[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MEKK2Y8SGC0G02GGZHZ0CD":3,"skill-same:01M6MEKK2Y8SGC0G02GGZHZ0CD":92},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":41,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M6MEKK2Y8SGC0G02GGZHZ0CD","superloopy-loop",null,"Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-backed completion.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1571,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"loop","superloopy loop","codex","tasks","harness","use","evidence","artifact","progress","for","2026-11-10 10:12:30",false,"---\nname: superloopy-loop\ndescription: Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-backed completion.\nmetadata:\n  short-description: Lightweight strict-evidence loop harness\n---\n\n# superloopy-loop\n\nUse this skill when the user asks for Superloopy, loopywork, lpy, a loop harness, durable criteria, evidence-backed completion, strict-but-light task flow, or guided next actions.\n\n## Contract\n\n- State lives in `.superloopy\u002F`, or `.superloopy\u002Fsessions\u002F\u003Cid>\u002F` when `--session-id` is used.\n- Do not hand-edit `.superloopy\u002Fgoals.json`; use the CLI.\n- A criterion can pass only after a real artifact exists under the active evidence root.\n- User steering must use `SUPERLOOPY_STEER` JSON; do not hand-edit `.superloopy\u002Fgoals.json`.\n- Executor receipts should end with `SUPERLOOPY_EVIDENCE: \u003Cpath-under-active-evidence-root>`.\n- Legacy `EVIDENCE_RECORDED` receipts remain accepted for compatibility.\n- Tests are useful evidence, but completion requires the Superloopy evidence artifact.\n- Use `superloopy loop prove` when an active goal needs command-backed evidence for its next unresolved criterion.\n- Keep the workflow lightweight unless the task genuinely needs heavier review.\n- A leading `loopy` keyword wakes the loop engineer: take the rest of the prompt as the brief, run the loop yourself, and report progress instead of asking the user to type Superloopy commands.\n- `loopywork`, `$lpy`, and `lpy` are lighter prompt triggers; they inject guidance but never mutate `.superloopy\u002F` state by themselves.\n- Full Loopy runs default to direct, concise, complete user-facing progress and final responses. Exact `say-it-straight off` \u002F `직설 모드 끄기` and `say-it-straight on` \u002F `직설 모드 켜기` controls apply only to the current incomplete loop; new loops reset this default to enabled.\n- This output overlay changes wording only. It never silently rewrites supplied prose, task artifacts, code, documentation, comments, evidence, quotations, or user source text; direct artifact editing remains explicit-only. `i-have-adhd` still owns structure, and `humanize-korean` still owns Korean artifact rewriting.\n\n## Load on demand\n\nThese references hold the situational detail. Read the one a row names when its condition holds; the rules above and below apply to every run.\n\n| Read | When |\n|---|---|\n| [CLI flow](references\u002Fcli-flow.md) | Running Superloopy commands beyond the loop engineer's `begin` → `guide` → `prove` → `check` → `finish` path: `create`, `capture`, manual `evidence`, `trace`, `report`, a blocked `check` repair plan, custom `review`\u002F`checkpoint` gate workflows, or a cache-satisfied final proof. |\n| [Continuation engine](references\u002Fcontinuation.md) | The Stop hook re-prompted you (\"Superloopy continuation\"), a loop shown `blocked` or `paused` in `superloopy loop status`, a quota\u002Fusage limit, or scheduling an auto-resume. |\n| [Evidence audit](references\u002Fevidence-audit.md) | Running `superloopy loop audit`, dispatching `assayer`, or handling a failed, `inconclusive`, or `blocked` audit. |\n| [Crew](references\u002Fcrew.md) | Before dispatching any subagent (solo light delegation or `loopy team`\u002Fcrew): parent responsibilities, `handoff`\u002F`fleet` bookkeeping, the self-contained dispatch contract, subagent lifecycle, and agent allocation. |\n| [Reassurance copy](references\u002Freassurance-copy.md) | The reassurance-copy condition below applies. |\n\n## Loop engineer (`loopy` keyword)\n\nWhen the user opens a message with `loopy \u003Ctask>`, act as the loop engineer:\n\n- Start once with `superloopy loop begin --brief \"\u003Ctask>\" --mode light --json`; do not create a second plan if one is active.\n- Drive each step from `superloopy loop guide --json`, prove criteria with `superloopy loop prove -- \u003Ccommand>`, preflight with `superloopy loop check`, then finish with `superloopy loop finish --evidence \"\u003Csummary>\" --artifact .superloopy\u002Fevidence\u002Fgate.json --json`.\n- The user types only `loopy \u003Ctask>`. You run every Superloopy command and report progress as criteria proven and the next step.\n- `loopy` with no task asks what to build; `loopy` mid-loop resumes from existing state. After a `loopy` prompt, the packaged Stop hook keeps this session going while criteria remain, until the user sends a plain prompt (`SUPERLOOPY_STOP_HOOK=on` drives every session, `off` disables it). If it reports a worker that stopped without proof, treat that worker's reply as unproven.\n\n### Execution discipline\n\nThe loop engineer directive carries three rules distilled from a component-level harness study (arXiv 2609.20804). For strong models, most avoidable cost is redundant verification, unchanged re-runs of a failing check, and many small re-patches.\n\n- Prove each criterion once with the narrowest command that decides it, then move on. Do not re-run passing proof or broad suites between criteria; `loop finish` re-runs every passed command-backed criterion before it completes (trusted commands only; commandless proof gets an artifact-existence check). `loop check` validates artifacts and does not re-run anything.\n- When a proof fails, its output is already in the capture artifact. Read the failing part (tail or search), then change the code or the proof command before proving again; if the criterion itself is wrong, ask the user to revise it with a `revise_criterion` steer. After 3 consecutive failures of one criterion with the same command, exit, and normalized output tail, `prove`, `capture`, `trace`, `check`, and `report` emit a `repeated-failing-proof` warning. Normalization ignores run-to-run noise (timestamps, durations, labeled PIDs and ports, UUIDs, hashes, temp paths, stack positions, numbers of 10+ digits such as epoch times) but keeps other numbers, so a changed assertion value or pass\u002Ffail count breaks the streak. Any other evidence for that criterion, including a pass, a manual `loop evidence` record, or a revised criterion, resets it. The warning is advisory and never blocks; with `SUPERLOOPY_STOP_HOOK=on`, the Stop hook's no-progress cap (3 iterations without a new pass) still marks a stalled loop `blocked`.\n- Batch independent reads and shell steps into one call, and land each file change as one coherent edit.\n- After compaction, the recovery capsule lists failing proof with its artifact path. Re-read that artifact instead of re-running the command to see the error again.\n\n### Reassurance-copy gate (conditional)\n\n- Decide from the affected artifact: if it creates or changes user-visible Korean product copy about behavior, add a plan criterion for RC-1 through RC-4 and Korean naturalness.\n- State supplied outcomes, fallback, recovery, or next action; preserve verified privacy\u002Flegal commitments; never invent behavior.\n- Apply `humanize-korean` semantic review for misplaced modifiers.\n- Ignore internal logs, developer docs, quotations, general\u002Fmarketing prose, and non-Korean copy.\n\nRead the detailed [reassurance-copy reference](references\u002Freassurance-copy.md) when this condition applies. Artifact ownership decides the condition; prompt wording does not.\n\n### Two tiers: solo and crew (`loopy team`)\n\nThe loop engineer directive is injected for every `loopy` prompt, and it scales to the work:\n\n- **Solo (default).** A plain `loopy \u003Ctask>` drives one agent through the loop. The directive still permits light delegation: if the work splits into 2+ genuinely independent slices, you may fan them out with the native subagent controls exposed by the current host; keep each assignment self-contained. For a single cohesive change, stay solo.\n- **Crew (`loopy team \u003Ctask>` \u002F `loopy crew \u003Ctask>`, the connected one-word `loopycrew \u003Ctask>`, or the standalone `ultrawork \u003Ctask>`).** The same engineer escalates into full fan-out: dispatch the crew across independent lanes, collect them with the host's native lifecycle controls, and record only artifact-backed proof. The escalation keyword is stripped from the brief that seeds the loop. This is the active counterpart to \"Optional Subagent-Driven Mode\" below — same dispatch contract, receipt gate, and mandatory `handoff`\u002F`fleet` tracking.\n\nEach crew dispatch uses the configured name when the host exposes named selection: `forge` to build, `sentinel` to review, `probe` to test, `arbiter` to gate, `assayer` to audit, and `pathfinder` to navigate. The assignment also stays self-contained (`TASK: act as \u003Crole> ...`). The orchestrator itself runs on the model the user selected in the host (`gpt-6-astra` is allowed when selected); crew lanes keep their `model-policy.json` pins and never inherit the orchestrator's model. The host-owned stop callback observes the actual role identity; if the host cannot attest that identity or model, report `role_unverified` or `model_unverified`.\n\nBoth tiers are steering, not enforcement: the directive instructs the main agent, and actual spawning depends on the host's native multi-agent tool being available. Superloopy never spawns; it gates the evidence workers deliver. See \"Optional Subagent-Driven Mode\" for the full dispatch contract and crew roles.\n\n## Optional Subagent-Driven Mode\n\nUse project custom agents from `.codex\u002Fagents\u002F` only when the user asks for subagents or the work has independent implementation, review, and QA lanes. The normal single-agent Superloopy flow remains the default for small changes.\n\nSuperloopy provisions and tracks these agents; the host (Codex) spawns them. Superloopy never spawns. The host spawn surface cannot reliably select a bundled TOML role, model, or reasoning effort by name, so every dispatch must be self-contained and judged by delivered evidence — never by the role label requested. See `docs\u002Fsuperloopy-host-contract.md`.\n\nPlugin installs bootstrap the `superloopy` command wrapper and bundled custom agents on the first approved `SessionStart` hook. If the host does not run that hook, run `node src\u002Fcli.js install --json` from the Superloopy checkout or installed plugin root. `superloopy agents install` remains available to copy only the bundled custom agents into the personal Codex agents directory (`$CODEX_HOME\u002Fagents` when set, otherwise `~\u002F.codex\u002Fagents`). Restart Codex after installation.\n\nBefore dispatching any worker, read [Crew](references\u002Fcrew.md): it carries the parent agent responsibilities, the dispatch contract, the subagent lifecycle, and agent allocation.\n\n## Quality Gate\n\nEvery listed artifact must exist, be non-empty, and live under the active evidence root. Superloopy also accepts strict review gates and matrix gates when reviewer\u002Farchitect, executor QA, rerun, artifact, and coverage fields validate. `loop review` and `loop finish` always write the default gate. A review gate is JSON you write by hand and pass to `loop checkpoint --quality-gate`; write one only when `sentinel`, `probe`, and `arbiter` each actually ran, and sign it as [Crew](references\u002Fcrew.md) describes under \"Review gate actors\".\n\nFor executor receipts, use the active evidence root. A global loop normally records under `.superloopy\u002Fevidence\u002F`; a scoped loop records under `.superloopy\u002Fsessions\u002F\u003Cid>\u002Fevidence\u002F`. If a receipt is missing or invalid, the receipt block message names the active evidence root to repair.\n\nKeep the human final gate report and the Superloopy quality gate artifact separate. A `arbiter` report is Markdown evidence (for example `.superloopy\u002Fevidence\u002Farbiter-final-gate-report.md`). The `superloopy loop review` and `superloopy loop finish --artifact` flag writes the machine-validated quality gate artifact and must point to JSON, normally `.superloopy\u002Fevidence\u002Fgate.json`. Never pass the Markdown report path as the finish artifact.\n\n## Steering\n\nAccept only structured prompt-level steering:\n\n```text\nSUPERLOOPY_STEER: {\"kind\":\"annotate\",\"evidence\":\"fact\",\"rationale\":\"why it matters\"}\nSUPERLOOPY_STEER: {\"kind\":\"add_goal\",\"title\":\"New slice\",\"objective\":\"Concrete objective\",\"rationale\":\"why it changed\"}\nSUPERLOOPY_STEER: {\"kind\":\"revise_criterion\",\"goalId\":\"G001\",\"criterionId\":\"C002\",\"scenario\":\"New scenario.