Skip to content

oprogramadorreal/optimus-claude / skills/gauntlet

gauntlet

Verified

Runs a Gauntlet Loop: turns an ambitious goal into a builder/critic prompt judged against a concrete quality bar, confirms with the user, then leads the run until the output beats the bar or the user stops it — or exports a paste-ready /goal prompt for a fresh session. Use for long-horizon goals with an inspectable reference. Long-running; spawns many subagents, edits project files, and commits and pushes finished pieces to a feature branch.

FileKindSize
README.mdmarkdown13.0 KB
SKILL.mdskill md11.1 KB
agents/openai.yamlconfig198 B
references/goal-handoff-claude.mdmarkdown1.7 KB
references/goal-handoff-codex.mdmarkdown3.9 KB
references/goal-handoff.mdmarkdown4.2 KB

references/goal-handoff-claude.md

View on GitHub
# Claude Code goal handoff

Shared export, completion, and size rules live in the calling
`goal-handoff.md` reference.

## Runtime instructions

Keep these in the handoff page and add a compact sentence to the message:
the small per-turn goal evaluator reads only conversation evidence and uses
no tools. Its reason is a continuation nudge, never a critic gap or a new
rule. Fresh-context critics remain the only quality judges.

## Checklist above the message

- Claude Code 2.1.139 or later (`claude --version`), workspace trusted and
  hooks permitted; `/goal` is unavailable when hook policy disables it.
- A NEW conversation in the run's directory, with the handoff page and all
  bar materials present. Select `/effort` → ultracode for serious runs and
  choose the permission mode deliberately: a goal grants no extra access.
- Paste as one block, then inspect bare `/goal`; the registered condition
  must include the final "met ONLY when" paragraph. If truncated, clear it
  with `/goal clear` and paste the complete message again.
- Stop with `/goal clear`; interrupting a turn alone does not clear the goal.
  Bare `/goal` shows status/spend; an active goal survives session resume,
  while `/clear` removes it.
- The evaluator can clear a goal as impossible, and errors or nonprogress
  can clear or pause it. Inspect the stated reason and fix a real blocker
  before restarting; if the evaluator mistook a hard bar for an impossible
  one, re-paste the same condition. Clearing is not proof of success.
- After the run, in the run's session: `/optimus:commit` for any leftovers,
  then `/optimus:pr`; then `/optimus:code-review` in a fresh conversation.

Behavior source: [Claude Code goals](https://code.claude.com/docs/en/goal).
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall