claude-coordinator-kit: Instructions file for Claude Code

CLAUDE.md

claude-coordinator-kit CLAUDE.md is an instructions file for Claude Code, Codex from nikolamin/claude-coordinator-kit. It costs 10,756 tokens per session, scanned A, original, MIT.

Project instructions for a coordinator that plans and directs work but does not carry it out. They define how to resume work, route tasks between models, and follow a documented process.

In plain words
What is it for?
Coordinating multi-step coding work, assigning tasks to other agents or models, and maintaining process and state documents.
Why use it?
They give the agent a fixed coordination process and keep project state manageable across sessions. This reduces confusion about who should execute each task and what to read when resuming.

Instructions file for Claude CodeCodex

Written for Codex and Claude Code: runs codex exec, but also the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

This is nikolamin/claude-coordinator-kit's own configuration. It tells Claude Code and Codex how to work on claude-coordinator-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-coordinator-kit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nikolamin/claude-coordinator-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nikolamin/claude-coordinator-kit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nikolamin/claude-coordinator-kit

Made for: Claude Code, Codex.

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 claude-coordinator-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nikolamin/claude-coordinator-kit/claude-md.svg)](https://agentmods.dev/instructions/nikolamin/claude-coordinator-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nikolamin/claude-coordinator-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/nikolamin/claude-coordinator-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 10,756 This file is loaded in full into every session.
When invoked 10,756 The same file — it is already loaded in full.
Security scan A 1 finding. 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 5.1 $0.10756 $0.10756
Opus 5 $0.05378 $0.05378
Sonnet 5 $0.02151 $0.02151
Haiku 4.5 $0.01076 $0.01076

Measured 2d ago against content hash 7c1dca4444a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-coordinator-kit CLAUDE.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- No investigative or diagnostic Bash — not even a "quick check" (CI status, `curl`-ing an
CLAUDE.md · 607 lines

How it starts

The opening of the file, as written. The whole thing — 607 lines — stays where its author put it; the contents beside it link to each section on GitHub.

— Coordinator Instructions

This session is the coordinator. Full phase loop: docs/coordination/PROCESS.md. Current state: docs/coordination/STATE.md (read first when resuming — keep it small enough that reading it first is actually practical; roll older entries into docs/coordination/state-archive/YYYY-MM.md rather than letting it grow unbounded). These instructions override default behavior — follow them exactly.

The installed kit version is recorded in docs/coordination/kit-version.md. A kit update runs by re-pasting the install prompt: its own step 2 detects the existing install and switches to an update branch instead of copying files wholesale — see FILE-COPY-INSTALL.md's ## Updating section for the procedure. That update branch consults UPDATING.md as its per-file reference (REPLACE/NEVER TOUCH/MERGE classification and the reasoning behind each) — UPDATING.md is not itself the procedure. CLAUDE.md is both the file an update rewrites and this running session's own operating instructions: Claude Code loads project instructions once at session start, so editing this file on disk mid-session does not change the current session's behavior — it keeps following the text already loaded into its context. An update therefore ends in a session restart, not a live switchover; don't treat a just-applied update as in effect before that restart happens. Because an update rewrites the coordinator's own rules, the CLAUDE.md portion gets founder review before it's applied — never silently self-merged.

Role: coordinator only, never executor

The coordinator never does substantive work itself. This is broader than "don't write code":

  • No coding, no research, no design/creative/artifact work.
  • No investigative or diagnostic Bash — not even a "quick check" (CI status, curl-ing an endpoint, git log archaeology, dependency probing, installing a CLI tool).
  • No verification of build output — that's a separate agent's job, even when it looks trivial.
  • On an existing codebase (PROCESS.md Phase 0.5), the repo map comes from dispatched read-only analysis agents — the coordinator never explores the repo itself to build it.

Read the full file on GitHub · 607 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. 2d ago Changed · +34 lines · +772 tokens per session 7c1dca4444a7
  2. 6d ago First seen · 573 lines · 9,984 tokens per session scan A b7218c90d9e8

Subscribe to this mod's changes

claude-coordinator-kit CLAUDE.md is an instructions file published in the GitHub repository nikolamin/claude-coordinator-kit (2 stars, last pushed 3d ago), licensed MIT. It adds 10,756 tokens to every session, about $0.0538 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens