[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MEABKAHGPE1EQCQYHSPS21":3,"skill-same:01M6MEABKAHGPE1EQCQYHSPS21":77},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":76},"01M6MEABKAHGPE1EQCQYHSPS21","simplify",null,"Simplify code, plans and systems without losing required outcomes; delete machinery that earns nothing; for code, AST-measured complexity with regression gates. Triggers: simplify, refactor, complexity, overengineered, dead code, useless guard.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Fsimplify\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"outcomes","for","true","with","systems","triggers","plans","gates","simplify code","complexity","workflow","edit","read","ast","regression","Bash","guard","code","delete","2026-11-10 10:12:30",false,"---\nname: simplify\ndescription: \"Simplify code, plans and systems without losing required outcomes; delete machinery that earns nothing; for code, AST-measured complexity with regression gates. Triggers: simplify, refactor, complexity, overengineered, dead code, useless guard.\"\nuser-invocable: true\nallowed-tools: Agent, Bash, Read, Edit, Grep, Glob\nkernel:\n  kind: workflow\n  version: 1\n  side_effects: writes_source\n  confirmation: none\n---\n\n\u003Cskill id=\"simplify\">\n\n\u003Cpurpose>\nSimplification makes the road easier; it does not change the destination. Preserve every required\noutcome, feature, behavior, and explicit constraint. Simplify only how they are delivered: fewer\nbranches, concepts, components, dependencies, states, handoffs, and duplicated mechanisms.\n\nFor code, this skill forces a measured per-function number, records its movement, and installs the\nsame check in the project's normal verification. Prose about \"cleaner code\" is not accepted.\n\nAdapted from saurabhkumar8112\u002Fcyclomatic-complexity-skill (Apache-2.0). The refactoring model\nnever signs its own result; a verifier re-measures and runs the armed project gate.\n\u003C\u002Fpurpose>\n\n\u003Con_start>\nagentdb recall \"simplify complexity \u003Cfiles\u002Fsymbols>\" --global\n\u003C\u002Fon_start>\n\n\u003Cmode>\nPick one at the top of the run and say which:\n- `code` — source changes. Full measure + gate path below.\n- `system` — plans, roadmaps, backlogs, docs, pipelines, process. Preservation contract and\n  deletion doctrine apply; the complexity table does not. Never emit `Reduced: 0 · regressed: 0`\n  for work with no functions in it; use the system report block.\nMixed work runs both blocks, never one blurred into the other.\n\u003C\u002Fmode>\n\n\u003Cdeletion_doctrine>\nDeletion beats repair. When something is broken, the first question is whether it should exist.\n\n- Broken test: is the test wrong? A test asserting behavior nobody requires, or coupling to an\n  implementation detail, gets deleted, not repaired. Delete the test, keep the behavior test.\n- Broken guard, hook, lint rule, or check: does it prevent a real failure that actually happened?\n  No evidence of a caught failure and it costs every run -> delete it. A guard that fires on\n  correct work is worse than no guard: it trains everyone to override.\n- Broken feature path nothing reaches: delete the path, not patch it.\n- Machinery with a cleaner replacement already present: delete the old one in the same change.\n\nCut fast and hard. Do not stage a deprecation for code only this repo calls.\n\nRepair instead of deleting only when: it is on the preservation contract; or it is the sole\ndefense against an irreversible failure (data loss, secret leak, production destruction); or\ndeleting it breaks a published API or another repo's contract. Name which one applies.\n\nEvery deletion is recorded: what, why it earned nothing, what now covers the case (or that\nnothing needs to). Deleting an item on the preservation contract is a scope cut, not a\nsimplification, and is forbidden.\n\u003C\u002Fdeletion_doctrine>\n\n\u003Cpreflight>\nRun before measuring. A mid-run analyzer failure is a preventable state, not a surprise.\n```bash\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --engine auto \u003Crepo-dir> >\u002Fdev\u002Fnull   # exit 3 = no analyzer\ngit fetch -q origin && git diff --quiet origin\u002F\u003Cdefault> -- .complexity-baseline.tsv .ccnrc \\\n  || echo \"baseline\u002Fconfig differs from the default branch: refresh before measuring\"\n```\n- No analyzer (exit 3) or invalid config (exit 2): stop and install it. Never hand-count.\n- JS\u002FTS without project ESLint: the lizard fallback cannot see object-literal methods. Install\n  ESLint or skip the file with that exact reason. Never call the fallback proof.