\",\"rationale\":\"why it changed\"}\nSUPERLOOPY_STEER: {\"kind\":\"reorder_pending\",\"goalIds\":[\"G003\",\"G002\"],\"rationale\":\"why this order\"}\n```\n\nAfter any accepted steering, follow the returned guide; run `superloopy loop status --json` when you need a fresh reorientation.\n\n## Doctor\n\n`superloopy doctor --json` checks the package, hooks, bundled skills, CLI, dependency-free boundary, runtime ignore policy, file inventory, gate notes, design audit, generic comparison scan status, dispatch coherence, model policy, and reviewability.\n\nUse `superloopy doctor --comparison-path \u002Fpath\u002Fto\u002Fcomparison --json` only when you need copied-block evidence against an external folder. The generic comparison scan compares code-shaped files for substantial contiguous blocks without naming or coupling Superloopy to any source project.\n","# superloopy-loop\n\nUse this skill when the user asks for Superloopy, loopywork, lpy, a loop harness, durable criteria, evidence-backed completion, strict-but-light task flow, or guided next actions.\n\n## Contract\n\n- State lives in `.superloopy\u002F`, or `.superloopy\u002Fsessions\u002F\u003Cid>\u002F` when `--session-id` is used.\n- Do not hand-edit `.superloopy\u002Fgoals.json`; use the CLI.\n- A criterion can pass only after a real artifact exists under the active evidence root.\n- User steering must use `SUPERLOOPY_STEER` JSON; do not hand-edit `.superloopy\u002Fgoals.json`.\n- Executor receipts should end with `SUPERLOOPY_EVIDENCE: \u003Cpath-under-active-evidence-root>`.\n- Legacy `EVIDENCE_RECORDED` receipts remain accepted for compatibility.\n- Tests are useful evidence, but completion requires the Superloopy evidence artifact.\n- Use `superloopy loop prove` when an active goal needs command-backed evidence for its next unresolved criterion.\n- Keep the workflow lightweight unless the task genuinely needs heavier review.\n- A leading `loopy` keyword wakes the loop engineer: take the rest of the prompt as the brief, run the loop yourself, and report progress instead of asking the user to type Superloopy commands.\n- `loopywork`, `$lpy`, and `lpy` are lighter prompt triggers; they inject guidance but never mutate `.superloopy\u002F` state by themselves.\n- Full Loopy runs default to direct, concise, complete user-facing progress and final responses. Exact `say-it-straight off` \u002F `직설 모드 끄기` and `say-it-straight on` \u002F `직설 모드 켜기` controls apply only to the current incomplete loop; new loops reset this default to enabled.\n- This output overlay changes wording only. It never silently rewrites supplied prose, task artifacts, code, documentation, comments, evidence, quotations, or user source text; direct artifact editing remains explicit-only. `i-have-adhd` still owns structure, and `humanize-korean` still owns Korean artifact rewriting.\n\n## Load on demand\n\nThese references hold the situational detail. Read the one a row names when its condition holds; the rules above and below apply to every run.\n\n| Read | When |\n|---|---|\n| [CLI flow](references\u002Fcli-flow.md) | Running Superloopy commands beyond the loop engineer's `begin` → `guide` → `prove` → `check` → `finish` path: `create`, `capture`, manual `evidence`, `trace`, `report`, a blocked `check` repair plan, custom `review`\u002F`checkpoint` gate workflows, or a cache-satisfied final proof. |\n| [Continuation engine](references\u002Fcontinuation.md) | The Stop hook re-prompted you (\"Superloopy continuation\"), a loop shown `blocked` or `paused` in `superloopy loop status`, a quota\u002Fusage limit, or scheduling an auto-resume. |\n| [Evidence audit](references\u002Fevidence-audit.md) | Running `superloopy loop audit`, dispatching `assayer`, or handling a failed, `inconclusive`, or `blocked` audit. |\n| [Crew](references\u002Fcrew.md) | Before dispatching any subagent (solo light delegation or `loopy team`\u002Fcrew): parent responsibilities, `handoff`\u002F`fleet` bookkeeping, the self-contained dispatch contract, subagent lifecycle, and agent allocation. |\n| [Reassurance copy](references\u002Freassurance-copy.md) | The reassurance-copy condition below applies. |\n\n## Loop engineer (`loopy` keyword)\n\nWhen the user opens a message with `loopy \u003Ctask>`, act as the loop engineer:\n\n- Start once with `superloopy loop begin --brief \"\u003Ctask>\" --mode light --json`; do not create a second plan if one is active.\n- Drive each step from `superloopy loop guide --json`, prove criteria with `superloopy loop prove -- \u003Ccommand>`, preflight with `superloopy loop check`, then finish with `superloopy loop finish --evidence \"\u003Csummary>\" --artifact .superloopy\u002Fevidence\u002Fgate.json --json`.\n- The user types only `loopy \u003Ctask>`. You run every Superloopy command and report progress as criteria proven and the next step.\n- `loopy` with no task asks what to build; `loopy` mid-loop resumes from existing state. After a `loopy` prompt, the packaged Stop hook keeps this session going while criteria remain, until the user sends a plain prompt (`SUPERLOOPY_STOP_HOOK=on` drives every session, `off` disables it). If it reports a worker that stopped without proof, treat that worker's reply as unproven.\n\n### Execution discipline\n\nThe loop engineer directive carries three rules distilled from a component-level harness study (arXiv 2609.20804). For strong models, most avoidable cost is redundant verification, unchanged re-runs of a failing check, and many small re-patches.\n\n- Prove each criterion once with the narrowest command that decides it, then move on. Do not re-run passing proof or broad suites between criteria; `loop finish` re-runs every passed command-backed criterion before it completes (trusted commands only; commandless proof gets an artifact-existence check). `loop check` validates artifacts and does not re-run anything.\n- When a proof fails, its output is already in the capture artifact. Read the failing part (tail or search), then change the code or the proof command before proving again; if the criterion itself is wrong, ask the user to revise it with a `revise_criterion` steer. After 3 consecutive failures of one criterion with the same command, exit, and normalized output tail, `prove`, `capture`, `trace`, `check`, and `report` emit a `repeated-failing-proof` warning. Normalization ignores run-to-run noise (timestamps, durations, labeled PIDs and ports, UUIDs, hashes, temp paths, stack positions, numbers of 10+ digits such as epoch times) but keeps other numbers, so a changed assertion value or pass\u002Ffail count breaks the streak. Any other evidence for that criterion, including a pass, a manual `loop evidence` record, or a revised criterion, resets it. The warning is advisory and never blocks; with `SUPERLOOPY_STOP_HOOK=on`, the Stop hook's no-progress cap (3 iterations without a new pass) still marks a stalled loop `blocked`.\n- Batch independent reads and shell steps into one call, and land each file change as one coherent edit.\n- After compaction, the recovery capsule lists failing proof with its artifact path. Re-read that artifact instead of re-running the command to see the error again.\n\n### Reassurance-copy gate (conditional)\n\n- Decide from the affected artifact: if it creates or changes user-visible Korean product copy about behavior, add a plan criterion for RC-1 through RC-4 and Korean naturalness.\n- State supplied outcomes, fallback, recovery, or next action; preserve verified privacy\u002Flegal commitments; never invent behavior.\n- Apply `humanize-korean` semantic review for misplaced modifiers.\n- Ignore internal logs, developer docs, quotations, general\u002Fmarketing prose, and non-Korean copy.\n\nRead the detailed [reassurance-copy reference](references\u002Freassurance-copy.md) when this condition applies. Artifact ownership decides the condition; prompt wording does not.\n\n### Two tiers: solo and crew (`loopy team`)\n\nThe loop engineer directive is injected for every `loopy` prompt, and it scales to the work:\n\n- **Solo (default).** A plain `loopy \u003Ctask>` drives one agent through the loop. The directive still permits light delegation: if the work splits into 2+ genuinely independent slices, you may fan them out with the native subagent controls exposed by the current host; keep each assignment self-contained. For a single cohesive change, stay solo.\n- **Crew (`loopy team \u003Ctask>` \u002F `loopy crew \u003Ctask>`, the connected one-word `loopycrew \u003Ctask>`, or the standalone `ultrawork \u003Ctask>`).