Iterative measurement-driven improvement loop. Measure, profile, mutate, re-measure, commit. Works for performance, bundle size, complexity, test coverage — anything quantifiable. Use when the user wants to systematically improve a metric through repeated cycles of profiling and targeted changes.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Iterative measurement-driven improvement loop. Each cycle: measure → profile → find biggest contributor → mutate → re-measure → commit only if improvement exceeds noise.
Use AskUserQuestion to collect:
forge-pr skill for title/body). PR description includes a measurements table updated as cycles complete.docs/<target>-ralph-report.md with baseline, methodology, optimization log table, and findings.TaskCreate list with N cycle tasks — emit all calls as parallel tool_use blocks in a single assistant turn so the seed is one model round-trip, not N.Each cycle:
.md is a deliverable — useful for blog posts and future reference.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Modern, interactive alternative to `/do` — clarify intent up front, then take a task end-to-end with a serial AI review gauntlet (lens debate (lowy ⇄ hickey) → codex debate → simplify → code-police, each editing the branch in turn) → CI → evidence. ONLY invoke when the user explicitly types `/be` or `$be`; never auto-select from a natural-language request.
The English summary is being prepared. Showing the original description.
Run /be's review gauntlet SERIALLY — /lens-debate (lowy ⇄ hickey), then /codex-debate, then /simplify, then code-police, each editing and committing on the live branch in turn. Use from /be §4, or when the user asks to "run the review gauntlet". Requires Claude Code's Skill tool.
The English summary is being prepared. Showing the original description.
Reference for the `odu` runner — how to invoke a full pipeline, a single recipe, or a platform-pinned node, and how to attach to a live run, from a project whose CI odu runs. Trigger when the user asks to "run CI", "run the pipeline", "re-run a check", to run named lanes or recipes (e.g. "run fmt and nix", "just the e2e lane", bare selectors like `fmt`/`nix`/`e2e`), or names a recipe by `<recipe>@<platform>`. This skill — not a repo's local `just ci` / `just <recipe>` — is how an odu-run request is served.
The English summary is being prepared. Showing the original description.
Review code for quality, simplicity, and common mistakes before declaring work complete.
The English summary is being prepared. Showing the original description.
Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex (reviewer) critiques the current diff and a Claude subagent (author) fixes/disputes, looping until they agree. `answer` — Claude and codex each answer a freeform prompt in parallel, then cross-check until they agree, and a unified answer is returned. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".
The English summary is being prepared. Showing the original description.
Do a task end-to-end — implement, PR, CI loop, ship. ONLY invoke when the user explicitly types `/do` or `$do`; never auto-select from a natural-language request, even one that sounds like an end-to-end task.
The English summary is being prepared. Showing the original description.