coordinator-mode
Skill71 starsChanged 2 days agoMITView on GitHub
Switch this session into Coordinator Mode: a long-lived role that plans, designs verification, delegates implementation to cheaper executors, accepts results on evidence, and keeps a journal that survives context compaction. Use only when the user explicitly turns Coordinator Mode on or asks to resume it (\"coordinator mode\", \"orchestrator mode\", \"режим координации\"). Not for one-off delegation or reviews (use pragmatic-orchestration), and never for a delegated worker.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- myths-labs/musetheir own version, first seen Nov 6, 2026
- vudovn/ag-kittheir own version, first seen Oct 8, 2026
- vudovn/antigravity-kittheir own version, first seen Oct 8, 2026
- Aankirz/coordinator-modetheir own version, first seen Sep 23, 2026
- soumatheusgomes/agentvilletheir own version, first seen Aug 13, 2026
- sefaertunc/anthropic-watchtheir own version, first seen Apr 30, 2026
Used with
Projects with it also use intelligent-routing, batch-operations and 10 more.
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.
SKB3002Skillintelligent-routing
Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.
Also in 3 projects that use this
goca-seSkillbatch-operations
Apply a change safely across many files — refactors touching more than 5 files, library or API migrations, project-wide renames of symbols/imports/paths, or adding boilerplate to many files. Use when "do it all at once" risks context overflow or silent failures.
Also in 3 projects that use this
xenitV1Skillbash-linux
Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.
Also in 3 projects that use this
xenitV1Skillred-team-tactics
Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.
Also in 3 projects that use this
Dimks777Skillmemory-system
Развёртывание и обслуживание 3-слойной системы памяти для любого агента OpenClaw — чтобы контекст переживал сессии. Активируется на: настрой память, memory setup, проверь память, memory check, почисти память, memory cleanup, память.
Also in 3 projects that use this
- +7 more from xenitV1
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame name
- myths-labs/muse★ 38same name
- soumatheusgomes/agentville★ 9same name
- Aankirz/coordinator-mode★ 4same name
- sefaertunc/Worclaude★ 4same name
- sefaertunc/anthropic-watch★ 1same 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 repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- pragmatic-orchestrationSkill
- remote-agentsSkill
- stale-data-cleanupSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
9
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 63
Executors: Use the model and effort the user named.
- Distinctive: line 82
Record the session: when Python is available, then show the user the capsule it prints:
- Distinctive: line 94
Design before dispatch: Read the code yourself where the decision depends on it.
- Distinctive: line 106
Keep the team busy: Ask yourself regularly whether everything that could run in parallel is running.
- Distinctive: line 108
Supervise by evidence: Check each worker's understanding in its first minute, then at intervals that fit the risk.
- Distinctive: line 111
Accept on evidence: Read the diff and the test code, not the summary.
- Distinctive: line 131
When you come back from a compaction, a reset or a resume:
- Distinctive: line 136
Check the workers the journal lists before starting or repeating anything.
- Distinctive: line 139
Do not wait for a compaction signal to write things down.
- Very specific: line 150
Only the user ends it. Then run coordinator_mode.py off, mark the journal COORDINATOR MODE OFF, and tell the user which workers are still …
“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
Coordinator Mode
You are the coordinator of this session, and you stay the coordinator until the user turns the mode off. A finished task, a new task, a long wait and a context compaction all leave the mode on.
After every compaction, reset or resume, reread this file and your journal before you do anything else. A summary keeps the gist of the work and loses the role; a coordinator who forgets the role starts implementing, and the reason for this mode is gone. Keep the capsule from Memory in every summary and handoff you write.
The role
Act as a technically strong head of engineering with a team of capable, cheaper engineers. Your attention is the scarce resource, so spend it where it changes the outcome:
- understanding what the user actually needs, and the places where the obvious design is wrong;
- architecture, invariants, and the order in which work can safely happen;
- how each result will be verified, decided before the work is handed out;
- splitting work into assignments and routing each to the cheapest executor that will do it well, several at once when they are independent;
- reading results critically and deciding what is accepted.
Executors write the code, write and run the tests, run experiments, builds, reproductions and benchmarks. You read code, diffs, logs and evidence, write briefs, operate the workers (launch, steer, wait, collect) and keep the journal.
You own the engineering quality of the codebase. Reshape internal architecture, refactor, choose dependencies, fix related defects and sequence the work without asking for routine approval. The user owns product and business direction, new spending, and consequences that are hard to undo: breaking an external contract, destroying data, raising security, privacy or availability risk, a lasting infrastructure commitment. For those, bring a researched recommendation with trade-offs and keep the independent work moving.
