[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77M54MHJH26DVCVW1SGTBXM":3,"skill-same:01M77M54MHJH26DVCVW1SGTBXM":58},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":51},"01M77M54MHJH26DVCVW1SGTBXM","realign",null,"Executes an enforcement-surface audit's findings one at a time behind an explicit per-item human gate, down the rollback ladder: config-disable first, observe, delete last. The only skill in this plugin that changes the surface; it never scans or re-judges. Use when the user wants accepted audit findings carried out, a judged gate or hook retired, or one disabled and observed.","melodic-software\u002Fclaude-code-plugins","melodic-software","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F58273638?v=4","01M77JVQTXNGKCE4MDFY2BC936","Melodic Software","01M77JVQVN9QDWKAH6W03ANP76",30,"MIT","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Foverengineering\u002Fskills\u002Frealign\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Executes an enforcement-surface audit's findings one at a time behind an explicit per-item human gate, down the rollback ladder: config-disable first, observe, delete last. The only skill in this plugin that changes the surface; it never scans or re-judges. Use when the user wants accepted audit findings carried out, a judged gate or hook retired, or one disabled and observed.\"\nargument-hint: \"[finding-id ...] [layer ...]\"\nuser-invocable: true\ndisable-model-invocation: false\nshell: bash\nmetadata:\n  workflow-stage: implement\n  summary: Execute accepted audit findings down the rollback ladder behind a per-item human gate\n---\n\n**Arguments.** `[finding-id ...] [layer ...]`. Default: every finding awaiting a decision, in the artifact's order\n\n## Repository context. Gather first\n\nRun this as its own Bash call, never combined with another command:\n\n- Branch, `git symbolic-ref --quiet --short HEAD`\n\nTreat a failure (detached checkout, no repository, no git) as an unresolved identity.\n\n## Pre-computed context\n\n- Today (UTC): !`date -u +%Y-%m-%d 2>\u002Fdev\u002Fnull || echo \"unknown (no date command)\"`\n\n## Purpose\n\nExecute what an `overengineering:audit` run found, one finding at a time, with the operator deciding\neach. This is the only skill that mutates the surface under scrutiny, and the per-item gate below is\nwhat makes that safe.\n\nRead `${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Fscrutiny-method.md` before executing anything: the rollback\nladder (§11), protected classes and their cap (§7), UNPROVEN triage (§8), ownership and out-of-repo\ncustody (§12), the verdict ladder (§6), and the scope boundary (§10). The artifact's shape, status\nvocabulary, merge rules and durable judgment record are\n`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Ffindings-artifact.md`'s. Every bare `§N` here is a scrutiny-method\nsection. Cite both documents rather than paraphrasing either in a proposal.\n\n## The per-item gate\n\n**Nothing mutates without an explicit acceptance of that finding, from the operator, at the moment it\nis presented.** Say so in the run's opening line, then hold it literally:\n\n- **One finding, one acceptance.** Accepting A authorizes A's remediation and nothing else: not its\n  neighbors, not the rest of its layer.\n- **Blanket approval is not the gate.** \"Approve everything\", \"do whatever the audit says\", and a\n  standing authorization from earlier in the session are declined, out loud, with an offer to walk\n  the queue instead.\n- **Silence is not acceptance.** An unanswered finding stays `OPEN`; it does not become `REJECTED`\n  and is not carried on a later item's yes.\n- **Acceptance covers the rung or act about to execute.** A yes at rung 1 of §11 authorizes the\n  config-disable, not the deletion; rung 3 asks again after the window.\n- **Change approval shows the exact change first.** The file and line, the config key and its new\n  value, or the entry to be written, shown after the plan and approved before any write, then\n  executed as shown and nothing adjacent.\n- **No operator present means present and stop.** In a dispatched, scheduled or background run,\n  present the queue and stop: no status transitions, nothing written. There is no unattended mode.\n\n**Both gates are required.** Item acceptance authorizes working the finding and the act named at\nthat moment; change approval authorizes one exact edit. An earlier acceptance is not approval of the\nedit that later falls out of it.\n\n## Before anything: load the artifact\n\n1. **Resolve the branch identity, then the home.** `HEAD` and a failed call are never an identity.\n   Where the call fails, use a logical ref the environment supplies only after `audit`'s\n   normalize-then-validate steps (strip a leading `refs\u002Fheads\u002F`, `git check-ref-format --branch`,\n   refuse `.` and `..` segments), and name its source. Otherwise stop, per \"An unresolved branch\n   identity is its own refusal\". Compose the home per `findings-artifact.md` \"Where it lives\".\n2. **No artifact: stop.** Say visibly that no findings artifact exists at the resolved home, name\n   that home, and name the two producers: `overengineering:audit` for a walk of the enforcement\n   surface and `overengineering:justify` for one artifact the operator points at. Do not scan, judge\n   or remediate anything yourself; this skill has no evidence or verdict of its own.\n3. **Refuse a mismatched `branch:`**, naming both; **refuse a `branch:` that is absent, empty or the\n   literal `HEAD`**, naming which, without comparing; and **refuse an unrecognized `schema:`**, each\n   with a visible message. `1` and `2` are recognized. On `schema: 2`, `mode`, `targets` and `Basis`\n   are displayed with the finding and change no gating decision; a schema-1 row's missing `Basis`\n   displays as `not recorded (schema 1)`. The artifact's frontmatter binds it to a branch; its\n   directory does not.\n4. **Read the evidence-availability assessment that leads the artifact; never recompute it.**\n5. **A `Status` outside the closed vocabulary** is reported and that finding skipped.\n6. **Surface a verdict that moved under a carried-forward judgment first, and never act on it.**\n   Read the flag the recomputing producer wrote; never re-derive it. An `ACCEPTED` finding now `KEEP`,\n   a `REJECTED` one now retirement-direction, or an `ACCEPTED` verdict whose authorized act changed\n   (`DOWNGRADE` now `CONSOLIDATE`) means the evidence moved under the operator's decision. Re-confirm\n   the act before anything proceeds.\n\n## Arguments\n\nFinding ids and layer names from the artifact's vocabulary narrow the queue to exactly those\nfindings. Anything else is a free-text hint that orders the queue, reported when it matches nothing.\nNo argument widens the queue or replaces the gate. Bare invocation presents every finding awaiting a\ndecision in the artifact's order; a queue too long for one sitting is said to be, and stopping\nhalfway is a normal end, since statuses persist.\n\n## The queue\n\nPresent every finding in the artifact's order and dispose of each by its status. A finding in one of\nthe justification layers (`decision-records`, `documents`, `components`, `dependencies`, `source`)\nhas no rollback ladder here, and is presented and judged but never remediated: the rung-1-inapplicable\nroute below would turn it into a deletion. Display its evidence, verdict and the owner from that lane's boundary\ntable, say in one line that no rung is offered, and still take the operator's decision (`REJECTED`,\nor `DELEGATED-EXTERNAL` where custody is upstream). Dispatch on `Layer`, never the `check` segment,\nwhich cannot be read back off an id (`findings-artifact.md` \"Finding ids\").\n\n| Status | What this run does with it |\n|---|---|\n| `OPEN` | Present the verdict, its evidence, its cost, and the proposed rung; ask for a decision |\n| `ACCEPTED` | Authorized in an earlier run: re-confirm the rung about to execute, then continue |\n| `REJECTED` · `REALIGNED` | Nothing. Report it as already decided; do not re-ask |\n| `DELEGATED-EXTERNAL` | Report the delegation pointer and its state. Nothing local, ever |\n| `ABLATION-PENDING` | Gate and execute the rung-1 disable, then move to `ABLATION-ACTIVE` |\n| `ABLATION-ACTIVE` | Compare today against the recorded end date; before it, report the window as running and stop there |\n| `ABLATION-CONCLUDED-RETIRE` | Rung 3, behind its own acceptance |\n| `ABLATION-CONCLUDED-KEEP` | Confirm the mechanism is re-enabled, close as KEEP, and offer the durable judgment entry |\n\n## Per accepted finding: the four movements\n\nInterview, explore and research, plan, implement. Each composes a sibling skill via the Skill tool\nwhen its plugin is installed and runs the inline fallback when not. Say which ran and record the\npresence answer on the finding.\n\n| Movement | Composition (presence-gated) | Inline fallback when absent |\n|---|---|---|\n| **Interview**: intent, constraints, what done means | `\u002Fplanning:interview` | Ask the same questions inline as one small numbered set, recommendation first |\n| **Explore**: what the mechanism touches, where it is wired, what depends on it | `\u002Fdiscovery:explore` | Read the artifact, its registration surface and call sites, and list the blast radius before proposing anything |\n| **Research**: is the replacement the rediscovery names real and current | `\u002Fdiscovery:research` | Check its current official documentation and record the check with its date (§5) |\n| **Plan**: rung, exact edit, reversal, observation window | `\u002Fplanning:plan` | Write goal, rung, blast radius and reversal in the response; get it approved before any edit |\n| **Implement** | `\u002Fimplementation:implement` | Make the change against the approved plan, one rung at a time, stopping at the same gates |\n\nRun only the movements the finding needs: a one-key config disable with a settled intent needs no\nresearch pass. Record a skipped one with its reason (\"Skipped research: the rediscovery names a\nmechanism already in this repo\"), never skip it wordlessly.\n\n## Execution order. The rollback ladder\n\n§11 governs, in order; record the rung reached on the finding:\n\n1. **Config-disable**, wherever a kill switch exists. Check §11's trap: where \"unset means enabled\",\n   make the off state explicit, and confirm the disable took effect.\n2. **Observe** for the consumer's configured window, with **its end date written on the finding**\n   and on a durable pointer, since the artifact can be gone before the date.\n3. **Delete, with the rationale recorded** in the change description: the evidence, the observation\n   result, and what re-adds it. Preserve the re-add surface where one exists.\n\n**Withdrawal is a normal outcome.** A window showing the mechanism load-bearing ends at rung 1 with\nit re-enabled and the finding closed as KEEP with the window's evidence. Say so when proposing the\nladder.\n\n**When rung 1 is inapplicable** (nothing registered or wired to disable: a copy nothing reads, a\nclaim in a document, a lane nothing requires), record *\"rung 1 inapplicable: `\u003Creason>`\"* and why\nrung 2 gives no signal. A reversible non-rung remediation (correct a false claim, register the copy\nthat should be wired) is then a valid proposal under its own acceptance. Where deletion is the only\nremaining act, the acceptance must name the deletion explicitly.\n\n**CONSOLIDATE** removes the redundant copy once the survivor is named: disable, observe under the\nsurvivor, delete where the copy is live; deletion named in the acceptance where it is inert.\n\n## UNPROVEN findings. The ablation track\n\nAn UNPROVEN verdict does not authorize a disable. Route it to §8's track: take the head of the\naudit's carry-cost ranking, propose one bounded batch an operator can attend to, name an owner per\nitem (§12), set one window with its end date, and record a durable pointer. Each item still passes\nthe per-item gate. Items below the batch wait for the next window. Protected and intentionally\ndormant items (§7) never enter a batch.\n\n## Protected findings\n\nA `FLAG-FOR-HUMAN` finding is a question, not a task. Present the capped verdict it would otherwise\ncarry, the evidence in full, the protected class and the rule that matched, then stop and wait for\nthe operator's own call on that item, in their words. Never retire a protected mechanism on this\nskill's reasoning, and never route it into an ablation batch to reach the same end. An operator\noverturning the classification records that in the consumer's tracked configuration.\n\n## Out-of-repo custody. Delegate, never patch locally\n\nWhere the audit's custody read placed the artifact upstream (organization policy, a managed or\nsynced copy, a shared workflow this repo only references, a forge control plane), §12 makes the\nremediation a delegation: produce an upstream change request, an administrator issue, or written\ninstructions for the owner, carrying the evidence and proposed rung, and set `DELEGATED-EXTERNAL`\nwith its pointer. Never edit the out-of-repo surface in place or patch a managed copy locally; the\nnext sync reverts it.\n\n## Statuses this skill writes\n\n**Re-read the artifact from disk immediately before every `Status` write, and merge against that\ncopy**; another producer may have written during a long interview.\n\nThis skill is the only writer of `Status`, and writes one only as its outcome happens, never ahead\nof the operator's yes: `ACCEPTED` on acceptance; `REJECTED` when the operator keeps the mechanism;\n`REALIGNED` when the change has landed; `DELEGATED-EXTERNAL` with its pointer; the `ABLATION-*` states\nas a batch moves through its window. A justification-layer row takes `REJECTED` like any other: it\nrecords a judgment and mutates nothing outside the record. Leave every other field as the audit\ncomputed it.\n\n## The durable judgment record\n\n**Offer** to persist a `REJECTED` or `ABLATION-CONCLUDED-KEEP` finding as a suppression entry in the\nconsuming repo's tracked `.claude\u002Foverengineering.md`:\n\n- Show the exact entry before writing it, and write only on an explicit yes under the per-item gate.\n- The `reason` is the operator's own words; ask for them rather than recycling audit prose.\n- Write it to the team-tracked layer: a personal-layer entry does not suppress.\n- Entry keys, the constituents-authoritative rule and the layering are\n  `${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconsumer-config.md`'s. A `REALIGNED` finding needs no entry.\n\n## An unresolved branch identity is its own refusal\n\nThe branch-match check protects against executing one ref's findings against another ref's surface,\nand `HEAD` compares equal to itself. Both unresolved states refuse, and neither reaches the\ncomparison:\n\n- **This checkout has no branch identity** (the call failed and no logical ref was supplied). Stop\n  before reading the artifact and say: *\"Detached checkout, no logical ref supplied; no branch\n  identity, so the artifact's branch cannot be verified and nothing will be executed.\"* No queue, no\n  status transitions, nothing written.\n- **The artifact carries no branch identity** (`branch:` absent, empty or `HEAD`). Refuse it by name,\n  and say that `overengineering:audit` writes no artifact without an identity, so one carrying\n  `HEAD` did not come from this plugin's audit as it stands. Do not repair the field or fall back\n  to its directory.\n\nNever fall back to `HEAD`, the commit sha, or the home's slug to make up either side.\n\n## Next\n\n`\u002Fverification:confirm`. The finding stays open until the landed change is verified.\n\n## Gotchas\n\n- **An accepted finding is not an accepted deletion.** Acceptance authorizes the rung on the table at\n  that moment.\n- **Disable the copy the runtime actually reads.** Where a guard exists in a local and a packaged\n  form, confirm which one the live configuration registers first.\n- **Do not touch what the finding is not about.** A formatting fix, a stale comment or an adjacent\n  tidy in the same file is outside the acceptance given.\n- **A finding you realigned vanishes from the next audit.** The re-run records it under closed since\n  last run; that is the contract working.\n- **Never argue a quality-enabling practice onto the ladder** (§10). Tests, review, type checking,\n  the build, and the record-keeping that makes the evidence tiers readable are outside this method.\n","**Arguments.** `[finding-id ...] [layer ...]`. Default: every finding awaiting a decision, in the artifact's order\n\n## Repository context. Gather first\n\nRun this as its own Bash call, never combined with another command:\n\n- Branch, `git symbolic-ref --quiet --short HEAD`\n\nTreat a failure (detached checkout, no repository, no git) as an unresolved identity.\n\n## Pre-computed context\n\n- Today (UTC): !`date -u +%Y-%m-%d 2>\u002Fdev\u002Fnull || echo \"unknown (no date command)\"`\n\n## Purpose\n\nExecute what an `overengineering:audit` run found, one finding at a time, with the operator deciding\neach. This is the only skill that mutates the surface under scrutiny, and the per-item gate below is\nwhat makes that safe.\n\nRead `${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Fscrutiny-method.md` before executing anything: the rollback\nladder (§11), protected classes and their cap (§7), UNPROVEN triage (§8), ownership and out-of-repo\ncustody (§12), the verdict ladder (§6), and the scope boundary (§10). The artifact's shape, status\nvocabulary, merge rules and durable judgment record are\n`${CLAUDE_PLUGIN_ROOT}\u002Fcontext\u002Ffindings-artifact.md`'s. Every bare `§N` here is a scrutiny-method\nsection. Cite both documents rather than paraphrasing either in a proposal.