** The same engineer escalates into full fan-out: dispatch the crew across independent lanes, collect them with the host's native lifecycle controls, and record only artifact-backed proof. The escalation keyword is stripped from the brief that seeds the loop. This is the active counterpart to \"Optional Subagent-Driven Mode\" below — same dispatch contract, receipt gate, and mandatory `handoff`\u002F`fleet` tracking.\n\nEach crew dispatch uses the configured name when the host exposes named selection: `forge` to build, `sentinel` to review, `probe` to test, `arbiter` to gate, `assayer` to audit, and `pathfinder` to navigate. The assignment also stays self-contained (`TASK: act as \u003Crole> ...`). The orchestrator itself runs on the model the user selected in the host (`gpt-6-astra` is allowed when selected); crew lanes keep their `model-policy.json` pins and never inherit the orchestrator's model. The host-owned stop callback observes the actual role identity; if the host cannot attest that identity or model, report `role_unverified` or `model_unverified`.\n\nBoth tiers are steering, not enforcement: the directive instructs the main agent, and actual spawning depends on the host's native multi-agent tool being available. Superloopy never spawns; it gates the evidence workers deliver. See \"Optional Subagent-Driven Mode\" for the full dispatch contract and crew roles.\n\n## Optional Subagent-Driven Mode\n\nUse project custom agents from `.codex\u002Fagents\u002F` only when the user asks for subagents or the work has independent implementation, review, and QA lanes. The normal single-agent Superloopy flow remains the default for small changes.\n\nSuperloopy provisions and tracks these agents; the host (Codex) spawns them. Superloopy never spawns. The host spawn surface cannot reliably select a bundled TOML role, model, or reasoning effort by name, so every dispatch must be self-contained and judged by delivered evidence — never by the role label requested. See `docs\u002Fsuperloopy-host-contract.md`.\n\nPlugin installs bootstrap the `superloopy` command wrapper and bundled custom agents on the first approved `SessionStart` hook. If the host does not run that hook, run `node src\u002Fcli.js install --json` from the Superloopy checkout or installed plugin root. `superloopy agents install` remains available to copy only the bundled custom agents into the personal Codex agents directory (`$CODEX_HOME\u002Fagents` when set, otherwise `~\u002F.codex\u002Fagents`). Restart Codex after installation.\n\nBefore dispatching any worker, read [Crew](references\u002Fcrew.md): it carries the parent agent responsibilities, the dispatch contract, the subagent lifecycle, and agent allocation.\n\n## Quality Gate\n\nEvery listed artifact must exist, be non-empty, and live under the active evidence root. Superloopy also accepts strict review gates and matrix gates when reviewer\u002Farchitect, executor QA, rerun, artifact, and coverage fields validate. `loop review` and `loop finish` always write the default gate. A review gate is JSON you write by hand and pass to `loop checkpoint --quality-gate`; write one only when `sentinel`, `probe`, and `arbiter` each actually ran, and sign it as [Crew](references\u002Fcrew.md) describes under \"Review gate actors\".\n\nFor executor receipts, use the active evidence root. A global loop normally records under `.superloopy\u002Fevidence\u002F`; a scoped loop records under `.superloopy\u002Fsessions\u002F\u003Cid>\u002Fevidence\u002F`. If a receipt is missing or invalid, the receipt block message names the active evidence root to repair.\n\nKeep the human final gate report and the Superloopy quality gate artifact separate. A `arbiter` report is Markdown evidence (for example `.superloopy\u002Fevidence\u002Farbiter-final-gate-report.md`). The `superloopy loop review` and `superloopy loop finish --artifact` flag writes the machine-validated quality gate artifact and must point to JSON, normally `.superloopy\u002Fevidence\u002Fgate.json`. Never pass the Markdown report path as the finish artifact.