\n- The baseline is a committed file measured against the current default branch. A baseline from a\n  stale checkout is not a baseline; refresh it from `origin\u002F\u003Cdefault>` first and say so.\n- Sandboxed workspace: `complexity.py` redirects an unwritable uv cache to tmp on its own.\n\u003C\u002Fpreflight>\n\n\u003Cmeasure>\n```bash\n# violations, worst first (TSV: file, line, function, ccn, nloc)\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh \u003Crepo-dir>\n# only what this branch changed\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh \u003Crepo-dir> \u003Cbase-ref>\n# complete snapshot + before\u002Fcurrent diff\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --all \u003Crepo-dir> > before.tsv\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --diff before.tsv \u003Crepo-dir>\n# CI ratchet: baseline contains only current over-budget debt\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --check-baseline .complexity-baseline.tsv \u003Crepo-dir>\n```\n\nProject config is `.ccnrc` JSON:\n\n```json\n{\n  \"version\": 1,\n  \"default\": 15,\n  \"budgets\": { \"src\u002Fmachine.ts:transition\": 20 },\n  \"skip\": { \"src\u002Flegacy-repo.ts:*\": \"lizard cannot enter createLegacyRepo's returned methods\" }\n}\n```\n\nSelectors are `repo-relative-file:function` globs. `--skip 'selector=reason'` is the one-run\nequivalent. A skip without a reason is invalid. Budgets are declared design constraints, not a\nway to bless today's number: name why the function earns the higher ceiling in the config diff.\n\nLadder (default, project config outranks it):\n- 1 to 5: leave alone\n- 6 to 10: refactor only if already touching\n- 11 to 15: refactor now\n- over 15: must split\n\u003C\u002Fmeasure>\n\n\u003Cworkflow>\n1. Write the preservation contract to `.simplify-contract.md` before editing: every required\n   outcome, feature, behavior, explicit constraint, and acceptance condition from the request and\n   current source of truth, one checkable line each, with its source. Deferred is not preserved\n   unless the source already defers it. A contract held only in the model's head is not a\n   contract; the verifier diffs this file.\n2. Trace each contract line to a concrete part of the proposed result, in the file. Any line with\n   no route invalidates the simplification. Never redefine product scope, success, or priority to\n   make the implementation smaller.\n3. List deletion candidates against `\u003Cdeletion_doctrine>`: dead paths, tests asserting nothing\n   required, guards with no caught-failure evidence, superseded machinery. Cut them first; the\n   cheapest complexity reduction is code that stops existing.\n4. `code` mode: run preflight, then measure. Print the table before touching anything, ranked by\n   CCN descending. `system` mode: skip to 8.\n5. Confirm tests exist and pass. None: say so, refactor conservatively, propose one test per\n   extracted function.\n6. Save `--all` output as the before baseline. Refactor worst first, one function at a time.\n7. Re-measure with `--diff before.tsv`. Any `regressed` row is unresolved.\n8. Wire the project-owned gate before handoff:\n   - add a `complexity` script\u002Fcheck using the project's checked-in runner or native analyzer;\n   - seed `.complexity-baseline.tsv` with current over-budget rows only; the CI ratchet\n     grandfathers those exact values, rejects increases\u002Fnew violations, and requires a refreshed\n     baseline after reductions or removals;\n   - commit the baseline and record the ref it was measured against;\n   - include it in `npm run verify`, Make\u002Fjust verify, or the existing pre-commit gate;\n   - run that exact parent command red against a seeded over-budget fixture, then green;\n   - never point CI at a developer's plugin-cache path.\n9. Re-check `.simplify-contract.md` line by line against the result. Anything dropped, weakened,\n   postponed, or made optional is a regression, even when the complexity score improves. Every\n   surviving line that moved to a later phase names its delivery route and acceptance condition\n   in the file, or it was cut.\n10. Hand off to the verifier. Its fresh diff, contract check, deletion review, and armed-gate run\n    are the record.\n\u003C\u002Fworkflow>\n\n\u003Ctactics order=\"preference\">\n1. Delete it. Nothing is simpler than absent code.\n2. Guard clauses: invert, return early, kill nesting.\n3. Extract function. The name says what, not how. Names are documentation.\n4. Lookup table or map instead of if\u002Felse or switch chains.\n5. Named predicates: `if is_eligible_for_refund(order)` beats a four-clause boolean.\n6. Polymorphism or strategy for switch-on-type, only when the switch appears in 2+ places.\n7. Flatten loops: extract the body, `continue` instead of nested `if`.\n\u003C\u002Ftactics>\n\n\u003Chard_rules>\n- Preserve the destination: every requested outcome and feature remains required and reachable.\n  Simplify architecture and execution, never the user's ambition or product scope.\n- Preserve behavior that anything requires. Tests before and after. Same inputs, same outputs,\n  same errors.\n- Removal is allowed, and preferred, for duplication, dead paths, unearning guards, and machinery\n  whose absence cannot change any contract line. \"Not now,\" \"later,\" \"manual for the pilot,\" and\n  narrower audiences\u002Fproducts are scope cuts when the source of truth did not already say them.\n- Do not use sequencing as deletion. Later phases must still name their delivery route and\n  acceptance condition; evidence gates may reorder work, but cannot cancel it.\n- Do not game the metric. A dense one-liner hiding six branches is worse than the honest\n  if-chain it replaced. Complexity moves into named units; it never disappears into cleverness.\n  A CCN drop with a rising token count per line is the tell.\n- Do not change public APIs or exported signatures without asking.\n- One responsibility per function. If the name needs \"and\", split again.\n- Small functions with clear names beat few functions with section comments.\n- No optional finish: a manual complexity command without project verify\u002Fpre-commit wiring is\n  incomplete.\n- Never introduce the gate red on the existing default branch. Snapshot current debt, declare\n  narrow budgets with reasons, then tighten them as functions improve.\n- The verifier is a different agent than the builder. `self`, `builder self-measure`, `primary\n  lane validation`, a script the builder wrote this session, and an unfilled `\u003Cverifier identity>`\n  placeholder are all invalid signatures. An unsigned report is an unfinished run.\n\u003C\u002Fhard_rules>\n\n\u003Cverify>\nSpawn a verifier that never saw this session's reasoning. It receives: the diff,\n`.simplify-contract.md`, the deletion list, the before table, the claimed after table, the test\ncommand, and this contract:\n\n```\nACCEPTANCE: every contract line has an equally strong delivery route; every deletion is justified under the deletion doctrine; no measured function regresses; budgets hold; the project's normal verify path runs the gate\nACCEPT WHEN: contract file checks line by line with zero removed, weakened, newly deferred, or optional outcomes; every deleted test\u002Fguard\u002Fpath names what it failed to earn and what covers the case now; fresh --diff says regressed=0; project verify passes; seeded over-budget fixture makes it fail; no exported signature changed\nCHECK: diff .simplify-contract.md against the source of truth and the result line by line; ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --diff \u003Cbefore.tsv> \u003Crepo>; \u003Cproject verify command>; \u003Cseeded failure probe>; git diff \u003Cbase-ref> --diff-filter=D --name-only; git diff \u003Cbase-ref> -- \u003Cfiles> | grep -E '^[-+](def |export |func |pub fn )'\nESCALATE IF: any contract line lacks a route or became weaker\u002Flater\u002Foptional; a deletion removed the only defense against an irreversible failure; AST-aware JS\u002FTS parsing is unavailable for object-literal methods; any row regresses; a skip lacks a concrete parser limitation; or a one-liner replaced a branch without a name\nDISCOVERY AXIS: invariant\n```\nBuilder and verifier identities go on the receipt and must differ. The builder never fills in\n\"behavior verified\".\n\u003C\u002Fverify>\n\n\u003Coutput>\nEnd with the block for the mode you ran, and nothing after it.\n\n`code`:\n```\n## Complexity report\nReduced: N · unchanged: N · regressed: 0 · removed: N\nDeleted: \u003Cfile:symbol - what it failed to earn> | none\nDestination: N\u002FN contract lines preserved · weakened\u002Fdeferred\u002Fremoved: 0 (.simplify-contract.md)\nBudgets: \u003Cconfig path>; exceptions: \u003Cnone | selectors + reasons>\nGate: \u003Cproject verify command> (seeded red -> clean green), baseline @ \u003Cref>\nVerified by: \u003Cverifier identity, not the builder>\n```\n\n`system`:\n```\n## Simplification report\nDestination: N\u002FN contract lines preserved · weakened\u002Fdeferred\u002Fremoved: 0 (.simplify-contract.md)\nRemoved: \u003Cduplicated mechanism \u002F dead step \u002F unearning gate - why it earned nothing> | none\nCollapsed: \u003Cwhat merged into what>\nSequenced: \u003Citem - later phase, its delivery route, its acceptance condition> | none\nVerified by: \u003Cverifier identity, not the builder>\n```\nKeep prose minimal. Numbers and diffs do the talking.