\n\n## The per-item gate\n\n**Nothing mutates without an explicit acceptance of that finding, from the operator, at the moment it\nis presented.** Say so in the run's opening line, then hold it literally:\n\n- **One finding, one acceptance.** Accepting A authorizes A's remediation and nothing else: not its\n  neighbors, not the rest of its layer.\n- **Blanket approval is not the gate.** \"Approve everything\", \"do whatever the audit says\", and a\n  standing authorization from earlier in the session are declined, out loud, with an offer to walk\n  the queue instead.\n- **Silence is not acceptance.** An unanswered finding stays `OPEN`; it does not become `REJECTED`\n  and is not carried on a later item's yes.\n- **Acceptance covers the rung or act about to execute.** A yes at rung 1 of §11 authorizes the\n  config-disable, not the deletion; rung 3 asks again after the window.\n- **Change approval shows the exact change first.** The file and line, the config key and its new\n  value, or the entry to be written, shown after the plan and approved before any write, then\n  executed as shown and nothing adjacent.\n- **No operator present means present and stop.** In a dispatched, scheduled or background run,\n  present the queue and stop: no status transitions, nothing written. There is no unattended mode.\n\n**Both gates are required.** Item acceptance authorizes working the finding and the act named at\nthat moment; change approval authorizes one exact edit. An earlier acceptance is not approval of the\nedit that later falls out of it.\n\n## Before anything: load the artifact\n\n1. **Resolve the branch identity, then the home.** `HEAD` and a failed call are never an identity.\n   Where the call fails, use a logical ref the environment supplies only after `audit`'s\n   normalize-then-validate steps (strip a leading `refs\u002Fheads\u002F`, `git check-ref-format --branch`,\n   refuse `.` and `..` segments), and name its source. Otherwise stop, per \"An unresolved branch\n   identity is its own refusal\". Compose the home per `findings-artifact.md` \"Where it lives\".\n2. **No artifact: stop.** Say visibly that no findings artifact exists at the resolved home, name\n   that home, and name the two producers: `overengineering:audit` for a walk of the enforcement\n   surface and `overengineering:justify` for one artifact the operator points at. Do not scan, judge\n   or remediate anything yourself; this skill has no evidence or verdict of its own.\n3. **Refuse a mismatched `branch:`**, naming both; **refuse a `branch:` that is absent, empty or the\n   literal `HEAD`**, naming which, without comparing; and **refuse an unrecognized `schema:`**, each\n   with a visible message. `1` and `2` are recognized. On `schema: 2`, `mode`, `targets` and `Basis`\n   are displayed with the finding and change no gating decision; a schema-1 row's missing `Basis`\n   displays as `not recorded (schema 1)`. The artifact's frontmatter binds it to a branch; its\n   directory does not.\n4. **Read the evidence-availability assessment that leads the artifact; never recompute it.**\n5. **A `Status` outside the closed vocabulary** is reported and that finding skipped.\n6. **Surface a verdict that moved under a carried-forward judgment first, and never act on it.**\n   Read the flag the recomputing producer wrote; never re-derive it. An `ACCEPTED` finding now `KEEP`,\n   a `REJECTED` one now retirement-direction, or an `ACCEPTED` verdict whose authorized act changed\n   (`DOWNGRADE` now `CONSOLIDATE`) means the evidence moved under the operator's decision. Re-confirm\n   the act before anything proceeds.\n\n## Arguments\n\nFinding ids and layer names from the artifact's vocabulary narrow the queue to exactly those\nfindings. Anything else is a free-text hint that orders the queue, reported when it matches nothing.\nNo argument widens the queue or replaces the gate. Bare invocation presents every finding awaiting a\ndecision in the artifact's order; a queue too long for one sitting is said to be, and stopping\nhalfway is a normal end, since statuses persist.\n\n## The queue\n\nPresent every finding in the artifact's order and dispose of each by its status. A finding in one of\nthe justification layers (`decision-records`, `documents`, `components`, `dependencies`, `source`)\nhas no rollback ladder here, and is presented and judged but never remediated: the rung-1-inapplicable\nroute below would turn it into a deletion. Display its evidence, verdict and the owner from that lane's boundary\ntable, say in one line that no rung is offered, and still take the operator's decision (`REJECTED`,\nor `DELEGATED-EXTERNAL` where custody is upstream). Dispatch on `Layer`, never the `check` segment,\nwhich cannot be read back off an id (`findings-artifact.md` \"Finding ids\").\n\n| Status | What this run does with it |\n|---|---|\n| `OPEN` | Present the verdict, its evidence, its cost, and the proposed rung; ask for a decision |\n| `ACCEPTED` | Authorized in an earlier run: re-confirm the rung about to execute, then continue |\n| `REJECTED` · `REALIGNED` | Nothing. Report it as already decided; do not re-ask |\n| `DELEGATED-EXTERNAL` | Report the delegation pointer and its state. Nothing local, ever |\n| `ABLATION-PENDING` | Gate and execute the rung-1 disable, then move to `ABLATION-ACTIVE` |\n| `ABLATION-ACTIVE` | Compare today against the recorded end date; before it, report the window as running and stop there |\n| `ABLATION-CONCLUDED-RETIRE` | Rung 3, behind its own acceptance |\n| `ABLATION-CONCLUDED-KEEP` | Confirm the mechanism is re-enabled, close as KEEP, and offer the durable judgment entry |\n\n## Per accepted finding: the four movements\n\nInterview, explore and research, plan, implement. Each composes a sibling skill via the Skill tool\nwhen its plugin is installed and runs the inline fallback when not. Say which ran and record the\npresence answer on the finding.\n\n| Movement | Composition (presence-gated) | Inline fallback when absent |\n|---|---|---|\n| **Interview**: intent, constraints, what done means | `\u002Fplanning:interview` | Ask the same questions inline as one small numbered set, recommendation first |\n| **Explore**: what the mechanism touches, where it is wired, what depends on it | `\u002Fdiscovery:explore` | Read the artifact, its registration surface and call sites, and list the blast radius before proposing anything |\n| **Research**: is the replacement the rediscovery names real and current | `\u002Fdiscovery:research` | Check its current official documentation and record the check with its date (§5) |\n| **Plan**: rung, exact edit, reversal, observation window | `\u002Fplanning:plan` | Write goal, rung, blast radius and reversal in the response; get it approved before any edit |\n| **Implement** | `\u002Fimplementation:implement` | Make the change against the approved plan, one rung at a time, stopping at the same gates |\n\nRun only the movements the finding needs: a one-key config disable with a settled intent needs no\nresearch pass. Record a skipped one with its reason (\"Skipped research: the rediscovery names a\nmechanism already in this repo\"), never skip it wordlessly.\n\n## Execution order. The rollback ladder\n\n§11 governs, in order; record the rung reached on the finding:\n\n1. **Config-disable**, wherever a kill switch exists. Check §11's trap: where \"unset means enabled\",\n   make the off state explicit, and confirm the disable took effect.\n2. **Observe** for the consumer's configured window, with **its end date written on the finding**\n   and on a durable pointer, since the artifact can be gone before the date.\n3. **Delete, with the rationale recorded** in the change description: the evidence, the observation\n   result, and what re-adds it. Preserve the re-add surface where one exists.\n\n**Withdrawal is a normal outcome.** A window showing the mechanism load-bearing ends at rung 1 with\nit re-enabled and the finding closed as KEEP with the window's evidence. Say so when proposing the\nladder.\n\n**When rung 1 is inapplicable** (nothing registered or wired to disable: a copy nothing reads, a\nclaim in a document, a lane nothing requires), record *\"rung 1 inapplicable: `\u003Creason>`\"* and why\nrung 2 gives no signal. A reversible non-rung remediation (correct a false claim, register the copy\nthat should be wired) is then a valid proposal under its own acceptance. Where deletion is the only\nremaining act, the acceptance must name the deletion explicitly.\n\n**CONSOLIDATE** removes the redundant copy once the survivor is named: disable, observe under the\nsurvivor, delete where the copy is live; deletion named in the acceptance where it is inert.