ShravanSunder\u002Fsunstack-tools --skill verify-sunstack-rule","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002FSKILL.md",true,[45,51,55,59,63,67,71,75,79,83,87,91,95,99,103,107,111,115,119,123,127,131,135,139,143,147,151,155,159,163,169,173,177,181,185,189,193,197,201,205,209,213,217,221,225,229,233,237,241,245,249,253,257,261,265,269,273,277,281,285,289,293,297,301],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fcli-report-errors.md","REFERENCE","参考文档",10394,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fcli-report-errors.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fconfig-only.md",7570,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fconfig-only.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fcontainer-matrix.md",4025,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fcontainer-matrix.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fdecision-trees.md",9528,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fdecision-trees.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fevidence-selection.md",13803,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fevidence-selection.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fexecutable-operations.md",10632,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fexecutable-operations.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fgit-first.md",9241,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fgit-first.md",{"path":76,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fheading-text.md",8753,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fheading-text.md",{"path":80,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fhosted-decisions.md",14471,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fhosted-decisions.md",{"path":84,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fhtml-evidence.md",11262,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fhtml-evidence.md",{"path":88,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fhtml-sections.md",17024,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fhtml-sections.md",{"path":92,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Flibrary-gates.md",9839,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Flibrary-gates.md",{"path":96,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Flint-runner.md",5838,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Flint-runner.md",{"path":100,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Flint-usability.md",8646,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Flint-usability.md",{"path":104,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Flocator-limits.md",8980,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Flocator-limits.md",{"path":108,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":109,"sourceHtmlUrl":110},"references\u002Fmarkdown-sections.md",11118,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fmarkdown-sections.md",{"path":112,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":113,"sourceHtmlUrl":114},"references\u002Fmarkdown-skill-rules.md",2910,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fmarkdown-skill-rules.md",{"path":116,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":117,"sourceHtmlUrl":118},"references\u002Fmilestone-1.md",11301,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fmilestone-1.md",{"path":120,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":121,"sourceHtmlUrl":122},"references\u002Fmilestone-2.md",18251,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fmilestone-2.md",{"path":124,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":125,"sourceHtmlUrl":126},"references\u002Fprepare-requests.md",12914,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fprepare-requests.md",{"path":128,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":129,"sourceHtmlUrl":130},"references\u002Frelease-rehearsal.md",17432,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Frelease-rehearsal.md",{"path":132,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":133,"sourceHtmlUrl":134},"references\u002Frulebook-check-refusals.md",9035,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Frulebook-check-refusals.md",{"path":136,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":137,"sourceHtmlUrl":138},"references\u002Frulebook-lint.md",19301,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Frulebook-lint.md",{"path":140,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":141,"sourceHtmlUrl":142},"references\u002Fsdk-journeys.md",79259,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fsdk-journeys.md",{"path":144,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":145,"sourceHtmlUrl":146},"references\u002Fselection-cuts.md",7867,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fselection-cuts.md",{"path":148,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":149,"sourceHtmlUrl":150},"references\u002Fsince-encoding.md",6861,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fsince-encoding.md",{"path":152,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":153,"sourceHtmlUrl":154},"references\u002Funsure-summary.md",5087,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Funsure-summary.md",{"path":156,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":157,"sourceHtmlUrl":158},"references\u002Fusage-scenarios.md",14240,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fusage-scenarios.md",{"path":160,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":161,"sourceHtmlUrl":162},"references\u002Fwithin-kinds.md",9469,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Freferences\u002Fwithin-kinds.md",{"path":164,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":167,"sourceHtmlUrl":168},"scripts\u002Fcomposition_scenarios.py","SCRIPT","脚本",23988,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fcomposition_scenarios.py",{"path":170,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":171,"sourceHtmlUrl":172},"scripts\u002Fconnected_scenarios.py",17336,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fconnected_scenarios.py",{"path":174,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":175,"sourceHtmlUrl":176},"scripts\u002Fcontainer_matrix.py",9565,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fcontainer_matrix.py",{"path":178,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":179,"sourceHtmlUrl":180},"scripts\u002Fcursor_scenarios.py",9415,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fcursor_scenarios.py",{"path":182,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":183,"sourceHtmlUrl":184},"scripts\u002Fdependency_scenarios.py",20148,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fdependency_scenarios.py",{"path":186,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":187,"sourceHtmlUrl":188},"scripts\u002Ffixtures\u002Fusage-scenarios\u002Fclaude-handoff.jsonl",1609,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Ffixtures\u002Fusage-scenarios\u002Fclaude-handoff.jsonl",{"path":190,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":191,"sourceHtmlUrl":192},"scripts\u002Ffixtures\u002Fusage-scenarios\u002Fcursor-seeds.json",948,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Ffixtures\u002Fusage-scenarios\u002Fcursor-seeds.json",{"path":194,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":195,"sourceHtmlUrl":196},"scripts\u002Ffixtures\u002Fusage-scenarios\u002Ftool-payload.schema.json",436,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Ffixtures\u002Fusage-scenarios\u002Ftool-payload.schema.json",{"path":198,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":199,"sourceHtmlUrl":200},"scripts\u002Fgit_scenario_fixtures.py",10095,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fgit_scenario_fixtures.py",{"path":202,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":203,"sourceHtmlUrl":204},"scripts\u002Fhandoff_scenario.py",11674,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fhandoff_scenario.py",{"path":206,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":207,"sourceHtmlUrl":208},"scripts\u002Fhook_scenarios.py",6905,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fhook_scenarios.py",{"path":210,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":211,"sourceHtmlUrl":212},"scripts\u002Flint_observations.py",14547,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Flint_observations.py",{"path":214,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":215,"sourceHtmlUrl":216},"scripts\u002Frecent_scenarios.py",19007,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frecent_scenarios.py",{"path":218,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":219,"sourceHtmlUrl":220},"scripts\u002Frelease_assets_test.py",3497,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frelease_assets_test.py",{"path":222,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":223,"sourceHtmlUrl":224},"scripts\u002Frelease_assets.py",6178,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frelease_assets.py",{"path":226,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":227,"sourceHtmlUrl":228},"scripts\u002Frunner_containers_test.py",4963,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frunner_containers_test.py",{"path":230,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":231,"sourceHtmlUrl":232},"scripts\u002Frunner_containers.py",5879,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frunner_containers.py",{"path":234,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":235,"sourceHtmlUrl":236},"scripts\u002Frunner_contracts_test.py",24559,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frunner_contracts_test.py",{"path":238,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":239,"sourceHtmlUrl":240},"scripts\u002Frunner_contracts.py",9186,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frunner_contracts.py",{"path":242,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":243,"sourceHtmlUrl":244},"scripts\u002Frunner_fixture_cases.py",24591,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frunner_fixture_cases.py",{"path":246,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":247,"sourceHtmlUrl":248},"scripts\u002Frunner_fixture_setup.py",4602,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frunner_fixture_setup.py",{"path":250,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":251,"sourceHtmlUrl":252},"scripts\u002Frunner_linkage.py",2738,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frunner_linkage.py",{"path":254,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":255,"sourceHtmlUrl":256},"scripts\u002Frunner_process.py",8288,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Frunner_process.py",{"path":258,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":259,"sourceHtmlUrl":260},"scripts\u002Fscenario_checks.py",11484,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fscenario_checks.py",{"path":262,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":263,"sourceHtmlUrl":264},"scripts\u002Fscenario_checks.py.lock",44688,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fscenario_checks.py.lock",{"path":266,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":267,"sourceHtmlUrl":268},"scripts\u002Fscenario_fixtures.py",5723,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fscenario_fixtures.py",{"path":270,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":271,"sourceHtmlUrl":272},"scripts\u002Fscenario_readback_checks.py",19584,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fscenario_readback_checks.py",{"path":274,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":275,"sourceHtmlUrl":276},"scripts\u002Fscenario_runtime.py",8801,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fscenario_runtime.py",{"path":278,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":279,"sourceHtmlUrl":280},"scripts\u002Fscenario_transport.py",5996,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fscenario_transport.py",{"path":282,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":283,"sourceHtmlUrl":284},"scripts\u002Fschema_agreement_test.py",3056,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fschema_agreement_test.py",{"path":286,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":287,"sourceHtmlUrl":288},"scripts\u002Fschema_agreement.py",14096,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fschema_agreement.py",{"path":290,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":291,"sourceHtmlUrl":292},"scripts\u002Fschema_fixtures_test.py",3637,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fschema_fixtures_test.py",{"path":294,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":295,"sourceHtmlUrl":296},"scripts\u002Fschema_fixtures.py",5708,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fschema_fixtures.py",{"path":298,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":299,"sourceHtmlUrl":300},"scripts\u002Fusage_scenarios.py",6230,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fusage_scenarios.py",{"path":302,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":303,"sourceHtmlUrl":304},"scripts\u002Fusage_scenarios.py.lock",34991,"https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-sunstack-rule\u002Fscripts\u002Fusage_scenarios.py.lock",[306,312,319,325,332,339],{"skillNo":307,"name":308,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":309,"categories":310,"keywords":311,"publishedAt":19},"01M7EHCT4EWN4EWJ6SSY7E4B6E","smoke-fixture","https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002Fscripts\u002Frelease\u002Fsmoke-fixture\u002Fskill.md",[],[],{"skillNo":313,"name":314,"nameZh":6,"description":315,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":316,"categories":317,"keywords":318,"publishedAt":19},"01M7EHCQJWP7TNVKV4S1BR3QYA","demistify-explainer","Use when writing, editing, or checking Demistify markup: component syntax, attributes, nesting, layouts, Markdown\u002FMermaid islands, and data references.","https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002Fpackages\u002Fdemistify\u002Fskill\u002FSKILL.md",[],[],{"skillNo":320,"name":321,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":322,"categories":323,"keywords":324,"publishedAt":19},"01M7EHCNB60T960ND6G9P0R5EE","examples","https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002Fdocs\u002Fspecs\u002F2026-10-12-rust-rule-engine\u002Fexamples\u002FSKILL.md",[],[],{"skillNo":326,"name":327,"nameZh":6,"description":328,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":329,"categories":330,"keywords":331,"publishedAt":19},"01M7EHCF5QKTPPAD5XWP1WTCVR","verification-design","Use when planning how a design project's requirements will be proven: for each requirement, the reference, the target and `verify-\u003Capp>` journey, a passing condition a wrong build fails, reused real-path tests and what stays unverified, after Program Design or when that plan is missing or stale. Not for observing or challenging a delivered claim (practices-verification), building journeys (practices-verification-maintenance), or regression tests.","https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002Fcrates\u002Fsunstack\u002Ftests\u002Ffixtures\u002Frulebook-lint\u002Fskills\u002Fverification-design\u002FSKILL.md",[],[],{"skillNo":333,"name":334,"nameZh":6,"description":335,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":336,"categories":337,"keywords":338,"publishedAt":19},"01M7EHCB34APZ6K02GXFCGRZGC","practices-retrospective","Use when asked for a blameless retrospective, a look back, or lessons from a finished or bounded session or delivery: what helped, what hindered, what to preserve, or why an owner or review correction keeps recurring across sessions. Not for re-anchoring a shared model in the current conversation, diagnosing a current failure, collecting evidence alone, choosing which skills to create or merge, or maintaining a verification skill.","https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002Fcrates\u002Fsunstack\u002Ftests\u002Ffixtures\u002Frulebook-lint\u002Fskills\u002Fpractices-retrospective\u002FSKILL.md",[],[],{"skillNo":340,"name":341,"nameZh":6,"description":342,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":343,"categories":344,"keywords":345,"publishedAt":19},"01M7EHC6QJ3GXRZWGXHAKD03CH","practices-research","Use when a task needs source gathering, prior-art research, current docs or web evidence, or memory, session-log, or saved-reader research before design, planning, review, or discussion can continue. Not for extracting unwritten owner meaning.","https:\u002F\u002Fgithub.com\u002FShravanSunder\u002Fsunstack-tools\u002Fblob\u002Fmain\u002Fcrates\u002Fsunstack\u002Ftests\u002Ffixtures\u002Frulebook-lint\u002Fskills\u002Fpractices-research\u002FSKILL.md",[],[]]