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.
npx agentmods add instructions/jerfowler/agent-comm-mcp-server/claude-mdgit clone --depth 1 https://github.com/jerfowler/agent-comm-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/jerfowler/agent-comm-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/jerfowler/agent-comm-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jerfowler/agent-comm-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.07445 | $0.07445 |
| Opus 5 | $0.03723 | $0.03723 |
| Sonnet 5 | $0.01489 | $0.01489 |
| Haiku 4.5 | $0.00745 | $0.00745 |
Grade A, and why
agent-comm-mcp-server CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 896 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Agent Communication MCP Server
This file provides guidance to Claude Code when working with the agent-comm-mcp-server NPM package.
Project Overview
Name: @jerfowler/agent-comm-mcp-server
Purpose: MCP server for AI agent task communication and delegation with diagnostic lifecycle visibility
Author: Jeremy Fowler
License: MIT
This is a standalone TypeScript NPM package that implements a Model Context Protocol (MCP) server enabling Claude Code to coordinate multiple specialized agents, track their progress in real-time, and understand exactly how they approach and solve complex tasks.
Repository Context
- Standalone NPM Package: This is NOT part of a parent project - it's an independent package
- GitHub: https://github.com/jerfowler/agent-comm-mcp-server
- NPM: https://www.npmjs.com/package/@jerfowler/agent-comm-mcp-server
- Node.js: >= 18.0.0 required
Architecture
Core Design Principles
- Zero File Path Exposure: Agents never see file paths, only clean context IDs
- Non-Blocking Operations: All agents can work simultaneously
- Context-Based Abstraction: Clean task descriptions automatically generated
- Diagnostic Visibility: Monitor without controlling execution flow
Component Hierarchy
MCP SDK Layer (JSON-RPC communication)
↓
Tool Layer (17 specialized MCP tools)
↓
Core Layer (TaskContextManager, ConnectionManager, EventLogger)
↓
Utility Layer (FileSystem, LockManager, TaskManager, validation)
↓
Storage Layer (File system with locking coordination)
Task Lifecycle
INIT → PLAN → PROGRESS → DONE/ERROR
↓ ↓ ↓ ↓
Context-based workflow with diagnostic visibility
Comprehensive TypeScript Strict Mode Enforcement System
This project implements a multi-layered enforcement system to permanently eliminate TypeScript strict mode violations, 'any' types, and direct fs-extra imports. This system prevents the "never ending cycle of fix, break, repeat" through comprehensive validation at multiple checkpoints.
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.
- 3d ago First seen · 896 lines · 7,445 tokens per session scan A fd760c334f1a
agent-comm-mcp-server CLAUDE.md is an instructions file published in the GitHub repository jerfowler/agent-comm-mcp-server (2 stars, last pushed 11mo ago), licensed MIT. It adds 7,445 tokens to every session, about $0.0372 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.
Other instructions, from other repositories
mcp-server-excel AGENTS.md
AGENTS.md instructions for sbroenne/mcp-server-excel, covering agent skills, repository rules, issue tracker and domain docs.
todox AGENTS.md
Instructions for beydemirfurkan/todox, covering this is not the next.js you know, todox — agent rules, sprint workflow, confusion protocol and 3-strike rule.
onplana-mcp-server GEMINI.md
Instructions for Onplana/onplana-mcp-server, covering onplana, gemini context, what onplana is, authenticating, hints when working with onplana data and common workflows.
dibs CLAUDE.md
Instructions for Agenxy/dibs, a project described as: Keeps your agents in the loop about each other. See what the fleet is doing, then message, sync and send files between agents. Dibs reports; it never acts.
todoist-mcp-server CLAUDE.md
Claude Code instructions for stevesimpson418/todoist-mcp-server, covering claude.md — project intelligence, project overview, tech stack, project structure and key commands.
microsoft-planner-mcp github-issues.instructions.md
Use when creating, filing, triaging, or discussing GitHub issues. Enforces use of the repository's ISSUETEMPLATE forms for bugs, features, and tasks.