\n\n## UNPROVEN findings. The ablation track\n\nAn UNPROVEN verdict does not authorize a disable. Route it to §8's track: take the head of the\naudit's carry-cost ranking, propose one bounded batch an operator can attend to, name an owner per\nitem (§12), set one window with its end date, and record a durable pointer. Each item still passes\nthe per-item gate. Items below the batch wait for the next window. Protected and intentionally\ndormant items (§7) never enter a batch.\n\n## Protected findings\n\nA `FLAG-FOR-HUMAN` finding is a question, not a task. Present the capped verdict it would otherwise\ncarry, the evidence in full, the protected class and the rule that matched, then stop and wait for\nthe operator's own call on that item, in their words. Never retire a protected mechanism on this\nskill's reasoning, and never route it into an ablation batch to reach the same end. An operator\noverturning the classification records that in the consumer's tracked configuration.\n\n## Out-of-repo custody. Delegate, never patch locally\n\nWhere the audit's custody read placed the artifact upstream (organization policy, a managed or\nsynced copy, a shared workflow this repo only references, a forge control plane), §12 makes the\nremediation a delegation: produce an upstream change request, an administrator issue, or written\ninstructions for the owner, carrying the evidence and proposed rung, and set `DELEGATED-EXTERNAL`\nwith its pointer. Never edit the out-of-repo surface in place or patch a managed copy locally; the\nnext sync reverts it.\n\n## Statuses this skill writes\n\n**Re-read the artifact from disk immediately before every `Status` write, and merge against that\ncopy**; another producer may have written during a long interview.\n\nThis skill is the only writer of `Status`, and writes one only as its outcome happens, never ahead\nof the operator's yes: `ACCEPTED` on acceptance; `REJECTED` when the operator keeps the mechanism;\n`REALIGNED` when the change has landed; `DELEGATED-EXTERNAL` with its pointer; the `ABLATION-*` states\nas a batch moves through its window. A justification-layer row takes `REJECTED` like any other: it\nrecords a judgment and mutates nothing outside the record. Leave every other field as the audit\ncomputed it.\n\n## The durable judgment record\n\n**Offer** to persist a `REJECTED` or `ABLATION-CONCLUDED-KEEP` finding as a suppression entry in the\nconsuming repo's tracked `.claude\u002Foverengineering.md`:\n\n- Show the exact entry before writing it, and write only on an explicit yes under the per-item gate.\n- The `reason` is the operator's own words; ask for them rather than recycling audit prose.\n- Write it to the team-tracked layer: a personal-layer entry does not suppress.\n- Entry keys, the constituents-authoritative rule and the layering are\n  `${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconsumer-config.md`'s. A `REALIGNED` finding needs no entry.\n\n## An unresolved branch identity is its own refusal\n\nThe branch-match check protects against executing one ref's findings against another ref's surface,\nand `HEAD` compares equal to itself. Both unresolved states refuse, and neither reaches the\ncomparison:\n\n- **This checkout has no branch identity** (the call failed and no logical ref was supplied). Stop\n  before reading the artifact and say: *\"Detached checkout, no logical ref supplied; no branch\n  identity, so the artifact's branch cannot be verified and nothing will be executed.\"* No queue, no\n  status transitions, nothing written.\n- **The artifact carries no branch identity** (`branch:` absent, empty or `HEAD`). Refuse it by name,\n  and say that `overengineering:audit` writes no artifact without an identity, so one carrying\n  `HEAD` did not come from this plugin's audit as it stands. Do not repair the field or fall back\n  to its directory.\n\nNever fall back to `HEAD`, the commit sha, or the home's slug to make up either side.\n\n## Next\n\n`\u002Fverification:confirm`. The finding stays open until the landed change is verified.\n\n## Gotchas\n\n- **An accepted finding is not an accepted deletion.** Acceptance authorizes the rung on the table at\n  that moment.\n- **Disable the copy the runtime actually reads.** Where a guard exists in a local and a packaged\n  form, confirm which one the live configuration registers first.