agent-audit
Audit agents spawned in the current/last run against the agent-selection taxonomy
Bootstrap industry-leading lint+autofix+commit-hygiene stack on the current project. Drops in lefthook, oxlint, ESLint, Prettier, Stylelint, markdownlint, ruff, shellcheck, shfmt, yamllint, hadolint, actionlint, jscpd, knip, semgrep, gitleaks, commitizen + git-cz-emoji
> /plugin marketplace add heymegabyte/claude-skillsHow it fires
How this command gets triggered: by you, by Claude, or both.
/install-lint-stackContext preview
What this command does when you run it.
Bootstrap industry-leading lint+autofix+commit-hygiene stack on the current project. Drops in lefthook, oxlint, ESLint, Prettier, Stylelint, markdownlint, ruff, shellcheck, shfmt, yamllint, hadolint, actionlint, jscpd, knip, semgrep, gitleaks, commitizen + git-cz-emoji
name: install-lint-stack description: Bootstrap industry-leading lint+autofix+commit-hygiene stack on the current project. Drops in lefthook, oxlint, ESLint, Prettier, Stylelint, markdownlint, ruff, shellcheck, shfmt, yamllint, hadolint, actionlint, jscpd, knip, semgrep, gitleaks, commitizen + git-cz-emoji (emoji-mandatory commits), and semantic-release. Idempotent — re-runs upgrade safely. See rules/lint-doctrine.md. argument-hint: "[project-dir]" user-invocable: true
Wires the canonical emdash lint stack into the target project. Source of truth: `~/.agentskills/templates/lint-stack/`. Doctrine: `~/.agentskills/rules/lint-doctrine.md`.
1. **Detects** Node/Python/Docker/Actions/Shell presence. 2. **Backs up** any existing configs to `.lint-stack-backup-<ts>/`. 3. **Copies** the appropriate template configs into the project root. 4. **Installs** npm/bun dev deps for the detected stack. 5. **Updates** `package.json` scripts: `lint`, `lint:fix`, `format`, `commit`, `release`, `lint:semgrep`, `lint:knip`, `lint:jscpd`. 6. **Installs** lefthook git hooks (`lefthook install`). 7. **Writes** ruff config for Python projects when absent.
Every time a linter catches a recurring class of bug across projects:
1. Add a semgrep rule under `~/.agentskills/templates/lint-stack/semgrep-custom/<topic>.yml`. 2. Append the pattern to `rules/lint-doctrine.md` §"Codified incidents". 3. Cross-link from the relevant existing rule (`code-style.md`, `ai-agent-security.md`, etc.). 4. Verify via `semgrep --test`. 5. Distribute by committing to the agentskills repo — auto-pushed per Brian's git policy.
This satisfies `prompt-as-training-signal` §6 — every novel bug class deterministically codified, never re-learned.
bash ~/.agentskills/bin/install-lint-stack.sh # current dir bash ~/.agentskills/bin/install-lint-stack.sh /path/to/X # named dir
After install:
npm run lint # autofix pass over all files git cz # compose emoji-prefixed commit npm run release # semantic-release publish
14-category autonomous product-building OS for 32+ AI coding tools. One-line prompts → deployed products.
Repo: heymegabyte/claude-skills
Audit agents spawned in the current/last run against the agent-selection taxonomy
Run the Agent Diversity Review gate and emit the result table
Meta-analyze the effectiveness of a /loop arc — per-iteration metrics, LOC delta trend, saturation detection, and a keep/lengthen/delete recommendation.
Audit the rules/ directory for missing foundational principles; output gap list with priority and justification
Validate ~/.claude/settings.json hooks block — event names, file existence, executability, matcher syntax; --fix repairs common issues
Catch Resend-class bug (isError: false on HTTP 4xx/5xx) across all MCP server tool handlers