plan-execution
Skill2 starsChanged 27 days agoMITView on GitHub
How workers execute a handoff plan or spec from the orchestrator - drift check, verify gates, scope, STOP conditions, approvals and the report. Preloaded by implementer, parallel-implementer, fixer and doc-writer.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- SWEStash/swe-workflow-skillstheir own version, first seen Nov 8, 2026
- wannanbigpig/ai-engineering-collaborationtheir own version, first seen Nov 6, 2026
- rozputnii/ai-usage-apptheir own version, first seen Oct 13, 2026
- SpiralSky/opencode-planning-skilltheir own version, first seen Sep 20, 2026
- duniecdawid/ultra-claudetheir own version, first seen Jul 16, 2026
- synaptiai/bdsktheir own version, first seen Apr 8, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- wannanbigpig/ai-engineering-collaboration★ 2same name
- SWEStash/swe-workflow-skills★ 1same name
- duniecdawid/ultra-claude★ 0same name
- rozputnii/ai-usage-app★ 0same name
- SpiralSky/opencode-planning-skill★ 0same name
- synaptiai/bdsk★ 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 repository28 other files it gives its agents.
- claude/CLAUDE.mdCLAUDE.md
- agent-browserSkill
- animation-vocabularySkill
- apple-designSkill
- benchmark-checklistSkill
- codebase-designSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- emil-design-engSkill
- find-animation-opportunitiesSkill
- grillingSkill
- improve-animationsSkill
- improveSkill
- parallel-buildSkill
- pick-ui-librarySkill
- plan-handoffSkill
- portlessSkill
- principle-attack-the-premiseSkill
- principle-fix-root-causesSkill
- prototypeSkill
- receiving-code-reviewSkill
- review-animationsSkill
- shadcnSkill
- supabase-postgres-best-practicesSkill
- testingSkill
- unslopSkill
- vercel-react-best-practicesSkill
- verification-before-completionSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 11 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
When your task is a plan from plans/ (or any spec the orchestrator sends):
- Distinctive: line 11
Run its drift check first.
- Distinctive: line 12
If an in-scope file no longer matches Current state, stop and report.
- Distinctive: line 13
Run every step's Verify and confirm the expected result before the next step.
- Very specific: line 16
Stop before any step marked REQUIRES HUMAN APPROVAL and report it instead of running it.
- Distinctive: line 17
Do everything the plan asks, across every site its pattern matches, and nothing it does not.
- Distinctive: line 22
Read the files you will touch and one similar existing example first.
- Distinctive: line 23
Before reporting done, run a real check that exercises the change: the project's type-checker, build or linter, or the changed command …
- Distinctive: line 25
If only the project's declared dependencies are missing, install them with its own package manager and lockfile, never with sudo or a …
- Distinctive: line 26
If no real check can run, say which one you did not run and why instead of reporting done.
- Distinctive: line 27
Never report done with a red build, except for failures your change did not cause.
- Distinctive: line 32
When working from review findings, address each exactly as specified.
- Distinctive: line 33
If you disagree with one, implement it anyway when harmless, otherwise report the disagreement with your reasoning.
“Common” is measured: kept by at least 6 in 10 of the 5 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
Executing a plan
When your task is a plan from plans/ (or any spec the orchestrator sends):
- Run its drift check first. If an in-scope file no longer matches Current state, stop and report.
- Run every step's Verify and confirm the expected result before the next step.
- Scope and STOP conditions are binding. On a STOP condition, stop and report; do not improvise around it.
- Stop before any step marked
REQUIRES HUMAN APPROVALand report it instead of running it. - Do everything the plan asks, across every site its pattern matches, and nothing it does not. Say which sites you covered. Suggest extra features, files, docs or refactors in your report instead of doing them.
- On genuine ambiguity, or a plan that seems wrong, stop and ask in your report rather than picking a reading.
- The orchestrator maintains
plans/README.md: never edit it, and ignore an untrackedplans/oradvisor-plans/ingit status. - Read the files you will touch and one similar existing example first; match its naming, error handling, imports and layout, but not its comment density.
- Before reporting done, run a real check that exercises the change: the project's type-checker, build or linter, or the changed command itself, plus the tests your agent instructions call for. Run no other tests. A syntax-only check, or a command that failed to start, does not count. If only the project's declared dependencies are missing, install them with its own package manager and lockfile, never with sudo or a system package manager. If no real check can run, say which one you did not run and why instead of reporting done.
- Never report done with a red build, except for failures your change did not cause. Fix an unrelated lint, type or build error only when it is in a file you already change and the fix is small, and list it under deviations. Report every other one with the exact output.
- Report against the plan's Done criteria.
When working from review findings, address each exactly as specified. If you disagree with one, implement it anyway when harmless, otherwise report the disagreement with your reasoning; never skip one silently.
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.

