claudekit
Toolkit of custom commands, hooks, and expert subagents providing guardrails and workflow automation for Claude Code.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for claudekit, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
claudekit is an npm toolkit for Claude Code providing smart guardrails and workflow automation: real-time error catching, checkpoint save/restore, and expert subagents. It ships slash commands (/code-review with 6-agent parallel review, /spec:create, /research, /checkpoint:create) and hooks that block sensitive-file access and run TypeScript/lint checks on change. Its hook system enforces quality automatically and can be session-disabled.
Key features and capabilities
- File-security and change hooks (TS/lint checks)
- Checkpoint create/restore commands
- 6-agent parallel /code-review
- Domain expert subagents (react, testing, etc.)
Use cases
- Automated guardrails while AI edits code
- Checkpointing and reviewing changes