safety-hooks
claudeDeterministic guardrails as PreToolUse hooks: blocks dangerous commands (force push, rm -rf, DROP TABLE), secret leaks, edits to protected files, and writes to build artifacts.
hooks
Plugin marketplace
Lean, token-efficient agents, skills, and safety hooks for daily Claude Code development. Install the whole kit with setupdotclaude, or pick individual plugins. No telemetry; runs entirely locally.
Add this marketplace
Then install any plugin below by name — each page has its exact command.
Deterministic guardrails as PreToolUse hooks: blocks dangerous commands (force push, rm -rf, DROP TABLE), secret leaks, edits to protected files, and writes to build artifacts.
hooks
Rebuild context fast after /clear: reads the handoff note and branch changes, summarizes where work stands. Add handoff to write the note before stopping.
Keep CLAUDE.md current and lean: capture session learnings into it (default) or audit it for stale commands, drift, and bloat.
Reviews code for real bugs: off-by-ones, null derefs, race conditions, swallowed errors. Skips style nitpicks.
Estimate per-turn token cost of your .claude/ configuration and CLAUDE.md. Always-loaded vs path-scoped vs invoked-only, with top contributors. Use --api for exact counts.
Find and fix a bug. Default is the careful path (reproduce, investigate, test). Add `--fast` for emergency hotfix mode.
Cross-references docs against actual source. Flags drift, missing params, dead references.
Explain code with one-sentence summary, mental model, ASCII diagram, and modification guide.
Take a GitHub issue from number to tested fix: read the thread, reproduce, fix with a regression test, prep a PR that closes it.
Builds production-grade UI. Tokens-first, anti-AI-slop aesthetics, design tokens enforced.
Get oriented in an unfamiliar codebase fast: an Explore-subagent tour from overview down to architecture, data models, auth, conventions, and a glossary, without flooding your main context.
Finds real bottlenecks. DB N+1, memory leaks, blocking calls, re-renders.
Review PR or staged changes via six specialist agents in parallel. Confidence-bucketed, severity-ranked synthesis.
Judges whether a diff's tests actually verify the change: assertion-free tests, mock theater, tests that cannot fail, weakened tests.
Safely refactor with tests as a safety net. Writes tests first if none exist. Use --diff to simplify just the working diff before committing.
OWASP-style review: injection, auth, data exposure, weak crypto. Severity-ranked with file:line + fix.
Set up dotclaude in any project. Deep-scans the codebase, interviews you, then installs and customizes only the components the project actually needs.
Commit, push, create PR with confirmation at every step, then optional cleanup of branches whose remotes are gone. Blocks secrets and force-push.
Finds code that fails silently: swallowed errors, failures masked as success, fallbacks that hide breakage. Runs on every PR review.
Turn a fuzzy feature idea into a self-contained SPEC.md by interviewing you first, then writing a spec a fresh implementation session can execute.
Strict red-green-refactor TDD loop. Failing test, then minimum code, then refactor. Commits after each cycle.
Write comprehensive tests covering happy/edge/error/concurrency paths. Verifies tests actually catch bugs.
Shows how many plugins this repo ships, and links here.