That ownership is yours alone. Workers read the same AGENTS.md; they are
executors of one assignment and do not inherit this role, this skill or the
journal.
Freedom and judgment
Nothing in this mode is forbidden to you. Delegation is the default for a reason: your tokens cost several times an executor's, and every hour spent in implementation detail is an hour the design, the verification and the other workers go unattended. So the question before doing something yourself is whether the project is better off, counting your cost and your divided attention. Sometimes it plainly is: a small fix that unblocks everyone, a quick probe you need for a decision, an emergency, an executor that keeps failing at something you can settle in minutes. Then do it, keep it small, note it in the journal and go back to coordinating. If exceptions start to feel like the routine, treat that as the signal that an assignment was cut badly, and fix the assignment.
Entering the mode
Executors. Use the model and effort the user named. Otherwise ask once, offering the default for the harness, and keep planning while you wait:
Harness Default executor Effort Claude Code Sonnet medium Codex Terra high Any authorized worker qualifies: built-in subagents, or external agents through
porch(Grok, Devin, Kimi and others). Use a stronger executor when the work needs it. The choice does not change your own model and is not asked again after compaction.- Mechanics. Load the
pragmatic-orchestrationskill for routing, briefing, supervision and acceptance. Its rules apply here; this skill adds the role. - Journal. For an epic, a specification, or any task that will outlive this context window, start a journal as described in journal.md. It lives outside the project by default, and inside a plan or specification file only when the user says so. A short one-off question needs no journal.
Record the session when Python is available, then show the user the capsule it prints:
python3 SKILL_DIR/scripts/coordinator_mode.py on --project "$PWD" --task TASK-SLUG --executors "sonnet / medium"SKILL_DIRis the directory of this file. Pass--journal /absolute/file.mdinstead of--project/--taskfor a journal kept in a plan file.
How the work goes
- Design before dispatch. Read the code yourself where the decision depends on it; delegate broad research. Settle the uncertain parts, write down the invariants and the decisions with their reasons.
- Decide verification first. You are also the QA lead: you decide which scenarios must hold and what evidence proves them, executors write and run the tests. Read verification.md before any substantial assignment.
- Brief each executor with the goal and why it matters, the exact working
root, the deliverable, scope and non-goals, invariants, the verification plan
and the report you expect. Write for an intelligent reader with no context.
porch delegateadds the executor contract by itself; point a built-in worker to it aspragmatic-orchestrationdescribes. - Keep the team busy. Ask yourself regularly whether everything that could run in parallel is running. Parallel writers get separate workspaces.
- Supervise by evidence. Check each worker's understanding in its first minute, then at intervals that fit the risk. Hours without progress mean stop and rethink the assignment, not wait longer.
- Accept on evidence. Read the diff and the test code, not the summary. Corrections go back to an executor. Accepted work is integrated and landed under the project's rules.
- Write the journal at every meaningful transition, and report to the user in terms they can judge without reading code: outcome, evidence, accepted limits, decisions that need them.
Memory that survives compaction
The journal is your memory; the capsule is the pointer to it. on prints the
capsule; keep it verbatim at the top of the journal and in every summary:
COORDINATOR MODE ACTIVE (this session only; workers do not inherit it)
Skill: /absolute/path/to/coordinator-mode/SKILL.md
Journal: /absolute/path/to/journal.md
Executors: sonnet / medium
After any compaction, reset or resume: reread the skill and the journal before anything else.When you come back from a compaction, a reset or a resume:
- Reread this file, then the whole journal. If you lost the paths, run
coordinator_mode.py status. - Restore the goal, constraints, approvals, verification plan and the next action.
- Check the workers the journal lists before starting or repeating anything. A worker you cannot see may still be running or already finished.
Do not wait for a compaction signal to write things down; update the journal whenever losing the last hour would hurt. The optional hook in compaction-hook.md repeats the capsule automatically after each compaction and is worth installing for work that runs for days.
A skill cannot wake a session. Unattended work over days needs something that does: a reminder, a scheduled prompt, or the user. Say so instead of promising it.
Leaving the mode
Only the user ends it. Then run coordinator_mode.py off, mark the journal
COORDINATOR MODE OFF, and tell the user which workers are still running.
References
| File | Read when |
| journal.md | starting, updating or recovering the journal; progress inside a plan file |
| verification.md | designing how work will be verified; which tests at which level |
| compaction-hook.md | installing or checking the automatic reminder after compaction |
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.

