agentmods.dev

coordinate-agents AGENTS.md

Repository instructions for AI contributors working on the coordinate-agents project. They describe the project identity, file layout, required checks, and rules for making changes safely.

In plain words
What is it for?
Use them when contributing to coordinate-agents, locating its command and skill code, following its testing and change rules, or checking which files are authoritative.
Why use it?
They give coding agents the project context they need before editing files. This reduces incorrect changes, identity mix-ups, and accidental exposure of secrets or private data.

Instructions file for CodexOpenCode

101 3d ago C scan 1,451 tokens original MIT
View the source file hogancv/coordinate-agents
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 instructions/hogancv/coordinate-agents/agents-md
Clone the repo
git clone --depth 1 https://github.com/hogancv/coordinate-agents

Made for: Codex, OpenCode.

Per session 1,451 This file is loaded in full into every session.
When invoked 1,451 The same file — it is already loaded in full.
Security scan C 2 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 $0.01451 $0.01451
Opus 5 $0.00726 $0.00726
Sonnet 5 $0.00290 $0.00290
Haiku 4.5 $0.00145 $0.00145

Measured 3d ago against content hash 944116450255, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

coordinate-agents AGENTS.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

10. Do not use third-party mirrors, mutable unknown scripts, `curl | sh`, or long-lived npm tokens

Makes network callslowCapability

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

10. Do not use third-party mirrors, mutable unknown scripts, `curl | sh`, or long-lived npm tokens
AGENTS.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository instructions for AI contributors

This file governs development and maintenance after an agent has entered this repository. It is not the installation entry point. For installation, read AI_INSTALL.md.

Canonical identity

  • Repository: https://github.com/hogancv/coordinate-agents
  • npm package: @hogancv/coordinate-agents
  • Package source of truth: package.json

Do not rename, mirror, or substitute these identities. Never add credentials, tokens, cookies, recovery codes, private keys, personal email addresses, or raw .agent-bus data to commits, fixtures, logs, documentation, or release artifacts.

Repository map

  • bin/coordinate-agents.mjs: thin executable and compatibility export surface. Argument parsing lives in lib/cli/; top-level command execution lives in lib/commands/; shared legacy-compatible domain operations remain in lib/cli-core.mjs while they are incrementally extracted.
  • .codex-plugin/plugin.json: Codex Plugin manifest.
  • skills/coordinate-agents/: canonical self-contained Skill and runtime source (SKILL.md, agents/, adapters/, references/, scripts/). The Session implementation is scripts/pty-runtime.mjs, scripts/session-host.mjs, scripts/session-manager.mjs, and scripts/session-service.mjs; references/session-runtime.md is the detailed protocol reference.
  • scripts/: repository development and release tooling (demo.mjs, sync-llms.mjs).
  • AI_INSTALL.md: canonical safe installation procedure for AI assistants.
  • README.md and README.zh-CN.md: user-facing English and Simplified Chinese documentation.
  • docs/: GitHub Pages source for stable, evidence-focused task and FAQ pages. docs/llms.txt is the canonical machine index; npm run sync:llms generates the repository-root copy.
  • test/: Node.js tests, including cross-platform CLI, protocol, docs, and release checks.
  • .github/workflows/: pinned CI and trusted npm publishing workflows.

Required checks

Read the full file on GitHub · 102 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 · 102 lines · 1,451 tokens per session scan C 944116450255

Subscribe to this mod's changes

coordinate-agents AGENTS.md is an instructions file published in the GitHub repository hogancv/coordinate-agents (101 stars, last pushed 3d ago), licensed MIT. It adds 1,451 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Multi-Agentagent-coordinationagentic-workflowai-agentsantigravity-climulti-agent-systems
Related

Other instructions, from other repositories

adk-java GEMINI.md

Gemini CLI instructions for google/adk-java, covering gemini code assistant context, project overview, building and running, maven commands and development workflow.

google/adk-java · 1,249 tokens

Avernet AGENTS.md

Instructions for inclusionAI/Avernet, covering agents.md, source of truth, project overview, repository layout and module responsibilities.

inclusionAI/Avernet · 3,113 tokens

Lody AGENTS.md

Instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.

LodyAI/Lody · 1,846 tokens

sprawling AGENTS.md

Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.

2youg1/sprawling · 2,019 tokens

xiaobei CLAUDE.md

Claude Code instructions for TeamWiseFlow/xiaobei, covering claude.md, docker 部署规范, crew template 开发规范, 创建/更新 skill 时，如果涉及到脚本或者 cli 指导内容，必须遵从以下原则： and skill.md frontmatter 书写规范.

TeamWiseFlow/xiaobei · 1,778 tokens

xiaobei AGENTS.md

AGENTS.md instructions for TeamWiseFlow/xiaobei, covering agents.md, docker 部署规范, crew template 开发规范, 创建/更新 skill 时，如果涉及到脚本或者 cli 指导内容，必须遵从以下原则： and skill.md frontmatter 书写规范.

TeamWiseFlow/xiaobei · 1,633 tokens