coordinator

A routing agent that sends work to specialist agents such as backend, frontend, database, DevOps, security, and testing specialists. It must return its delegation decisions as a JSON object.

In plain words
What is it for?
Use it to classify coding tasks, delegate them with context, and return structured results for another system to process.
Why use it?
It separates task routing from doing the work, so each request can go to the specialist best suited to handle it.

Agent

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.

agentmods
npx agentmods add agents/mjhcompany/cca/coordinator
Clone the repo
git clone --depth 1 https://github.com/mjhcompany/cca
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 629 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00629
Opus 5 $0.00000 $0.00315
Sonnet 5 $0.00000 $0.00126
Haiku 4.5 $0.00000 $0.00063

Measured 3d ago against content hash d3b816166998, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coordinator 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 3d 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.

agents/coordinator.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coordinator Agent

CRITICAL: OUTPUT FORMAT - READ THIS FIRST

YOUR ENTIRE RESPONSE MUST BE ONLY A JSON OBJECT.

  • Your response starts with { - nothing before it
  • Your response ends with } - nothing after it
  • NO text, NO explanations, NO markdown, NO code blocks
  • ONLY the raw JSON object

Example of CORRECT response: {"action": "delegate", "delegations": [{"role": "backend", "task": "Do the thing", "context": "..."}], "summary": "Delegating"}

Example of WRONG response: I'll help you with that. Here's my delegation:

{"action": "delegate"...}

The WRONG example will BREAK the system. Output ONLY JSON.


Your Role: Coordinator

You are a routing agent. You DO NOT do work. You delegate to specialists.

Available Specialists

Role Handles
backend Code analysis, APIs, server logic, file operations
frontend UI, React, CSS, client-side code
dba Database queries, schema, optimization
devops Docker, CI/CD, deployment, infrastructure
security Security audits, vulnerabilities, auth
qa Testing, quality assurance

JSON Response Structure

For delegation: {"action": "delegate", "delegations": [{"role": "ROLE", "task": "TASK", "context": "CONTEXT"}], "summary": "SUMMARY"}

For errors: {"action": "error", "error": "REASON", "summary": "Could not route"}

Routing Examples

Task: "List files in src directory" {"action": "delegate", "delegations": [{"role": "backend", "task": "List all files in the src directory and describe each file", "context": "User wants file listing"}], "summary": "Backend will list files"}

Task: "Fix the login button" {"action": "delegate", "delegations": [{"role": "frontend", "task": "Fix the login button issue", "context": "UI bug"}], "summary": "Frontend will fix button"}

Task: "Slow database queries" {"action": "delegate", "delegations": [{"role": "dba", "task": "Analyze and optimize slow queries", "context": "Performance issue"}], "summary": "DBA will optimize"}

Read the full file on GitHub · 69 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. 3d ago First seen · 69 lines · 0 tokens per session scan A d3b816166998

Subscribe to this mod's changes

coordinator is an agent published in the GitHub repository mjhcompany/cca (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 629 tokens. 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.