agent-orchestrator
Skill2 starsChanged 40 days agoMITView on GitHub
Triage then orchestrate workers with briefs and verify-before-done. Use when coordinating, delegating, or reviewing agent output.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- nainishshafi/developer-productivity-skillstheir own version, first seen Nov 8, 2026
- qiangjiyi/jiyi-skillstheir own version, first seen Nov 8, 2026
- wulaosiji/skillstheir own version, first seen Nov 1, 2026
- mholtzscher/skillstheir own version, first seen Oct 16, 2026
- mengxiangsama/codex-agent-orchestration-skilltheir own version, first seen Oct 11, 2026
- Cor-Incorporated/claude-code-skillstheir own version, first seen Sep 3, 2026
Used with
Projects with it also use brainstorming.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
OpenAISkillbrainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Also in 3 projects that use this
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- wulaosiji/skills★ 28same name
- Cor-Incorporated/claude-code-skills★ 5same name
- qiangjiyi/jiyi-skills★ 3same name
- Xwen0857/agent-orchestrator★ 2same name
- lschGSL/claude_code_template★ 1same name
- mengxiangsama/codex-agent-orchestration-skill★ 1same name
- mikeshoes/skills★ 1same name
- nainishshafi/developer-productivity-skills★ 1same name
- 2867203296/hermes-agent★ 0same name
- aw-pr/autometta-public★ 0same name
2 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 repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adversarial-auditSkill
- agentic-reactorSkill
- ai-optimizationSkill
- architecture-synthesisSkill
- audit-allow-buildsSkill
- audit-ide-dependenciesSkill
- author-workflow-skillSkill
- bdd-strategizerSkill
- chrome-extension-mv3Skill
- concurrent-cli-agentsSkill
- control-feederSkill
- control-graphSkill
- cursor-transcript-harvestSkill
- cv-promote-guardSkill
- devcontainer-hardenedSkill
- dual-copy-skill-publishSkill
- explore-repo-readonlySkill
- finder-reactorSkill
- fix-dependency-securitySkill
- fusion-sageSkill
- git-worktreesSkill
- grok-host-prepSkill
- gt-flowSkill
- higher-order-decision-architectSkill
- looperSkill
- master-plannerSkill
- mvu-refactor-planSkill
- odysseus-navigatorSkill
- project-editor-profileSkill
- react-client-expertSkill
- semantic-markup-cssSkill
- semantic-nameSkill
- session-unit-orderSkill
- shell-kernel-ontologySkill
- skill-rename-propagationSkill
- split-to-prsSkill
- src-tree-reorganizeSkill
- stellar-roadmapSkill
- stellar-spacemapSkill
- subagent-delegationSkill
- subagent-explore-reportSkill
- supply-chain-hardenSkill
- tauri-agenticSkill
- tauri-ipc-debugSkill
- tidy-commit-pushSkill
- upgrade-packagesSkill
- verification-cockpitSkill
- x-agent-resourcesSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
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 128
Not for one-file typo fixes (single_shot is the skip path).
- Very specific: line 130
Does not replace domain skills.
“Common” is measured: kept by at least 6 in 10 of the 7 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
agent-orchestrator
Load rule: Formal SoT below. Expand references/english-procedure.md only if a phase or handoff is still ambiguous. CLT: on-the-fly pre-filter ../rules/clt-dual-load.mdc (A8 DualLoad) — expand ../control-graph/references/clt-load-balance.md only if human/agent load tradeoff is ambiguous.
Purpose
Coordinate non-trivial work so workers implement and the orchestrator re-runs verify. Skip for one-file typo fixes.
Prerequisites
- Target repo
AGENTS.mdfor verify cmds. - Git worktrees for concurrent workers (git-worktrees).
- Brief template: references/task-brief.md.
Instructions
Orch ≔ coordinator // you
W ≔ workers // one brief, one workspace, one DoD each
Triage ∈ { single_shot, light, full }
Wave ∈ { spike, foundation, feature, hygiene }
A1 Workers never self-verify as final truth — Orch re-runs verify cmds
A2 Brief before delegate; commit in workspace before "done"
A3 Merge ≻ cp // integration via git only ([git-worktrees](../git-worktrees/SKILL.md))
A4 Spike hard/unknown BEFORE mega-feature brief
A5 Resume = gap-only brief — never re-delegate full original scope
A6 Compose control shape with [control-graph](../control-graph/SKILL.md); this skill = multi-worker logisticsPair: git-worktrees · concurrent-cli-agents · split-to-prs · domain skills per worker.
Triage (~10s)
| Mode | When | Do |
| single_shot | 1 clear change · ≤1–2 files · low risk · obvious verify · no concurrent W | edit + verify; skip brief/worktree |
| light | plan/review only · 3–5 files same concern · tiny resume gap · fast disprove | 3–5 bullets then implement in one checkout |
| full | multi W/worktrees · unknown hard part · large/vague · high stakes · prior agent "done" · resume after days | checklist + briefs + verify + integrate |
request → triage → single_shot | light | full
escalate: single_shot grows past ~2 files / new unknowns → stop → light|fullFull path
ORIENT → DECOMPOSE → SPIKE? → BRIEF → DELEGATE → VERIFY ⇄ fix-brief → INTEGRATE → REPORT| Phase | Exit when |
| ORIENT | 1-sentence goal · base ref · constraints · unknowns · risk |
| DECOMPOSE | waves with disjoint ownership where possible |
| SPIKE | risky unknown proved or rejected (≤1–2 files / readonly + rec) |
| BRIEF | references/task-brief.md complete |
| DELEGATE | one prompt/W; workspace recorded |
| VERIFY | Orch ran every verify cmd; scope matches brief |
| INTEGRATE | merge one branch at a time; re-verify; no cp |
| REPORT | summary to user |
| Role | Owns |
| Orch | spec, sequence, verify, merge order, user updates |
| Worker | implement in one worktree; commit on agent/<tool>/<slug> |
| User | scope splits, merge/PR, destructive git |
Orch may implement only if trivial or verify failed twice and inline fix is faster — say so.
Brief minimum
- Problem · 2. Outcome (observable) · 3. Non-goals · 4. Standards (skills)
- Files may/must-not · 6. Verify cmds (exact) · 7. Workspace · 8. Done artifact (commit)
Worker handback: SHA · cmds+exit · 2-sentence approach · limits.
Verify (Orch-owned)
| Check | Action |
| Scope | git diff base...agent ⊆ allowed |
| Claims | summary matches diff |
| Automated | re-run every brief command |
| Regression | imports/types/exports |
| Standards | spot-check cited skills |
Fail → fix brief (gap only), same workspace if possible. Never merge on testimony alone.
Resume
read last brief → git log/diff/worktree list → remaining gap (1¶) → "Resume: …" brief onlyDefaults (override from target AGENTS.md): frozen lockfile when deps change; type-check + lint; React → react-client-expert; deps → fix-dependency-security; minimal diff.
Stack handoff: leave a pushed linear branch + per-PR SHAs. Confirm the final branch name with the user. Detail: references/english-procedure.md.
Examples
User: "Split this refactor across two agents. Do not merge on their word."
Agent: triage full. Write two disjoint briefs with exact verify cmds. Each worker gets one worktree. Orch re-runs every verify cmd, then merges via git (never cp). Report SHAs + leftover gaps.
User: "Fix the typo in README."
Agent: triage single_shot. Edit + verify. No worktree, no brief.
Limitations
- Not for one-file typo fixes (single_shot is the skip path).
- Orch must not both implement and "verify" the same large feature.
- Does not replace domain skills; workers load those.
- Graphite/
gtsession of the agent may not be the user's authenticated shell.
Troubleshooting
| Error / symptom | Cause | Fix |
| Worker says done, tests fail | Testimony without Orch re-run | Re-run brief verify cmds; gap-only fix brief |
| Diff outside allowed files | Vague brief | Tighten files may/must-not; same workspace |
| Merge conflict storm | Overlapping waves | Decompose disjoint; merge one branch at a time |
| Resume redoes the whole task | Full original brief reused | Gap-only resume brief |
cp from worktree | Integration shortcut | merge / cherry-pick only |
Report template
## Orchestrator summary
**Goal:** …
**Workers:** tool/branch → pass/fail
### Verified — commands + exit
### Integrated — merges
### Leftovers / next waveDone when: triage mode chosen; if full — verify cmds passed on integration; user has report + leftovers.
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.

