Evidence-first loop harness for Codex and Claude Code
Done means proven.
Superloopy turns one prompt into a bounded loop. It writes the criteria first, proves each one with a real command, and won't call the work done until the receipts exist.
npx superloopy@latest
Needs Node.js 22+. Finds Claude Code, Codex, Antigravity and omp, asks before each one, and updates hosts that already have it.
codex plugin marketplace add https://github.com/beefiker/superloopy
codex plugin add superloopy@beefiker
Run in a terminal, restart Codex, approve the hooks.
/plugin marketplace add beefiker/superloopy
/plugin install superloopy@beefiker
Run inside Claude Code.
Then type loopy in front of any task.
01 · How it works
One prompt, one bounded loop. Every step leaves a file you can open later.
- 01
Criteria
loop beginturns the brief into a goal with concrete pass criteria before any code changes. - 02
Proof
loop prove -- <cmd>runs the check and stores its full output as evidence, pass or fail. - 03
Gate
loop check · loop finishconfirms every criterion has a valid artifact. Finish re-runs the proof before it completes. - 04
Receipt
A report, a gate file and every capture stay under .superloopy/evidence, next to the code.
$ superloopy loop begin --brief "Fix cart total" --mode light
superloopy began: G001 Fix cart total
$ superloopy loop prove -- npm test
superloopy prove: G001/C001 -> fail (.superloopy/evidence/G001-C001-capture.txt)
# fix: drop the stray “+ 1”
$ superloopy loop prove -- npm test
superloopy prove: G001/C001 -> pass (.superloopy/evidence/G001-C001-capture.txt)
$ superloopy loop prove -- node --test total.test.js
superloopy prove: G001/C002 -> pass (.superloopy/evidence/G001-C002-capture.txt)
$ superloopy loop check
superloopy check: ok
Evidence summary: 2 artifact-backed criteria, 0 unresolved, 0 invalid
$ superloopy loop finish
superloopy finish: complete
02 · The crew
Six roles, one job each. Type loopy team to delegate in parallel. A worker without a receipt doesn't count.
03 · Skills
Lanes for the work you do. The proof rule is the same in every lane.
- 01superloopy-loopThe evidence loop: criteria, proof, gate.
loopy <task> - 02superloopy-backendContracts first, sibling conventions, guarded migrations.
loopy <backend task> - 03superloopy-frontendScreen-based UI, with visual QA as evidence.
$superloopy:superloopy-frontend - 04superloopy-cloneRebuild a page from a URL with specs and screenshot diffs.
loopy clone <url> - 05superloopy-slidesHTML decks and PPTX, checked visually.
loopy slides <topic> - 06superloopy-researchResearch that cites what it actually read.
loopy <research question> - 07superloopy-doctorDiagnose install, hooks and host wiring.
superloopy doctor - 08humanize-koreanKorean prose that sounds human, facts untouched.
$superloopy:humanize-korean - 09say-it-straightDirect, concise prose without losing meaning.
$superloopy:say-it-straight - 10i-have-adhdAction-first output, only when you ask for it.
$superloopy:i-have-adhd
Invoke any skill with $superloopy:<skill> (Codex) · /superloopy:<skill> (Claude Code)
04 · FAQ
Questions, answered with receipts.
How is this different from a careful prompt?
A prompt asks for care. Superloopy checks for it: criteria are written before the work starts, each one needs a command-backed artifact, and finish re-runs the proof before it completes.
Where does the evidence live?
In your project, under .superloopy/evidence: command captures, the gate file and a markdown report. Keep the folder in .gitignore, or attach the report to a pull request.
What happens when the loop can't finish?
It says so. The report names the blocker and keeps the evidence found so far. With the Stop hook on, a stalled loop is marked blocked instead of done.
Does it work with Claude Code?
Yes. Codex and Claude Code both get the loop, the crew and the skills. npx superloopy@latest installs it into every host it finds, and npx superloopy@latest update keeps them all current.