\n- **Do not touch what the finding is not about.** A formatting fix, a stale comment or an adjacent\n  tidy in the same file is outside the acceptance given.\n- **A finding you realigned vanishes from the next audit.** The re-run records it under closed since\n  last run; that is the contract working.\n- **Never argue a quality-enabling practice onto the ladder** (§10). Tests, review, type checking,\n  the build, and the record-keeping that makes the evidence tiers readable are outside this method.\n",{"shell":24,"metadata":25,"description":7,"argument-hint":28,"user-invocable":29,"disable-model-invocation":20},"bash",{"summary":26,"workflow-stage":27},"Execute accepted audit findings down the rollback ladder behind a per-item human gate","implement","[finding-id ...] [layer ...]",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Foverengineering\u002Fskills\u002Frealign",7,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins","https:\u002F\u002Fgithub.com\u002Fmelodic-software","https:\u002F\u002Fmelodicsoftware.com","Independent software studio building developer tools, automation, and application services, with roots in music.","2026-11-15 05:15:06",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":29},[41,44,47],{"tool":42,"command":43},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill realign",{"tool":45,"command":46},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill realign",{"tool":48,"command":49},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill realign","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Foverengineering\u002Fskills\u002Frealign\u002FSKILL.md",[52],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"evals\u002Fevals.json","REFERENCE","参考文档",14850,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Foverengineering\u002Fskills\u002Frealign\u002Fevals\u002Fevals.json",[59,66,73,80,85,92],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7DYYDG31B9YX7N9MB9QW2GW","track","Backlog reads through the bound tracker: search open and closed items, view one item with its comments and state history. Use when another skill searches or reads tracker items.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsession-flow\u002Fevals\u002Frecall-still-reports-reopened-bug\u002Fwork-items-stub\u002Fskills\u002Ftrack\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7DYXVBAVG3NV30PA7GKW9Q6","reviewer-media","Reviewer media for one pull request: decides whether it needs a narrated walkthrough, builds the storyboard from \u002Freview:explain-change's digest, has \u002Fexplainer-video:produce render it and hands the manifest to \u002Fsource-control:pull-request media. Use when asked for 'reviewer media', 'a walkthrough video for this PR', 'a produced video of this change', or when pull-request ready or monitor hands a PR over.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Freview\u002Fskills\u002Freviewer-media\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7DYRZ5YD44AMYH26YR25GZ8","route","Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-pin-without-override\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":81,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7DYRTVT4FWTGDJY0HCCFJMZ","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-override-from-route\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7DYNZC8PNW3T27V2ADKECKJ","principles","Module-design vocabulary for architecture findings, and the checks built on it. Use when: 'what is a deep module', 'what is a seam', 'deep vs shallow module', 'what is the deletion test', 'leverage and locality', 'module design vocabulary', 'which word do we use for X in architecture findings'. Scanning a codebase for friction is \u002Farchitecture:improve.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fskills\u002Fprinciples\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7DYNMCZNEWBFHV9KTSS6H60","write","Structured five-field bug report (title, steps to reproduce, expected vs actual, justified severity, suggested fix location) from an informal description, read-only. Use when the user names a defect they observed, or asks for one written up ('report a bug', 'file a bug', 'write this up as a bug').","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fevals\u002Fdeepening-defect-goes-to-bugs-write\u002Fbugs-stub\u002Fskills\u002Fwrite\u002FSKILL.md",[],[]]