[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70GP7MX6J067492PR75HN6C":3,"skill-same:01M70GP7MX6J067492PR75HN6C":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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M70GP7MX6J067492PR75HN6C","plankton-code-quality",null,"Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks. Use when setting up write-time formatting, linting, or auto-fix hooks on file edits.","mdnaimul22\u002Fhuman-skills","mdnaimul22","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64520358?v=4","01M70FH95MH2H796Q01TYSFZ03","Naimul","01M70FH96798CQR4YHA13F17GA",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fplankton-code-quality\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"code quality","quality","code","plankton","plankton code quality","formatting","linting","when","up","hooks","community","file","use","enforcement","edit","write","auto","auto-fix","fix","time","2026-11-10 10:12:30",false,"---\nname: plankton-code-quality\ndescription: \"Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks. Use when setting up write-time formatting, linting, or auto-fix hooks on file edits.\"\nmetadata:\n  origin: community\n---\n\n# Plankton Code Quality Skill\n\nIntegration reference for Plankton (credit: @alxfazio), a write-time code quality enforcement system for Claude Code. Plankton runs formatters and linters on every file edit via PostToolUse hooks, then spawns Claude subprocesses to fix violations the agent didn't catch.\n\n## When to Use\n\n- You want automatic formatting and linting on every file edit (not just at commit time)\n- You need defense against agents modifying linter configs to pass instead of fixing code\n- You want tiered model routing for fixes (Haiku for simple style, Sonnet for logic, Opus for types)\n- You work with multiple languages (Python, TypeScript, Shell, YAML, JSON, TOML, Markdown, Dockerfile)\n\n## How It Works\n\n### Three-Phase Architecture\n\nEvery time Claude Code edits or writes a file, Plankton's `multi_linter.sh` PostToolUse hook runs:\n\n```\nPhase 1: Auto-Format (Silent)\n├─ Runs formatters (ruff format, biome, shfmt, taplo, markdownlint)\n├─ Fixes 40-50% of issues silently\n└─ No output to main agent\n\nPhase 2: Collect Violations (JSON)\n├─ Runs linters and collects unfixable violations\n├─ Returns structured JSON: {line, column, code, message, linter}\n└─ Still no output to main agent\n\nPhase 3: Delegate + Verify\n├─ Spawns claude -p subprocess with violations JSON\n├─ Routes to model tier based on violation complexity:\n│   ├─ Haiku: formatting, imports, style (E\u002FW\u002FF codes) — 120s timeout\n│   ├─ Sonnet: complexity, refactoring (C901, PLR codes, oxlint complexity) — 300s timeout\n│   └─ Opus: type system, deep reasoning (unresolved-attribute) — 600s timeout\n├─ Re-runs Phase 1+2 to verify fixes\n└─ Exit 0 if clean, Exit 2 if violations remain (reported to main agent)\n```\n\n### What the Main Agent Sees\n\n| Scenario | Agent sees | Hook exit |\n|----------|-----------|-----------|\n| No violations | Nothing | 0 |\n| All fixed by subprocess | Nothing | 0 |\n| Violations remain after subprocess | `[hook] N violation(s) remain` | 2 |\n| Advisory (duplicates, old tooling) | `[hook:advisory] ...` | 0 |\n\nThe main agent only sees issues the subprocess couldn't fix. Most quality problems are resolved transparently.\n\n### Config Protection (Defense Against Rule-Gaming)\n\nLLMs will modify `.ruff.toml` or `biome.json` to disable rules rather than fix code. Plankton blocks this with three layers:\n\n1. **PreToolUse hook** — `protect_linter_configs.sh` blocks edits to all linter configs before they happen\n2. **Stop hook** — `stop_config_guardian.sh` detects config changes via `git diff` at session end\n3. **Protected files list** — `.ruff.toml`, `biome.json`, `.shellcheckrc`, `.yamllint`, `.hadolint.yaml`, and more\n\n### Package Manager Enforcement\n\nA PreToolUse hook on Bash blocks legacy package managers:\n- `pip`, `pip3`, `poetry`, `pipenv` → Blocked (use `uv`)\n- `npm`, `yarn`, `pnpm` → Blocked (use `bun`)\n- Allowed exceptions: `npm audit`, `npm view`, `npm publish`\n\n## Setup\n\n### Quick Start\n\n> **Note:** Plankton requires manual installation from its repository. Review the code before installing.\n\n```bash\n# Install core dependencies\nbrew install jaq ruff uv\n\n# Install Python linters\nuv sync --all-extras\n\n# Start Claude Code — hooks activate automatically\nclaude\n```\n\nNo install command, no plugin config. The hooks in `.claude\u002Fsettings.json` are picked up automatically when you run Claude Code in the Plankton directory.\n\n### Per-Project Integration\n\nTo use Plankton hooks in your own project:\n\n1. Copy `.claude\u002Fhooks\u002F` directory to your project\n2. Copy `.claude\u002Fsettings.json` hook configuration\n3. Copy linter config files (`.ruff.toml`, `biome.json`, etc.)\n4. Install the linters for your languages\n\n### Language-Specific Dependencies\n\n| Language | Required | Optional |\n|----------|----------|----------|\n| Python | `ruff`, `uv` | `ty` (types), `vulture` (dead code), `bandit` (security) |\n| TypeScript\u002FJS | `biome`; `oxlint` (>= 1.37.0) when using `complexity` | `semgrep`, `knip` (dead exports) |\n| Shell | `shellcheck`, `shfmt` | — |\n| YAML | `yamllint` | — |\n| Markdown | `markdownlint-cli2` | — |\n| Dockerfile | `hadolint` (>= 2.12.0) | — |\n| TOML | `taplo` | — |\n| JSON | `jaq` | — |\n\n## Pairing with ECC\n\n### Complementary, Not Overlapping\n\n| Concern | ECC | Plankton |\n|---------|-----|----------|\n| Code quality enforcement | PostToolUse hooks (Prettier, tsc) | PostToolUse hooks (20+ linters + subprocess fixes) |\n| Security scanning | AgentShield, security-reviewer agent | Bandit (Python), Semgrep (TypeScript) |\n| Config protection | — | PreToolUse blocks + Stop hook detection |\n| Package manager | Detection + setup | Enforcement (blocks legacy PMs) |\n| CI integration | — | Pre-commit hooks for git |\n| Model routing | Manual (`\u002Fmodel opus`) | Automatic (violation complexity → tier) |\n\n### Recommended Combination\n\n1. Install ECC as your plugin (agents, skills, commands, rules)\n2. Add Plankton hooks for write-time quality enforcement\n3. Use AgentShield for security audits\n4. Use ECC's verification-loop as a final gate before PRs\n\n### Avoiding Hook Conflicts\n\nIf running both ECC and Plankton hooks:\n- ECC's Prettier hook and Plankton's biome formatter may conflict on JS\u002FTS files\n- Resolution: disable ECC's Prettier PostToolUse hook when using Plankton (Plankton's biome is more comprehensive)\n- Both can coexist on different file types (ECC handles what Plankton doesn't cover)\n\n## Configuration Reference\n\nPlankton's `.claude\u002Fhooks\u002Fconfig.json` controls all behavior:\n\n```json\n{\n  \"languages\": {\n    \"python\": true,\n    \"shell\": true,\n    \"yaml\": true,\n    \"json\": true,\n    \"toml\": true,\n    \"dockerfile\": true,\n    \"markdown\": true,\n    \"typescript\": {\n      \"enabled\": true,\n      \"js_runtime\": \"auto\",\n      \"biome_nursery\": \"warn\",\n      \"semgrep\": true\n    }\n  },\n  \"phases\": {\n    \"auto_format\": true,\n    \"subprocess_delegation\": true\n  },\n  \"subprocess\": {\n    \"tiers\": {\n      \"haiku\":  { \"timeout\": 120, \"max_turns\": 10 },\n      \"sonnet\": { \"timeout\": 300, \"max_turns\": 10 },\n      \"opus\":   { \"timeout\": 600, \"max_turns\": 15 }\n    },\n    \"volume_threshold\": 5\n  }\n}\n```\n\n**Key settings:**\n- Disable languages you don't use to speed up hooks\n- `volume_threshold` — violations > this count auto-escalate to a higher model tier\n- `subprocess_delegation: false` — skip Phase 3 entirely (just report violations)\n\n## Environment Overrides\n\n| Variable | Purpose |\n|----------|---------|\n| `HOOK_SKIP_SUBPROCESS=1` | Skip Phase 3, report violations directly |\n| `HOOK_SUBPROCESS_TIMEOUT=N` | Override tier timeout |\n| `HOOK_DEBUG_MODEL=1` | Log model selection decisions |\n| `HOOK_SKIP_PM=1` | Bypass package manager enforcement |\n\n## References\n\n- Plankton (credit: @alxfazio)\n- Plankton REFERENCE.md — Full architecture documentation (credit: @alxfazio)\n- Plankton SETUP.md — Detailed installation guide (credit: @alxfazio)\n\n## ECC v1.8 Additions\n\n### Copyable Hook Profile\n\nSet strict quality behavior:\n\n```bash\nexport ECC_HOOK_PROFILE=strict\nexport ECC_QUALITY_GATE_FIX=true\nexport ECC_QUALITY_GATE_STRICT=true\n```\n\n### Language Gate Table\n\n- TypeScript\u002FJavaScript: Biome preferred, Prettier fallback\n- Python: Ruff format\u002Fcheck\n- Go: gofmt\n\n### Config Tamper Guard\n\nDuring quality enforcement, flag changes to config files in same iteration:\n\n- `biome.json`, `.eslintrc*`, `prettier.config*`, `tsconfig.json`, `pyproject.toml`\n\nIf config is changed to suppress violations, require explicit review before merge.\n\n### CI Integration Pattern\n\nUse the same commands in CI as local hooks:\n\n1. run formatter checks\n2. run lint\u002Ftype checks\n3. fail fast on strict mode\n4. publish remediation summary\n\n### Health Metrics\n\nTrack:\n- edits flagged by gates\n- average remediation time\n- repeat violations by category\n- merge blocks due to gate failures\n\n---\n\n## Gabe's addition: oxlint complexity + ratchet ceiling (JS\u002FTS)\n\nCloses the JS\u002FTS gap in the model-routing table above. Python complexity (ruff C901,\nPLR) already routes to Sonnet. JS\u002FTS had no equivalent rule turned on by default.\n\n### Turn on oxlint's `complexity` rule when using it\n\noxlint's `complexity` rule (source: eslint's `complexity` rule, ported) lives in the\n\"restriction\" category, which oxlint does not enable by default. It must be turned on\nby hand. Verified against [Oxlint's complexity rule](https:\u002F\u002Foxc.rs\u002Fdocs\u002Fguide\u002Fusage\u002Flinter\u002Frules\u002Feslint\u002Fcomplexity)\n(2026-08-27): default option is `max: 20`. The rule is available in oxlint >= 1.37.0.\n\nThe skill's Language-Specific Dependencies table keeps `oxlint` optional for TypeScript\u002FJS\ngenerally. When adopting the `complexity` rule, use oxlint >= 1.37.0 and treat it as a\nrequired dependency. Add the rule to the supported oxlint configuration the project already\nuses (`.oxlintrc.json`, `.oxlintrc.jsonc`, `oxlint.config.ts`, or `oxlint.config.mts`). If\nnone exists, create one; do not create a second configuration file in the same directory.\n\nMeasure the codebase's current worst complexity score before choosing the initial enforced\nceiling. The template below is intentionally incomplete: replace `\u003CMEASURED_CEILING>` with\nthat score, optionally plus a small amount of headroom, before committing the `\"error\"` gate.\nOxlint's default of 20 is a long-term target, not a safe universal starting ceiling.\n\n```json\n{\n  \"rules\": {\n    \"complexity\": [\"error\", { \"max\": \"\u003CMEASURED_CEILING>\" }]\n  }\n}\n```\n\nReplace the placeholder before running oxlint; it is not a valid numeric threshold until the\nrepository has been measured. See the ratchet section below for how the ceiling gets set on\na real codebase.\n\n### Model-routing row\n\nAdd oxlint `complexity` violations to the same row as the existing Python entry in the\nPhase 3 subprocess table:\n\n```\n├─ Sonnet: complexity, refactoring (C901, PLR codes, oxlint complexity), 300s timeout\n```\n\nSame tier as Python's C901\u002FPLR. A complexity violation is a refactoring job either way,\nlanguage does not change the model tier.\n\n### The ratchet-ceiling technique\n\nSource: [Hunk PR #861](https:\u002F\u002Fgithub.com\u002Fmodem-dev\u002Fhunk\u002Fpull\u002F861) (merged 2026-08-26, verified against\nthe PR's own diff and description via the GitHub API, not paraphrased from memory). Hunk\nturned on oxlint's `complexity` rule with `\"error\", { \"max\": 80 }` in `.oxlintrc.json`.\nTheir own worst score at the time was 78 (`App`), next was 76\n(`validateFileViewLayout`). From the PR body: \"This is intentionally an initial\nregression ceiling rather than the long-term target... so 80 adds enforcement without\ngrandfathering or suppressions. The ceiling can be ratcheted downward as existing\nhotspots are simplified.\" And: \"A global ceiling does not prevent a function below 80\nfrom growing toward it.\"\n\nThe technique, as actually run in that PR:\n\n1. Measure the current worst complexity score in the codebase (oxlint reports it when\n   the rule fires).\n2. Set the ENFORCED ceiling to a value at least as high as that worst score, not to\n   oxlint's own default of 20. Add a small amount of headroom if needed so the initial\n   enable does not fail CI on a score you have not fixed yet (hunk used 80 against a\n   worst of 78).\n3. Commit that as `\"error\"`, wired into the existing lint CI step. This is a real gate\n   from the first commit, not a suggestion.\n4. Never grandfather. The ceiling is global. A function sitting at 40 today is not\n   exempt, it still cannot cross the ceiling later. That is the whole point: catch\n   growth, not just today's worst offenders.\n5. Never blanket-suppress. No per-file or per-function disable comments to make a\n   violation go away. Fix it or leave it under the ceiling.\n6. Each time a flagged hotspot is refactored below the ceiling, re-measure the global\n   maximum across the whole codebase. Lower the ceiling by hand only to a value that\n   remains at least as high as every remaining function's score (plus any deliberate\n   headroom). This is a manual step done as its own commit, not automated. It is how the\n   ceiling moves toward the linter's real default of 20 over time instead of sitting at\n   the codebase's worst score forever.\n\nOne caveat, stated plainly: the PR itself went straight from \"rule off\" to `\"error\"`\nenforcement in one commit. It did not stage through a report-only or warn-only phase\nfirst. Starting with the rule set to `\"warn\"` for one CI run before flipping it to\n`\"error\"` is a reasonable staging step if a team has never measured its own worst score\nand does not want a surprise CI failure, but that staging step is Gabe's own prudent\npractice, not something verified in hunk's PR. Say so if you use it, do not attribute it\nto the source.\n","# Plankton Code Quality Skill\n\nIntegration reference for Plankton (credit: @alxfazio), a write-time code quality enforcement system for Claude Code. Plankton runs formatters and linters on every file edit via PostToolUse hooks, then spawns Claude subprocesses to fix violations the agent didn't catch.\n\n## When to Use\n\n- You want automatic formatting and linting on every file edit (not just at commit time)\n- You need defense against agents modifying linter configs to pass instead of fixing code\n- You want tiered model routing for fixes (Haiku for simple style, Sonnet for logic, Opus for types)\n- You work with multiple languages (Python, TypeScript, Shell, YAML, JSON, TOML, Markdown, Dockerfile)\n\n## How It Works\n\n### Three-Phase Architecture\n\nEvery time Claude Code edits or writes a file, Plankton's `multi_linter.sh` PostToolUse hook runs:\n\n```\nPhase 1: Auto-Format (Silent)\n├─ Runs formatters (ruff format, biome, shfmt, taplo, markdownlint)\n├─ Fixes 40-50% of issues silently\n└─ No output to main agent\n\nPhase 2: Collect Violations (JSON)\n├─ Runs linters and collects unfixable violations\n├─ Returns structured JSON: {line, column, code, message, linter}\n└─ Still no output to main agent\n\nPhase 3: Delegate + Verify\n├─ Spawns claude -p subprocess with violations JSON\n├─ Routes to model tier based on violation complexity:\n│   ├─ Haiku: formatting, imports, style (E\u002FW\u002FF codes) — 120s timeout\n│   ├─ Sonnet: complexity, refactoring (C901, PLR codes, oxlint complexity) — 300s timeout\n│   └─ Opus: type system, deep reasoning (unresolved-attribute) — 600s timeout\n├─ Re-runs Phase 1+2 to verify fixes\n└─ Exit 0 if clean, Exit 2 if violations remain (reported to main agent)\n```\n\n### What the Main Agent Sees\n\n| Scenario | Agent sees | Hook exit |\n|----------|-----------|-----------|\n| No violations | Nothing | 0 |\n| All fixed by subprocess | Nothing | 0 |\n| Violations remain after subprocess | `[hook] N violation(s) remain` | 2 |\n| Advisory (duplicates, old tooling) | `[hook:advisory] ...` | 0 |\n\nThe main agent only sees issues the subprocess couldn't fix. Most quality problems are resolved transparently.\n\n### Config Protection (Defense Against Rule-Gaming)\n\nLLMs will modify `.ruff.toml` or `biome.json` to disable rules rather than fix code. Plankton blocks this with three layers:\n\n1. **PreToolUse hook** — `protect_linter_configs.sh` blocks edits to all linter configs before they happen\n2. **Stop hook** — `stop_config_guardian.sh` detects config changes via `git diff` at session end\n3. **Protected files list** — `.ruff.toml`, `biome.json`, `.shellcheckrc`, `.yamllint`, `.hadolint.yaml`, and more\n\n### Package Manager Enforcement\n\nA PreToolUse hook on Bash blocks legacy package managers:\n- `pip`, `pip3`, `poetry`, `pipenv` → Blocked (use `uv`)\n- `npm`, `yarn`, `pnpm` → Blocked (use `bun`)\n- Allowed exceptions: `npm audit`, `npm view`, `npm publish`\n\n## Setup\n\n### Quick Start\n\n> **Note:** Plankton requires manual installation from its repository. Review the code before installing.\n\n```bash\n# Install core dependencies\nbrew install jaq ruff uv\n\n# Install Python linters\nuv sync --all-extras\n\n# Start Claude Code — hooks activate automatically\nclaude\n```\n\nNo install command, no plugin config. The hooks in `.claude\u002Fsettings.json` are picked up automatically when you run Claude Code in the Plankton directory.\n\n### Per-Project Integration\n\nTo use Plankton hooks in your own project:\n\n1. Copy `.claude\u002Fhooks\u002F` directory to your project\n2. Copy `.claude\u002Fsettings.json` hook configuration\n3. Copy linter config files (`.ruff.toml`, `biome.json`, etc.)\n4. Install the linters for your languages\n\n### Language-Specific Dependencies\n\n| Language | Required | Optional |\n|----------|----------|----------|\n| Python | `ruff`, `uv` | `ty` (types), `vulture` (dead code), `bandit` (security) |\n| TypeScript\u002FJS | `biome`; `oxlint` (>= 1.37.0) when using `complexity` | `semgrep`, `knip` (dead exports) |\n| Shell | `shellcheck`, `shfmt` | — |\n| YAML | `yamllint` | — |\n| Markdown | `markdownlint-cli2` | — |\n| Dockerfile | `hadolint` (>= 2.12.0) | — |\n| TOML | `taplo` | — |\n| JSON | `jaq` | — |\n\n## Pairing with ECC\n\n### Complementary, Not Overlapping\n\n| Concern | ECC | Plankton |\n|---------|-----|----------|\n| Code quality enforcement | PostToolUse hooks (Prettier, tsc) | PostToolUse hooks (20+ linters + subprocess fixes) |\n| Security scanning | AgentShield, security-reviewer agent | Bandit (Python), Semgrep (TypeScript) |\n| Config protection | — | PreToolUse blocks + Stop hook detection |\n| Package manager | Detection + setup | Enforcement (blocks legacy PMs) |\n| CI integration | — | Pre-commit hooks for git |\n| Model routing | Manual (`\u002Fmodel opus`) | Automatic (violation complexity → tier) |\n\n### Recommended Combination\n\n1. Install ECC as your plugin (agents, skills, commands, rules)\n2. Add Plankton hooks for write-time quality enforcement\n3. Use AgentShield for security audits\n4. Use ECC's