agentleFS
sefaertuncsefaertunc/Worclaude/.claude/skills/coordinator-mode/SKILL.md

coordinator-mode

Skill4 starsChanged 7 months agoMITView on GitHub

Multi-agent orchestration patterns: when to use coordinator mode, worker prompts, parallel execution

6 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use batch-operations, intelligent-routing 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.
  • goca-seSkill

    batch-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

  • SKB3002Skill

    intelligent-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

  • xenitV1Skill

    bash-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

  • xenitV1Skill

    red-team-tactics

    Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

    Also in 3 projects that use this

  • Dimks777Skill

    memory-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

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use coordinator patterns when:

    line 11
  2. Distinctive:

    Don't use coordinator patterns when:

    line 18
  3. Distinctive:

    Read the findings. Identify the approach.

    line 37
  4. Distinctive:

    Never write "based on your findings" or "based on the research." These phrases delegate understanding to the worker instead of doing it …

    line 40
  5. Distinctive:

    Commit and report the hash."

    line 50
  6. Distinctive:

    Read-only tasks (research) — run in parallel freely

    line 78
  7. Distinctive:

    Write-heavy tasks (implementation) — one at a time per set of files

    line 79
  8. Distinctive:

    When running multiple Claude Code terminals (Boris Mode):

    line 92
  9. Distinctive:

    Use /sync on develop after merging to reconcile shared-state files

    line 95
  10. Distinctive:

    Use /conflict-resolver if merges produce conflicts

    line 96

“Common” is measured: kept by at least 6 in 10 of the 6 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Coordinator Mode

When to Use Multi-Agent Coordination

Use coordinator patterns when:

  • A task has independent research + implementation phases
  • Multiple file areas can be worked on in parallel
  • Verification should run alongside implementation
  • You need to synthesize findings before directing follow-up work

Don't use coordinator patterns when:

  • The task is small enough for one session
  • Steps are strictly sequential with no parallelism
  • The overhead of coordination exceeds the work itself

Phase-Based Workflow

Most coordinated tasks follow four phases:

PhaseWhoPurpose
ResearchWorkers (parallel)Investigate codebase, find files, understand problem
SynthesisYou (coordinator)Read findings, understand the problem, craft implementation specs
ImplementationWorkersMake targeted changes per spec, commit
VerificationWorkersTest changes work, try to break them

The synthesis phase is the coordinator's most important job. When workers report research findings, you must understand them before directing follow-up work. Read the findings. Identify the approach. Then write a prompt that proves you understood by including specific file paths, line numbers, and exactly what to change.

Never write "based on your findings" or "based on the research." These phrases delegate understanding to the worker instead of doing it yourself.

Worker Prompt Best Practices

Workers cannot see your conversation. Every prompt must be self-contained:

Good — synthesized spec: "Fix the null pointer in src/auth/validate.ts:42. The user field is undefined when sessions expire but the token is still cached. Add a null check before user.id access. Commit and report the hash."

Bad — lazy delegation: "Based on your findings, fix the auth bug." "The worker found an issue. Please fix it."

Purpose Statement

Include a brief purpose so workers calibrate depth:

  • "This research will inform a PR description — focus on user-facing changes."
  • "I need this to plan an implementation — report file paths, line numbers, and type signatures."
  • "This is a quick check before we merge — just verify the happy path."

Continue vs Spawn Decision

SituationActionWhy
Research explored exactly the files that need editingContinue existing workerWorker has files in context
Research was broad, implementation is narrowSpawn fresh workerAvoid context noise
Correcting a failureContinue existing workerWorker has error context
Verifying code a different worker wroteSpawn fresh workerFresh eyes, no implementation bias
Wrong approach entirelySpawn fresh workerClean slate avoids anchoring

Parallel Execution

Parallelism is the primary advantage. Launch independent workers concurrently:

  • Read-only tasks (research) — run in parallel freely
  • Write-heavy tasks (implementation) — one at a time per set of files
  • Verification can sometimes run alongside implementation on different file areas

Scratchpad Pattern

For durable cross-worker knowledge, use a shared scratchpad file:

  • Workers write findings to a known location
  • Other workers read from it when they need context
  • Structure files by topic, not by worker

Multi-Terminal Workflow

When running multiple Claude Code terminals (Boris Mode):

  • Each terminal works on a separate feature branch or file area
  • Use /sync on develop after merging to reconcile shared-state files
  • Use /conflict-resolver if merges produce conflicts
  • Shared-state files (PROGRESS.md, SPEC.md, package.json version) are ONLY modified on develop

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.