Autoreview
Run OpenClaw structured code review as the default closeout check for local changes, branches, commits, and PR work. Uses Codex by default; Claude is optional for explicit second-model review.
Mcporter
CLI access to MCP servers without loading them into agent context (saves tokens). Use when: (1) calling MCP tools on-demand, (2) want to avoid MCP context overhead.
New Task
Iteratively clarify requirements for a new task until reaching 90%+ confidence, then auto-invoke plan-loop.
Ios Dev
Develop iOS apps with a fast simulator-first loop using the xcodebuildmcp CLI: discover project/schemes, build/test/run, capture logs, and triage failures. Use when: (1) normal iOS development, (2) simulator/device build issues, (3) runtime crashes or UI issues, (4) iterative fix/verify loops.
Review Loop
Post-implementation review/fix loop. Use host-appropriate review coverage on your implementation, fix issues, iterate until highly confident, then commit.
Codex Review
Run Codex's built-in `codex review` command as a fallback or explicit compatibility check for local changes, branches, commits, and PR work.
Oracle
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Computer Use Mcp
Open, agent-agnostic MCP server exposing macOS computer use to any MCP client (Claude Code, Cursor, Codex, …). Background-safe, works on every app.
Orchestrator
Coordinate complex work with Codex App worker threads. Keep the main thread as orchestrator: clarify, delegate, wait for worker completion, review outputs, iterate, verify, and ship without doing substantial implementation directly.
Ios Release
Run a preflight-gated iOS release workflow with asc for TestFlight and App Store: auth check, ID resolution, validation, blocker triage, then controlled publish/submit commands. Use when: (1) shipping to TestFlight, (2) preparing App Store submission, (3) diagnosing release blockers, (4) creating repeatable release playbooks.
Skills Audit
Audit agent skills in a repo against best practices — checks .claude/skills/ and .agents/skills/ for quality, structure, and coverage gaps. Use when the user wants to review, improve, or evaluate their skills, or when they mention skill quality, skill audit, or skill best practices.
Simplify
Review changed code for reuse, quality, and efficiency, then fix any issues found.
Self Test
Prove the requested goal works on the highest-signal affected surface before closing. Default closing behavior for every implementation task — not just when explicitly asked. Also triggers on: 'make sure it works', 'test it yourself', 'don't just tell me it's done', 'I don't want to test this'.
Use Loop
Default workflow for implementation and product goals: identify the verifiable goal, check tool/self-test access, start a real continuation loop, iterate until verified, report blockers or decisions, then close with simplify/self-test/autoreview. Use when the user asks for /use-loop, loop mode, autonomous iteration, repeated attempts, retry-until-green workflows, or any non-trivial coding/product…
Audit Loop
Lightweight read-only audit. Use host-appropriate review coverage for evidence and findings. Iterate on disagreement or low confidence. No code changes.
Plan Loop
Use for complex or high-risk implementation work that needs plan-first execution, explicit verification design, pre-code review, and autonomous post-implementation hardening through self-test, simplify, and review-loop.
Fix Ci
Check GitHub Actions status on the current PR, wait for checks to finish, analyze failures and review comments, fix issues, and repeat until CI passes. Use when a user asks to fix failing CI, check PR status, or get a PR merge-ready.