mightymattys
UserClaude orchestrates and reviews; GPT-5.6, Sonnet 5, or Opus 5 implements. Your head chef doesn't chop onions. A two-model kitchen for Claude Code.
Categories
Indexed Skills (7)
fire
Delegates well-specified implementation tasks to Codex CLI in the background, choosing a GPT-5.6 tier by task shape (--tier overrides; --with sonnet or opus routes to a Claude worker instead). Use for substantial spec-able work - features, refactors, migrations, or boilerplate; not small fixes or ambiguous design; never fire silently.
mise
Mise en place - setup and health check. Verifies Codex CLI and auth, installs the delegation profile, scaffolds AGENTS.md, and offers the routing policy. Re-run anytime, and after plugin updates to refresh the profile. Use when the user asks to set up expo, or when another expo skill fails because Codex or the profile is missing.
refire
Turns confirmed findings from a taste into one scoped fix run, then re-verifies each finding at its cited location. Use after /expo:taste when the user says to fix the findings, apply the review, or refire it. Not for new feature work - that is a fresh /expo:fire.
serve
Runs the whole line autonomously - implement via Codex, cross-review, fix confirmed findings, verify, report once at the end. Use when the user wants a task done end to end ("serve this", "just get it done"), or as the default for spec-able implementation when the routing policy is autonomous. Announces once; stops only for hard blockers.
simmer
Runs a goal loop - Codex implements fresh laps while Claude verifies each against a machine-checkable goal, until it passes or the budget runs out. Use only when the user explicitly asks for a loop ("simmer this", "loop until tests pass", "iterate until green") - it creates a branch and checkpoint commits, so confirm the contract first.
taste
Cross-model code review - Codex reviews the diff read-only, then Claude validates every finding against the code before presenting it. Use when the user asks for a review, a second opinion, or a cross-model check. Offer it for large or risky diffs; invoke it directly only when the routing policy is autonomous.
receipts
Prints the check - reads .expo/receipts/ and renders the last 10 run receipts as a table with a savings-floor total, and can reprint any receipt's shareable summary. Use when the user asks for receipts, costs, or savings, or invokes /expo:receipts. Receipts are written automatically at the end of every serve and simmer.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.