coordinator-mode

coordinator-mode is a skill for Claude Code from irfad7/claude-power-skills. It costs 94 tokens per session (1,521 once invoked), scanned A, original, MIT.

A way to manage complex work by splitting it into smaller tasks for multiple coding agents. It coordinates those agents, combines their results, and handles disagreements.

In plain words
What is it for?
Use it to parallelize audits, designs, refactors, and other large tasks with separate subtasks.
Why use it?
It removes the need to manually track many independent work streams. It is intended for tasks that can be divided into at least three bounded pieces.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-power-skills plugin — 20 skills shipped together

Good fit Use it to parallelize audits, designs, refactors, and other large tasks with separate subtasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/irfad7/claude-power-skills/coordinator-mode
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add irfad7/claude-power-skills --skill coordinator-mode
Clone the repo
git clone --depth 1 https://github.com/irfad7/claude-power-skills

Made for: Claude Code.

Or install claude-power-skills, the plugin that ships this one along with the rest of its 20 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for coordinator-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/irfad7/claude-power-skills/coordinator-mode/github.svg)](https://agentmods.dev/skills/irfad7/claude-power-skills/coordinator-mode)
Your own site
<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/coordinator-mode"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/coordinator-mode/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for coordinator-mode

Your own site · 80×15
<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/coordinator-mode"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/coordinator-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,521 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01521
Opus 5 $0.00047 $0.00760
Sonnet 5 $0.00019 $0.00304
Haiku 4.5 $0.00009 $0.00152

Measured 12d ago against content hash 66f4bebcddb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

coordinator-mode scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/coordinator-mode/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coordinator Mode — Multi-Agent Orchestration

You are a coordinator agent. Your job is not to do the work yourself — it's to decompose complex tasks into units, dispatch worker agents, manage their execution, merge their results, and resolve conflicts.

When To Use

  • Task has 3+ independent subtasks
  • Work can be parallelized for speed
  • Different parts of the task need different specializations
  • The task is too large to hold in a single context window
  • The user explicitly asks to parallelize

The Coordination Protocol

Step 1: Task Decomposition

Break the task into work units. Each unit must be:

  • Independent: Can be completed without waiting for other units
  • Self-contained: Has all the context it needs in its prompt
  • Verifiable: Has clear success criteria
  • Bounded: Fits in a single agent session
Task: "Refactor the API to use proper error handling"

Decomposition:
├── Unit 1: Audit all route files, list current error patterns
├── Unit 2: Design the error handling standard (types, formats, middleware)
├── Unit 3: Refactor auth routes to new pattern
├── Unit 4: Refactor user routes to new pattern
├── Unit 5: Refactor billing routes to new pattern
├── Unit 6: Update tests for new error responses
└── Unit 7: Update API documentation

Dependencies:
- Units 1,2 must complete before 3,4,5
- Units 3,4,5 are fully parallel
- Unit 6 depends on 3,4,5
- Unit 7 depends on 6

Step 2: Wave Planning

Group units into waves based on dependencies:

Wave 1 (parallel): [Unit 1, Unit 2]
Wave 2 (parallel): [Unit 3, Unit 4, Unit 5]  — depends on Wave 1
Wave 3 (sequential): [Unit 6]                 — depends on Wave 2
Wave 4 (sequential): [Unit 7]                 — depends on Wave 3

Step 3: Agent Dispatch

For each unit, create a clear agent prompt:

Agent Prompt Template:
─────────────────────
TASK: [specific task description]

CONTEXT:
[relevant codebase context — file paths, patterns, conventions]
[results from previous waves if applicable]

CONSTRAINTS:
[coding standards, patterns to follow, things to avoid]

DELIVERABLE:
[exactly what this agent should produce]

SUCCESS CRITERIA:
[how to verify the work is correct]
─────────────────────

Read the full file on GitHub · 175 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 175 lines · 94 tokens per session scan A 66f4bebcddb6

Subscribe to this mod's changes

coordinator-mode is a skill published in the GitHub repository irfad7/claude-power-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,521 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

import

Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.

skullninja/coco-workflow · 26 tokens

hotfix

Single-issue workflow for quick fixes and small changes that don't need full epic tracking. Creates a branch, implements the fix, commits with issue tracking, and closes.

skullninja/coco-workflow · 36 tokens

execute

Execute the next available tracked task with TDD, pre-commit validation, PR workflow, AI code review, and issue tracker bridge sync. Primary execution interface for multi-session feature work.

skullninja/coco-workflow · 39 tokens

council-review

Perform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review", "carmack review", or invoke /council-review. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js)…

SamJHudson01/Carmack-Council · 166 tokens

council-plan

Architect a feature with the Carmack Council before writing code. Use when explicitly asked to plan a feature, do a "council plan", "carmack plan", or invoke /council-plan. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo…

SamJHudson01/Carmack-Council · 165 tokens

test-architect

Map testable surfaces, audit existing tests for quality, and write test specifications that prevent AI shortcuts. Use when asked to "audit tests", "specify tests", "test architect", "map test coverage", or invoke /test-architect. Two modes — audit (evaluate existing tests against Beck's principles) and specify (write…

SamJHudson01/Carmack-Council · 110 tokens