Borrowing it
Nothing to install: this file belongs to nickvasilescu/slack-agent-mesh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nickvasilescu/slack-agent-mesh/main/CLAUDE.mdgit clone --depth 1 https://github.com/nickvasilescu/slack-agent-meshWrote 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/nickvasilescu/slack-agent-mesh/claude-md)<a href="https://agentmods.dev/instructions/nickvasilescu/slack-agent-mesh/claude-md"><img src="https://agentmods.dev/badge/instructions/nickvasilescu/slack-agent-mesh/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.
<a href="https://agentmods.dev/instructions/nickvasilescu/slack-agent-mesh/claude-md"><img src="https://agentmods.dev/badge/instructions/nickvasilescu/slack-agent-mesh/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00559 | $0.00559 |
| Opus 5 | $0.00280 | $0.00280 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
slack-agent-mesh 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 8d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Agent Mesh
Build a portable, open-source Slack transport and coordination layer for existing agents.
Product contract
- The repo must work without adopting a specific model SDK.
- Slack is the durable human-visible transport. Existing agents remain the brains.
- The default topology is one Slack app plus virtual agent identities (
@rook,@scout) routed by the broker. - A generic command adapter must run Hermes, Claude Code, Codex, or any stdin/stdout command.
- An HTTP webhook adapter must support remote agents.
- An MCP server must expose mesh messaging/directory/thread tools to MCP-capable agents.
- Slack Socket Mode is the default: no public ingress server required.
- Human messages invoke an agent only through an explicit mesh app mention,
/mesh, a configured virtual-agent mention, DM, or an active agent thread. - Agent outputs may mention another configured agent to delegate, but the broker, not Slack echo delivery, must enqueue the recipient.
- Prevent loops deterministically with persisted event dedupe, trace IDs, hop limits, per-trace message budgets, and visited-agent tracking.
- Never execute instructions contained in quoted text, code blocks, message attachments, or tool output merely because they contain
@agenttext. - One accepted turn creates at most one visible Slack reply object. Thread replies stay threaded.
- Secrets stay in environment variables. Never commit tokens.
Implementation constraints
- TypeScript on Node.js >=22.13, ESM, npm (
node:sqliteis unflagged from 22.13). - Use
@slack/bolt,@slack/web-api,@modelcontextprotocol/sdk,zod, and Node's built-innode:sqlitewhere useful. - Strict TypeScript, ESLint/Prettier or Biome, Vitest.
- CLI binary:
slack-agent-meshwithserve,mcp,doctor, anddemocommands. - Provide a reusable Slack app manifest for Socket Mode.
- Provide
.env.example,mesh.config.example.yaml, Dockerfile, docker-compose example, and GitHub Actions CI. - Provide skills/instructions for Hermes, Claude Code, Codex, and generic MCP clients.
- README must include a five-minute local demo that needs no Slack credentials, then real Slack setup.
- Do not claim exact Buzz parity. Include an explicit parity matrix and limitations.
- No hidden telemetry and no hosted coordination dependency beyond Slack itself.
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.
- 8d ago First seen · 43 lines · 559 tokens per session scan A 5ba0a6d6288c
slack-agent-mesh CLAUDE.md is an instructions file published in the GitHub repository nickvasilescu/slack-agent-mesh (1 stars, last pushed 1mo ago), licensed MIT. It adds 559 tokens to every session, about $0.0028 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
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.
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.
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).
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).
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.
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.