Lean toolkit for disciplined engineering workflows with AI Agents (Claude Code, Codex, Oh-my-pi, Cursor, Grok CLI, Antigravity, ZCode).
Agent Claude Code
Codebase explorer for understanding project structure, finding relevant files, tracing dependencies, and answering specific questions about code. Dispatched by cf-plan before planning, by cf-fix before diagnosing bugs, and by cf-ask, cf-advise, cf-optimize, cf-research, cf-scan, and cf-showcase for gathering code…
Agent Claude Code
Implementation agent — direct coding by default, TDD opt-in. Use this agent when you need to implement code changes. Dispatched by cf-tdd for substantial implementations (3+ files, complex algorithms, multi-step features), by cf-plan and cf-plan-resume for executing plan tasks, by cf-fix for bug fixes, by cf-optimize…
Agent Claude Code
Task decomposition and approach brainstorming agent. Use this agent when you need to break down a complex task into actionable steps, compare implementation approaches, or design a plan before coding. Dispatched by cf-plan for approach analysis. Trigger this agent when the task requires evaluating multiple strategies…
Agent Claude Code
Plan alignment review specialist. Checks whether code changes match the implementation plan. Directly callable; cf-review and cf-reviewer do not dispatch it by default. Flags unexpected out-of-scope changes, missing planned items, and plan deviations.
Agent Claude Code
Code quality review specialist. Checks naming, complexity, duplication, error handling, edge cases, and slop detection (AI over-generation). Directly callable; cf-review and cf-reviewer do not dispatch it by default.
Agent Claude Code
Review reducer agent. Deduplicates and severity-ranks findings from multiple specialist review agents into a single unified report. Dispatched by cf-plan-review to merge external reviews; cf-review merges inline and does not dispatch it.
Agent Claude Code
Project rules compliance specialist. Checks code changes against AGENTS.md project rules. Only flags violations of rules with MUST/SHOULD/ALWAYS/NEVER language. Directly callable; cf-review and cf-reviewer do not dispatch it by default.
Agent Claude Code
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. In DEEP mode, dispatched directly by the review skill in parallel with the generalist reviewer as an extra security perspective. Includes…
Agent Claude Code
Test coverage review specialist. Checks whether new code paths are tested, test quality, edge case coverage, and regression prevention. Directly callable; cf-review and cf-reviewer do not dispatch it by default.
Agent Claude Code
Code reviewer. Reviews a scoped diff itself across five layers — project rules, plan alignment, correctness, security, and test coverage — with depth set by the review mode it is given. Dispatched by cf-review for thorough review before merge. Trigger this agent when the user asks to review code changes — e.g. "review…
Agent Claude Code
Deep reasoning document writer for nuanced technical content, complex multi-concept synthesis, or very long context. Dispatched by cf-teach (always), by cf-plan for the human overview doc, and by cf-learn, cf-remember, and cf-scan for complex content. Trigger this agent instead of cf-writer when the content involves…
Agent Claude Code
Lightweight document writer for skills that generate markdown files. Dispatched by cf-learn, cf-remember, cf-scan, cf-fix, cf-ask, cf-advise, cf-sys-debug, and cf-warm for writing docs, memory files, and notes. Trigger this agent when a skill needs to write or update markdown documents — e.g. "write the doc", "save to…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: