oprogramadorreal/optimus-claude / skills/gauntlet
gauntlet
VerifiedRuns 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.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 13.0 KB |
| SKILL.md | skill md | 11.1 KB |
| agents/openai.yaml | config | 198 B |
| references/goal-handoff-claude.md | markdown | 1.7 KB |
| references/goal-handoff-codex.md | markdown | 3.9 KB |
| references/goal-handoff.md | markdown | 4.2 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).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |