What is agent-comm CLAUDE.md?

Project instructions for building agent-comm, a Node.js and TypeScript system for agents, messages, storage, web APIs, WebSockets, and an MCP connection. They also describe its plain JavaScript dashboard and coding conventions.

Use them when changing agent-comm services, SQLite storage, REST or WebSocket transport, MCP support, the dashboard, or its TypeScript and CSS styles.

They give maintainers the project's architecture and interface rules, helping new changes fit its dependency-injection structure, storage layer, transports, and dashboard.

How keshrath/agent-comm configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to keshrath/agent-comm. 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/keshrath/agent-comm/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/keshrath/agent-comm

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/keshrath/agent-comm/claude-md/github.svg)](https://agentmods.dev/instructions/keshrath/agent-comm/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/keshrath/agent-comm/claude-md"><img src="https://agentmods.dev/badge/instructions/keshrath/agent-comm/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/keshrath/agent-comm/claude-md"><img src="https://agentmods.dev/badge/instructions/keshrath/agent-comm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,143 This file is loaded in full into every session.

When invoked 1,143 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01143	$0.01143
Opus 5.5	$0.00457	$0.00457
Sonnet 5.5	$0.00229	$0.00229
Haiku 4.5	$0.00114	$0.00114

Measured 2mo ago against content hash 95c2fe519c52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-comm 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 2mo 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.

CLAUDE.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-comm

Architecture

Layered architecture with explicit dependency injection (no global state):

src/
  domain/     agents, channels, messages, state, feed, cleanup, rate-limit, events
  storage/    SQLite (better-sqlite3, WAL mode)
  transport/  REST (node:http), WebSocket (ws), MCP (stdio)
  ui/         Vanilla JS dashboard (no build step for UI)

No frameworks — no React, Vue, Express. Pure Node.js + TypeScript.
context.ts is the DI root — wires all services together.
UI files (index.html, app.js, styles.css) are plain files copied to dist/ui/ on build.

UI / Dashboard

Icons: Material Symbols Outlined (via Google Fonts CSS). No emojis.
Fonts: Inter (UI text), JetBrains Mono (code/data)
Theme: Light/dark toggle via .theme-light / .theme-dark class on <body>
Design tokens: CSS custom properties (--bg, --accent, --border, --shadow-*, etc.)
Accent color: #5d8da8
Radii: 12px cards, 16px panels, 8px small elements
Section headers: Uppercase, 13px, weight 600, letter-spacing 0.5px
Empty states: Material Symbols icon (block, centered) + text + optional hint

Code Style

ESLint + Prettier enforced via lint-staged (husky pre-commit)

Versioning

Version lives in package.json and is read at runtime (REST /health, WS state payload, UI sidebar)
Never hardcode version strings
Every commit must bump the patch version minimum
Commit message format: v1.0.x: short description

Build & Test

npm run build      # tsc + copy UI files to dist/
npm test           # vitest (unit + integration + e2e)
npm run check      # typecheck + lint + format + test
npm run dev        # watch mode (tsc + nodemon)

Key APIs

REST: GET /health, GET /api/agents, GET /api/messages, GET /api/channels, GET /api/state, GET /api/feed, POST /api/cleanup/stale, POST /api/cleanup/full, POST /api/state/:ns/:key/cas (atomic compare-and-swap, used by the file-coord hook)
WebSocket: Full state on connect, incremental events streamed, refresh request supported
MCP: 7 tools (comm_register, comm_agents, comm_send, comm_inbox, comm_poll, comm_channel, comm_state). comm_inbox accepts an importance filter; comm_poll blocks on message:sent until a matching message arrives (or timeout). Full-text search (FTS5) is available via REST (GET /api/messages/search) for the dashboard's human-facing search bar — agents use comm_inbox with filters instead. Activity feed is auto-emitted internally on all actions (no MCP tool needed).

Read the full file on GitHub · 73 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.

2mo ago First seen · 73 lines · 1,143 tokens per session scan A 95c2fe519c52

Subscribe to this mod's changes

agent-comm CLAUDE.md is an instructions file published in the GitHub repository keshrath/agent-comm (9 stars, last pushed 28d ago), licensed MIT. It adds 1,143 tokens to every session, about $0.0046 per session on Opus 5.5. 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.

Building agents Claude Code Multi-Agent ai-agents codex-cli mcp model-context-protocol

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 · 9,715 tokens

agent-comm: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

agent-comm

Architecture

UI / Dashboard

Code Style

Versioning

Build & Test

Key APIs

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

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

langchain AGENTS.md

vscode copilot-instructions.md

deno copilot-instructions.md