coordinator
Skill2 starsChanged 41 days agoMITView on GitHub
Coordinate a bounded mathematical-modeling case through runtime RESULT.json handoffs and human decisions.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- Ubuntu-Buddha/claude-code-stranger-dangertheir own version, first seen Nov 8, 2026
- christofferbergj/agent-skillstheir own version, first seen Nov 1, 2026
- magicpro97/vibeflowtheir own version, first seen Oct 25, 2026
- 3176467770-jpg/orca-coordinator-skilltheir own version, first seen Oct 20, 2026
- langwatch/langwatchtheir own version, first seen Oct 17, 2026
- steig/worktendertheir own version, first seen Oct 17, 2026
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- langwatch/langwatch★ 5ksame name
- raine/workmux★ 3ksame name
- Fullive-AI/Anima★ 1ksame name
- magicpro97/vibeflow★ 9same name
- Ubuntu-Buddha/claude-code-stranger-danger★ 8same name
- alphazede/bearing-lite★ 3same name
- christofferbergj/agent-skills★ 1same name
- steig/worktender★ 1same name
- summelon/skills★ 1same name
- 3176467770-jpg/orca-coordinator-skill★ 0same name
5 more not listed
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 repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- evidenceSkill
- executionSkill
- explorationSkill
- publicationSkill
- reviewSkill
The file
Files
Coordinator
Work only from selected task inputs and bounded continuation material. Do not assume an unlisted file, another author's first-round draft, or a human approval exists.
At the end of a turn, write RESULT.json in the task workspace. Use the runtime's ordinary shape:
{"requests": [], "wait_for": [], "deliverables": []}Each request must be a valid runtime task spec. Inputs, instructions, and skills are case-relative selected paths so the runtime can copy them. Use wait_for for known child task IDs. The workflow/control layer also accepts human_requests (scope, fixed displayed object, prompt, choices, limits) and wait_for_human question IDs; these ask for a human answer but do not authorize anything.
For a formal scientific request, include research_class: "formal", a human-approved research_scope, and non-empty bounds. Never submit a formal route, result, fusion, or paper-package selection without its exact human decision ID and exact displayed selected object. Treat failed, cancelled, paused, and unknown child outcomes as visible evidence, never success.
End a coordination turn after dispatching or asking a question. The runtime releases the model slot. On continuation, use only returned bounded child summaries and current human decisions; do not recreate submitted work.
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.

