Run it inside Claude Code, then install plugins from it with /plugin.
Plugins
1claude-md-compliancePlugin for checking code compliance with CLAUDE.md guidelines and automatic fixes
2code-reviewPlugin for multi-agent PR code review workflow
3compact-handoffSessionStart(compact) hook that extracts the raw log segment dropped by compaction and has `claude -p` summarize only the gaps the standard compaction summary tends to miss (rejected alternatives, unexecuted commitments, constraints), injecting the result as additionalContext
4package-manager-enforcerPlugin that blocks mismatched package manager commands by detecting the correct package manager from package.json packageManager field or lock files
5permission-gatePermissionRequest hook (all tools) that asks `claude -p` (haiku) to judge each pending operation against natural-language allow rules the user writes in ~/.claude/permission-gate.md and <project>/.claude/permission-gate.md, auto-approving only clear matches and falling back to the normal confirmation dialog on anything undecidable, on errors, or on timeout
6plan-archiveStop hook that moves plan files older than 30 days (by mtime) into an archived/ subdirectory, resolving the plans directory from the transcript's planFilePath and prefixing each filename with its last-modified timestamp (YYYY-MM-DD_HHMM)
7plan-rubocop-reviewPreToolUse(ExitPlanMode) hook that validates Ruby code blocks in the plan with RuboCop (--stdin) before allowing exit
8plan-rule-reviewPreToolUse(ExitPlanMode) hook that reviews the plan for compliance with project rules (CLAUDE.md / .claude/rules/) before allowing exit
9plan-visualizeUserPromptSubmit hook that injects plan visualization rules (Mermaid diagrams and tables) as additionalContext when permission_mode is plan, encouraging plans to express flows, structures, and comparisons visually
10plan-workflowUserPromptSubmit hook that injects Plan-drafting operating rules (requirement interview, model routing for drafting sub-agents, noting the plan-implementation skill) as additionalContext when permission_mode is plan, a PreToolUse(ExitPlanMode) command hook that checks whether an implementation plan references the plan-implementation skill and denies to prompt adding it if missing. Implementation-phase rules (delegating to Agents, model routing, running /simplify after implementation, no unsolicited commits) now live in the plan-implementation skill.
11rules-on-createPlugin that makes path-based rules in .claude/rules/ and CLAUDE.md apply on file creation (Write), not only on Read
12usage-guardUserPromptSubmit and PostToolBatch hooks that track the account's 5-hour and 7-day subscription usage windows and halt the agentic loop before the next model call once a configured threshold is crossed, so unattended automation can't silently burn usage credits; usage is read from the OAuth usage endpoint and cached, with dry-run/enforce modes and a time-boxed bypass