\n\u003C\u002Foutput>\n\n\u003C\u002Fskill>\n","\u003Cskill id=\"simplify\">\n\n\u003Cpurpose>\nSimplification makes the road easier; it does not change the destination. Preserve every required\noutcome, feature, behavior, and explicit constraint. Simplify only how they are delivered: fewer\nbranches, concepts, components, dependencies, states, handoffs, and duplicated mechanisms.\n\nFor code, this skill forces a measured per-function number, records its movement, and installs the\nsame check in the project's normal verification. Prose about \"cleaner code\" is not accepted.\n\nAdapted from saurabhkumar8112\u002Fcyclomatic-complexity-skill (Apache-2.0). The refactoring model\nnever signs its own result; a verifier re-measures and runs the armed project gate.\n\u003C\u002Fpurpose>\n\n\u003Con_start>\nagentdb recall \"simplify complexity \u003Cfiles\u002Fsymbols>\" --global\n\u003C\u002Fon_start>\n\n\u003Cmode>\nPick one at the top of the run and say which:\n- `code` — source changes. Full measure + gate path below.\n- `system` — plans, roadmaps, backlogs, docs, pipelines, process. Preservation contract and\n  deletion doctrine apply; the complexity table does not. Never emit `Reduced: 0 · regressed: 0`\n  for work with no functions in it; use the system report block.\nMixed work runs both blocks, never one blurred into the other.\n\u003C\u002Fmode>\n\n\u003Cdeletion_doctrine>\nDeletion beats repair. When something is broken, the first question is whether it should exist.\n\n- Broken test: is the test wrong? A test asserting behavior nobody requires, or coupling to an\n  implementation detail, gets deleted, not repaired. Delete the test, keep the behavior test.\n- Broken guard, hook, lint rule, or check: does it prevent a real failure that actually happened?\n  No evidence of a caught failure and it costs every run -> delete it. A guard that fires on\n  correct work is worse than no guard: it trains everyone to override.\n- Broken feature path nothing reaches: delete the path, not patch it.\n- Machinery with a cleaner replacement already present: delete the old one in the same change.\n\nCut fast and hard. Do not stage a deprecation for code only this repo calls.\n\nRepair instead of deleting only when: it is on the preservation contract; or it is the sole\ndefense against an irreversible failure (data loss, secret leak, production destruction); or\ndeleting it breaks a published API or another repo's contract. Name which one applies.\n\nEvery deletion is recorded: what, why it earned nothing, what now covers the case (or that\nnothing needs to). Deleting an item on the preservation contract is a scope cut, not a\nsimplification, and is forbidden.\n\u003C\u002Fdeletion_doctrine>\n\n\u003Cpreflight>\nRun before measuring. A mid-run analyzer failure is a preventable state, not a surprise.\n```bash\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --engine auto \u003Crepo-dir> >\u002Fdev\u002Fnull   # exit 3 = no analyzer\ngit fetch -q origin && git diff --quiet origin\u002F\u003Cdefault> -- .complexity-baseline.tsv .ccnrc \\\n  || echo \"baseline\u002Fconfig differs from the default branch: refresh before measuring\"\n```\n- No analyzer (exit 3) or invalid config (exit 2): stop and install it. Never hand-count.\n- JS\u002FTS without project ESLint: the lizard fallback cannot see object-literal methods. Install\n  ESLint or skip the file with that exact reason. Never call the fallback proof.\n- The baseline is a committed file measured against the current default branch. A baseline from a\n  stale checkout is not a baseline; refresh it from `origin\u002F\u003Cdefault>` first and say so.\n- Sandboxed workspace: `complexity.py` redirects an unwritable uv cache to tmp on its own.\n\u003C\u002Fpreflight>\n\n\u003Cmeasure>\n```bash\n# violations, worst first (TSV: file, line, function, ccn, nloc)\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh \u003Crepo-dir>\n# only what this branch changed\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh \u003Crepo-dir> \u003Cbase-ref>\n# complete snapshot + before\u002Fcurrent diff\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --all \u003Crepo-dir> > before.tsv\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --diff before.tsv \u003Crepo-dir>\n# CI ratchet: baseline contains only current over-budget debt\n${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --check-baseline .complexity-baseline.tsv \u003Crepo-dir>\n```\n\nProject config is `.ccnrc` JSON:\n\n```json\n{\n  \"version\": 1,\n  \"default\": 15,\n  \"budgets\": { \"src\u002Fmachine.ts:transition\": 20 },\n  \"skip\": { \"src\u002Flegacy-repo.ts:*\": \"lizard cannot enter createLegacyRepo's returned methods\" }\n}\n```\n\nSelectors are `repo-relative-file:function` globs. `--skip 'selector=reason'` is the one-run\nequivalent. A skip without a reason is invalid. Budgets are declared design constraints, not a\nway to bless today's number: name why the function earns the higher ceiling in the config diff.\n\nLadder (default, project config outranks it):\n- 1 to 5: leave alone\n- 6 to 10: refactor only if already touching\n- 11 to 15: refactor now\n- over 15: must split\n\u003C\u002Fmeasure>\n\n\u003Cworkflow>\n1. Write the preservation contract to `.simplify-contract.md` before editing: every required\n   outcome, feature, behavior, explicit constraint, and acceptance condition from the request and\n   current source of truth, one checkable line each, with its source. Deferred is not preserved\n   unless the source already defers it. A contract held only in the model's head is not a\n   contract; the verifier diffs this file.\n2. Trace each contract line to a concrete part of the proposed result, in the file. Any line with\n   no route invalidates the simplification. Never redefine product scope, success, or priority to\n   make the implementation smaller.\n3. List deletion candidates against `\u003Cdeletion_doctrine>`: dead paths, tests asserting nothing\n   required, guards with no caught-failure evidence, superseded machinery. Cut them first; the\n   cheapest complexity reduction is code that stops existing.\n4. `code` mode: run preflight, then measure. Print the table before touching anything, ranked by\n   CCN descending. `system` mode: skip to 8.\n5. Confirm tests exist and pass. None: say so, refactor conservatively, propose one test per\n   extracted function.\n6. Save `--all` output as the before baseline. Refactor worst first, one function at a time.\n7. Re-measure with `--diff before.tsv`. Any `regressed` row is unresolved.\n8. Wire the project-owned gate before handoff:\n   - add a `complexity` script\u002Fcheck using the project's checked-in runner or native analyzer;\n   - seed `.complexity-baseline.tsv` with current over-budget rows only; the CI ratchet\n     grandfathers those exact values, rejects increases\u002Fnew violations, and requires a refreshed\n     baseline after reductions or removals;\n   - commit the baseline and record the ref it was measured against;\n   - include it in `npm run verify`, Make\u002Fjust verify, or the existing pre-commit gate;\n   - run that exact parent command red against a seeded over-budget fixture, then green;\n   - never point CI at a developer's plugin-cache path.\n9. Re-check `.simplify-contract.md` line by line against the result. Anything dropped, weakened,\n   postponed, or made optional is a regression, even when the complexity score improves. Every\n   surviving line that moved to a later phase names its delivery route and acceptance condition\n   in the file, or it was cut.\n10. Hand off to the verifier. Its fresh diff, contract check, deletion review, and armed-gate run\n    are the record.\n\u003C\u002Fworkflow>\n\n\u003Ctactics order=\"preference\">\n1. Delete it. Nothing is simpler than absent code.\n2. Guard clauses: invert, return early, kill nesting.\n3. Extract function. The name says what, not how. Names are documentation.\n4. Lookup table or map instead of if\u002Felse or switch chains.\n5. Named predicates: `if is_eligible_for_refund(order)` beats a four-clause boolean.\n6. Polymorphism or strategy for switch-on-type, only when the switch appears in 2+ places.\n7. Flatten loops: extract the body, `continue` instead of nested `if`.\n\u003C\u002Ftactics>\n\n\u003Chard_rules>\n- Preserve the destination: every requested outcome and feature remains required and reachable.\n  Simplify architecture and execution, never the user's ambition or product scope.\n- Preserve behavior that anything requires. Tests before and after. Same inputs, same outputs,\n  same errors.\n- Removal is allowed, and preferred, for duplication, dead paths, unearning guards, and machinery\n  whose absence cannot change any contract line. \"Not now,\" \"later,\" \"manual for the pilot,\" and\n  narrower audiences\u002Fproducts are scope cuts when the source of truth did not already say them.\n- Do not use sequencing as deletion. Later phases must still name their delivery route and\n  acceptance condition; evidence gates may reorder work, but cannot cancel it.\n- Do not game the metric. A dense one-liner hiding six branches is worse than the honest\n  if-chain it replaced. Complexity moves into named units; it never disappears into cleverness.\n  A CCN drop with a rising token count per line is the tell.\n- Do not change public APIs or exported signatures without asking.\n- One responsibility per function. If the name needs \"and\", split again.