\n\n## Steering\n\nAccept only structured prompt-level steering:\n\n```text\nSUPERLOOPY_STEER: {\"kind\":\"annotate\",\"evidence\":\"fact\",\"rationale\":\"why it matters\"}\nSUPERLOOPY_STEER: {\"kind\":\"add_goal\",\"title\":\"New slice\",\"objective\":\"Concrete objective\",\"rationale\":\"why it changed\"}\nSUPERLOOPY_STEER: {\"kind\":\"revise_criterion\",\"goalId\":\"G001\",\"criterionId\":\"C002\",\"scenario\":\"New scenario.\",\"rationale\":\"why it changed\"}\nSUPERLOOPY_STEER: {\"kind\":\"reorder_pending\",\"goalIds\":[\"G003\",\"G002\"],\"rationale\":\"why this order\"}\n```\n\nAfter any accepted steering, follow the returned guide; run `superloopy loop status --json` when you need a fresh reorientation.\n\n## Doctor\n\n`superloopy doctor --json` checks the package, hooks, bundled skills, CLI, dependency-free boundary, runtime ignore policy, file inventory, gate notes, design audit, generic comparison scan status, dispatch coherence, model policy, and reviewability.\n\nUse `superloopy doctor --comparison-path \u002Fpath\u002Fto\u002Fcomparison --json` only when you need copied-block evidence against an external folder. The generic comparison scan compares code-shaped files for substantial contiguous blocks without naming or coupling Superloopy to any source project.\n",{"name":5,"metadata":34,"description":7},{"short-description":35},"Lightweight strict-evidence loop harness","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop",490,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 02:12:02",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill superloopy-loop",{"tool":52,"command":53},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill superloopy-loop",{"tool":55,"command":56},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill superloopy-loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop\u002FSKILL.md",true,[60,66,70,74,78,82,86],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"agents\u002Fopenai.yaml","REFERENCE","参考文档",381,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop\u002Fagents\u002Fopenai.yaml",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fcli-flow.md",4338,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop\u002Freferences\u002Fcli-flow.md",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fcontinuation.md",3829,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop\u002Freferences\u002Fcontinuation.md",{"path":75,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fcrew.md",6964,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop\u002Freferences\u002Fcrew.md",{"path":79,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fevidence-audit.md",3185,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop\u002Freferences\u002Fevidence-audit.md",{"path":83,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Freassurance-copy.md",2020,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop\u002Freferences\u002Freassurance-copy.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Faudit-reassurance-copy.mjs","SCRIPT","脚本",8492,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fbeefiker\u002Fsuperloopy\u002Fskills\u002Fsuperloopy-loop\u002Fscripts\u002Faudit-reassurance-copy.mjs",[93,101,108,115,142,167],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":100},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":100},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":100},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":29},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","when","you","done","reviewer","io","change","cli","merge","past",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":29},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[149,150,151,137,152,153,154,155,156,157,158,159,160,161,127,162,163,164,165,166],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":184,"publishedAt":29},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[173,178,181],{"categoryNo":174,"categoryName":175,"taxonomyType":176,"taxonomyTypeDesc":177},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":179,"categoryName":180,"taxonomyType":176,"taxonomyTypeDesc":177},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":182,"categoryName":183,"taxonomyType":176,"taxonomyTypeDesc":177},"01JBSEEDCAT000000000000010","后端与接口",[169,185,186,187,188,189,190,163,191,128,192,193,194,195,133,196,197,198,199,200],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]