guidance
01Agent
The agents stack injects host API keys into the container and persists CLI auth state in named volumes.
3 2mo ago A 0 tokens
original MIT
summary
02Agent
One-command devcontainer sandbox CLI for AI agent development (Claude Code / Codex / Gemini CLI).
3 2mo ago A 0 tokens
original MIT
tools
03Agent
One-command devcontainer sandbox CLI for AI agent development (Claude Code / Codex / Gemini CLI).
3 2mo ago A 0 tokens
original MIT
planner
04Agent
Repository-grounded planner. Dispatched when the orchestrator detects a task touching 3+ files, unknown code, schema/API/auth/secrets/infra changes, or when the user explicitly asks for a plan. Does not edit files.
3 2mo ago A 49 tokens
original MIT
reviewer
05Agent
Diff reviewer. Dispatched after the implementer finishes a slice and BEFORE the verifier runs. Reads the diff for taste, regressions, missing tests, and plan adherence. Cites paths and lines.
3 2mo ago A 43 tokens
original MIT
verifier
06Agent
Mechanical verifier. Invokes .claude/hooks/verify.sh and parses its structured output. Compares against the plan's Acceptance Criteria. Does NOT review for taste.
3 2mo ago A 37 tokens
original MIT
impact-map
07Skill Claude CodeCodex
Use before implementation when the requested change touches code you have not edited in this session.
3 2mo ago A 0 tokens
original MIT
Skill Claude CodeCodex
Use after implementation, before final response.
3 2mo ago A 0 tokens
original MIT