\n- Small functions with clear names beat few functions with section comments.\n- No optional finish: a manual complexity command without project verify\u002Fpre-commit wiring is\n  incomplete.\n- Never introduce the gate red on the existing default branch. Snapshot current debt, declare\n  narrow budgets with reasons, then tighten them as functions improve.\n- The verifier is a different agent than the builder. `self`, `builder self-measure`, `primary\n  lane validation`, a script the builder wrote this session, and an unfilled `\u003Cverifier identity>`\n  placeholder are all invalid signatures. An unsigned report is an unfinished run.\n\u003C\u002Fhard_rules>\n\n\u003Cverify>\nSpawn a verifier that never saw this session's reasoning. It receives: the diff,\n`.simplify-contract.md`, the deletion list, the before table, the claimed after table, the test\ncommand, and this contract:\n\n```\nACCEPTANCE: every contract line has an equally strong delivery route; every deletion is justified under the deletion doctrine; no measured function regresses; budgets hold; the project's normal verify path runs the gate\nACCEPT WHEN: contract file checks line by line with zero removed, weakened, newly deferred, or optional outcomes; every deleted test\u002Fguard\u002Fpath names what it failed to earn and what covers the case now; fresh --diff says regressed=0; project verify passes; seeded over-budget fixture makes it fail; no exported signature changed\nCHECK: diff .simplify-contract.md against the source of truth and the result line by line; ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --diff \u003Cbefore.tsv> \u003Crepo>; \u003Cproject verify command>; \u003Cseeded failure probe>; git diff \u003Cbase-ref> --diff-filter=D --name-only; git diff \u003Cbase-ref> -- \u003Cfiles> | grep -E '^[-+](def |export |func |pub fn )'\nESCALATE IF: any contract line lacks a route or became weaker\u002Flater\u002Foptional; a deletion removed the only defense against an irreversible failure; AST-aware JS\u002FTS parsing is unavailable for object-literal methods; any row regresses; a skip lacks a concrete parser limitation; or a one-liner replaced a branch without a name\nDISCOVERY AXIS: invariant\n```\nBuilder and verifier identities go on the receipt and must differ. The builder never fills in\n\"behavior verified\".\n\u003C\u002Fverify>\n\n\u003Coutput>\nEnd with the block for the mode you ran, and nothing after it.\n\n`code`:\n```\n## Complexity report\nReduced: N · unchanged: N · regressed: 0 · removed: N\nDeleted: \u003Cfile:symbol - what it failed to earn> | none\nDestination: N\u002FN contract lines preserved · weakened\u002Fdeferred\u002Fremoved: 0 (.simplify-contract.md)\nBudgets: \u003Cconfig path>; exceptions: \u003Cnone | selectors + reasons>\nGate: \u003Cproject verify command> (seeded red -> clean green), baseline @ \u003Cref>\nVerified by: \u003Cverifier identity, not the builder>\n```\n\n`system`:\n```\n## Simplification report\nDestination: N\u002FN contract lines preserved · weakened\u002Fdeferred\u002Fremoved: 0 (.simplify-contract.md)\nRemoved: \u003Cduplicated mechanism \u002F dead step \u002F unearning gate - why it earned nothing> | none\nCollapsed: \u003Cwhat merged into what>\nSequenced: \u003Citem - later phase, its delivery route, its acceptance condition> | none\nVerified by: \u003Cverifier identity, not the builder>\n```\nKeep prose minimal. Numbers and diffs do the talking.\n\u003C\u002Foutput>\n\n\u003C\u002Fskill>\n",{"name":5,"kernel":48,"description":7,"allowed-tools":52,"user-invocable":53},{"kind":34,"version":49,"confirmation":50,"side_effects":51},1,"none","writes_source","Agent, Bash, Read, Edit, Grep, Glob",true,"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Fsimplify",491,"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 14:06:13",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":53},[66,69,72],{"tool":67,"command":68},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill simplify",{"tool":70,"command":71},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill simplify",{"tool":73,"command":74},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill simplify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Fsimplify\u002FSKILL.md",[],[78,88,96,104,112,120],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":87},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":87},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":87},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":87},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":87},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":124,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":87},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]