goal-contract
Skill0 starsChanged 2 months agoMITView on GitHub
Convert multi-turn work into a runtime-neutral goal brief whose completion is decided by evidence. Use for “write a goal”, “goal brief”, “골”, performance work, flaky-test investigations, migrations, or any task requiring repeated verified passes—not simple one-turn requests.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- frontier-infra/proctortheir own version, first seen Oct 11, 2026
- aniketpanjwani/skillstheir own version, first seen Aug 17, 2026
- audriusstat/execution-disciplinetheir own version, first seen Jul 28, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- aniketpanjwani/skills★ 52same name
- audriusstat/execution-discipline★ 0same name
- frontier-infra/proctor★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- absorbSkill
- agent-starterSkill
- aim-before-buildSkill
- converge-planSkill
- decision-sheetSkill
- evidence-auditSkill
- harness-auditSkill
- morning-briefSkill
- phase-loopSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Create one brief that Codex, Claude Code, or another agent can execute without changing the finish line.
- Distinctive: line 23
Write a compact one-line goal plus a Markdown brief containing the six fields and an execution log.
- Very specific: line 27
Use phase-loop when the goal becomes three or more ordered implementation phases.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Goal Contract
Create one brief that Codex, Claude Code, or another agent can execute without changing the finish line.
Required contract
- Outcome — measurable state that must become true.
- Verification — runnable commands or inspectable artifacts that prove it.
- Constraints — behavior or quality that must not regress.
- Boundaries — allowed and forbidden files, systems, data, and actions.
- Iteration policy — how failed passes choose the next smallest change.
- Blocked stop — when the agent must stop and report instead of guessing.
Human taste or approval belongs between goals, not inside an automated completion check.
Output
Write a compact one-line goal plus a Markdown brief containing the six fields and an execution log. Use shell-runnable verification when possible; do not make an internal agent tool the only proof of success.
Next
Use phase-loop when the goal becomes three or more ordered implementation phases. If verification cannot be written, return to converge-plan.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.