verification-loop as a final gate before PRs\n\n### Avoiding Hook Conflicts\n\nIf running both ECC and Plankton hooks:\n- ECC's Prettier hook and Plankton's biome formatter may conflict on JS\u002FTS files\n- Resolution: disable ECC's Prettier PostToolUse hook when using Plankton (Plankton's biome is more comprehensive)\n- Both can coexist on different file types (ECC handles what Plankton doesn't cover)\n\n## Configuration Reference\n\nPlankton's `.claude\u002Fhooks\u002Fconfig.json` controls all behavior:\n\n```json\n{\n  \"languages\": {\n    \"python\": true,\n    \"shell\": true,\n    \"yaml\": true,\n    \"json\": true,\n    \"toml\": true,\n    \"dockerfile\": true,\n    \"markdown\": true,\n    \"typescript\": {\n      \"enabled\": true,\n      \"js_runtime\": \"auto\",\n      \"biome_nursery\": \"warn\",\n      \"semgrep\": true\n    }\n  },\n  \"phases\": {\n    \"auto_format\": true,\n    \"subprocess_delegation\": true\n  },\n  \"subprocess\": {\n    \"tiers\": {\n      \"haiku\":  { \"timeout\": 120, \"max_turns\": 10 },\n      \"sonnet\": { \"timeout\": 300, \"max_turns\": 10 },\n      \"opus\":   { \"timeout\": 600, \"max_turns\": 15 }\n    },\n    \"volume_threshold\": 5\n  }\n}\n```\n\n**Key settings:**\n- Disable languages you don't use to speed up hooks\n- `volume_threshold` — violations > this count auto-escalate to a higher model tier\n- `subprocess_delegation: false` — skip Phase 3 entirely (just report violations)\n\n## Environment Overrides\n\n| Variable | Purpose |\n|----------|---------|\n| `HOOK_SKIP_SUBPROCESS=1` | Skip Phase 3, report violations directly |\n| `HOOK_SUBPROCESS_TIMEOUT=N` | Override tier timeout |\n| `HOOK_DEBUG_MODEL=1` | Log model selection decisions |\n| `HOOK_SKIP_PM=1` | Bypass package manager enforcement |\n\n## References\n\n- Plankton (credit: @alxfazio)\n- Plankton REFERENCE.md — Full architecture documentation (credit: @alxfazio)\n- Plankton SETUP.md — Detailed installation guide (credit: @alxfazio)\n\n## ECC v1.8 Additions\n\n### Copyable Hook Profile\n\nSet strict quality behavior:\n\n```bash\nexport ECC_HOOK_PROFILE=strict\nexport ECC_QUALITY_GATE_FIX=true\nexport ECC_QUALITY_GATE_STRICT=true\n```\n\n### Language Gate Table\n\n- TypeScript\u002FJavaScript: Biome preferred, Prettier fallback\n- Python: Ruff format\u002Fcheck\n- Go: gofmt\n\n### Config Tamper Guard\n\nDuring quality enforcement, flag changes to config files in same iteration:\n\n- `biome.json`, `.eslintrc*`, `prettier.config*`, `tsconfig.json`, `pyproject.toml`\n\nIf config is changed to suppress violations, require explicit review before merge.\n\n### CI Integration Pattern\n\nUse the same commands in CI as local hooks:\n\n1. run formatter checks\n2. run lint\u002Ftype checks\n3. fail fast on strict mode\n4. publish remediation summary\n\n### Health Metrics\n\nTrack:\n- edits flagged by gates\n- average remediation time\n- repeat violations by category\n- merge blocks due to gate failures\n\n---\n\n## Gabe's addition: oxlint complexity + ratchet ceiling (JS\u002FTS)\n\nCloses the JS\u002FTS gap in the model-routing table above. Python complexity (ruff C901,\nPLR) already routes to Sonnet. JS\u002FTS had no equivalent rule turned on by default.\n\n### Turn on oxlint's `complexity` rule when using it\n\noxlint's `complexity` rule (source: eslint's `complexity` rule, ported) lives in the\n\"restriction\" category, which oxlint does not enable by default. It must be turned on\nby hand. Verified against [Oxlint's complexity rule](https:\u002F\u002Foxc.rs\u002Fdocs\u002Fguide\u002Fusage\u002Flinter\u002Frules\u002Feslint\u002Fcomplexity)\n(2026-08-27): default option is `max: 20`. The rule is available in oxlint >= 1.37.0.\n\nThe skill's Language-Specific Dependencies table keeps `oxlint` optional for TypeScript\u002FJS\ngenerally. When adopting the `complexity` rule, use oxlint >= 1.37.0 and treat it as a\nrequired dependency. Add the rule to the supported oxlint configuration the project already\nuses (`.oxlintrc.json`, `.oxlintrc.jsonc`, `oxlint.config.ts`, or `oxlint.config.mts`). If\nnone exists, create one; do not create a second configuration file in the same directory.\n\nMeasure the codebase's current worst complexity score before choosing the initial enforced\nceiling. The template below is intentionally incomplete: replace `\u003CMEASURED_CEILING>` with\nthat score, optionally plus a small amount of headroom, before committing the `\"error\"` gate.\nOxlint's default of 20 is a long-term target, not a safe universal starting ceiling.\n\n```json\n{\n  \"rules\": {\n    \"complexity\": [\"error\", { \"max\": \"\u003CMEASURED_CEILING>\" }]\n  }\n}\n```\n\nReplace the placeholder before running oxlint; it is not a valid numeric threshold until the\nrepository has been measured. See the ratchet section below for how the ceiling gets set on\na real codebase.\n\n### Model-routing row\n\nAdd oxlint `complexity` violations to the same row as the existing Python entry in the\nPhase 3 subprocess table:\n\n```\n├─ Sonnet: complexity, refactoring (C901, PLR codes, oxlint complexity), 300s timeout\n```\n\nSame tier as Python's C901\u002FPLR. A complexity violation is a refactoring job either way,\nlanguage does not change the model tier.\n\n### The ratchet-ceiling technique\n\nSource: [Hunk PR #861](https:\u002F\u002Fgithub.com\u002Fmodem-dev\u002Fhunk\u002Fpull\u002F861) (merged 2026-08-26, verified against\nthe PR's own diff and description via the GitHub API, not paraphrased from memory). Hunk\nturned on oxlint's `complexity` rule with `\"error\", { \"max\": 80 }` in `.oxlintrc.json`.\nTheir own worst score at the time was 78 (`App`), next was 76\n(`validateFileViewLayout`). From the PR body: \"This is intentionally an initial\nregression ceiling rather than the long-term target... so 80 adds enforcement without\ngrandfathering or suppressions. The ceiling can be ratcheted downward as existing\nhotspots are simplified.\" And: \"A global ceiling does not prevent a function below 80\nfrom growing toward it.\"\n\nThe technique, as actually run in that PR:\n\n1. Measure the current worst complexity score in the codebase (oxlint reports it when\n   the rule fires).\n2. Set the ENFORCED ceiling to a value at least as high as that worst score, not to\n   oxlint's own default of 20. Add a small amount of headroom if needed so the initial\n   enable does not fail CI on a score you have not fixed yet (hunk used 80 against a\n   worst of 78).\n3. Commit that as `\"error\"`, wired into the existing lint CI step. This is a real gate\n   from the first commit, not a suggestion.\n4. Never grandfather. The ceiling is global. A function sitting at 40 today is not\n   exempt, it still cannot cross the ceiling later. That is the whole point: catch\n   growth, not just today's worst offenders.\n5. Never blanket-suppress. No per-file or per-function disable comments to make a\n   violation go away. Fix it or leave it under the ceiling.\n6. Each time a flagged hotspot is refactored below the ceiling, re-measure the global\n   maximum across the whole codebase. Lower the ceiling by hand only to a value that\n   remains at least as high as every remaining function's score (plus any deliberate\n   headroom). This is a manual step done as its own commit, not automated. It is how the\n   ceiling moves toward the linter's real default of 20 over time instead of sitting at\n   the codebase's worst score forever.\n\nOne caveat, stated plainly: the PR itself went straight from \"rule off\" to `\"error\"`\nenforcement in one commit. It did not stage through a report-only or warn-only phase\nfirst. Starting with the rule set to `\"warn\"` for one CI run before flipping it to\n`\"error\"` is a reasonable staging step if a team has never measured its own worst score\nand does not want a surprise CI failure, but that staging step is Gabe's own prudent\npractice, not something verified in hunk's PR. Say so if you use it, do not attribute it\nto the source.\n",{"name":5,"metadata":54,"description":7},{"origin":39},"main","74715deacdc69119d739f38916f8ee4f0f979ebf","skills\u002Fstorage\u002Faffaan-m_ECC\u002Fplankton-code-quality",0,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills","https:\u002F\u002Fgithub.com\u002Fmdnaimul22","AI Agents Workflows Automation | Specializing in Python, FastAPI, MCP Agents & Custom ERP.","2026-11-11 21:16:57",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add mdnaimul22\u002Fhuman-skills --skill plankton-code-quality",{"tool":69,"command":70},"bunx","bunx skills add mdnaimul22\u002Fhuman-skills --skill plankton-code-quality",{"tool":72,"command":73},"pnpm","pnpm dlx skills add mdnaimul22\u002Fhuman-skills --skill plankton-code-quality","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fplankton-code-quality\u002FSKILL.md",true,[],[78,86,94,101,108,115],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":85},"01M767791C1KRP2ZRW2Z73VZ5Q","system-lifecycle-designer","Universal architectural methodology for designing granular, atomic, and sub-atomic lifecycles and end-to-end workflows for single functionality integrations across any domain (daemons, batch jobs, request transactions, resource pools). Provides patterns for deterministic identity, pre-commit validation, differential reconciliation, sticky leasing, state machines, transactional persistence, and closed-loop feedback.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fmy_skills\u002Fsystem-lifecycle-designer\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":93},"01M748ABPN5F1FANHH6HKZQMXT","style-sampling","Make a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for \"an episode of\", \"in the style of\", \"sample this style\", 「用这个风格做一集」. One video to copy is reverse-any-video.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Fstyle-sampling\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":93},"01M748A59V04PKW4HA0XQ81FGP","reverse-any-video","Rebuild any video file as an editable HyperFrames project - motion graphics, talking heads, live action or AI-generated footage - checked against the original frame by frame. Use to reverse, recreate, remake, replicate or copy a video, or 「复刻这个视频」「照着这个视频做一个」.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Freverse-any-video\u002FSKILL.md",[],[],{"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":93},"01M7487T50P55CSXMWXZ0G9KRG","typescript-patterns","TypeScript patterns for strict, type-safe, maintainable code in modern TypeScript and JavaScript applications. Covers strict compiler configuration, type design, narrowing, discriminated unions, generics, async and error handling, module boundaries, dependency hygiene, and type-level testing. Use when writing or reviewing TypeScript or JavaScript code.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftypescript-patterns\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":93},"01M7487ERZRGPC5NJ75077Y238","test-collaboration","Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit\u002Fintegration\u002Fcontract\u002FE2E\u002Fsmoke classification, bug-to-test regression protection, consumer\u002Fprovider contract testing, test-necessity review, and pre-delivery evidence review.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftest-collaboration\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":93},"01M748721J3GKR2WS6K0QWFC35","story-lifecycle","Manage a file-based epic → story → sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira\u002FLinear\u002FTaiga but needs structured delivery tracking.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fstory-lifecycle\u002FSKILL.md",[],[]]