Borrowing it
Nothing to install: this file belongs to jeremylongshore/claude-code-slack-channel. 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/jeremylongshore/claude-code-slack-channel/main/AGENTS.mdgit clone --depth 1 https://github.com/jeremylongshore/claude-code-slack-channelWrote 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/jeremylongshore/claude-code-slack-channel/agents-md)<a href="https://agentmods.dev/instructions/jeremylongshore/claude-code-slack-channel/agents-md"><img src="https://agentmods.dev/badge/instructions/jeremylongshore/claude-code-slack-channel/agents-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/jeremylongshore/claude-code-slack-channel/agents-md"><img src="https://agentmods.dev/badge/instructions/jeremylongshore/claude-code-slack-channel/agents-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 | $0.03304 | $0.03304 |
| Opus 5.5 | $0.01322 | $0.01322 |
| Sonnet 5.5 | $0.00661 | $0.00661 |
| Haiku 4.5 | $0.00330 | $0.00330 |
Grade A, and why
claude-code-slack-channel AGENTS.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 1mo 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — CCSC (claude-code-slack-channel)
This file is the cross-tool agent-instruction surface for this repo, following the open agents.md spec. It is read natively by Claude Code, OpenAI Codex CLI, Cursor, Cline, Aider, Devin, Sourcegraph Amp, Gemini CLI, Continue, Roo Code, Factory Droids, GitHub Copilot, Windsurf, and Amazon Q.
If you are an AI assistant helping a user with this repo, read this file FIRST.
What this repo is
CCSC is a two-way Slack ↔ Claude Code bridge via Slack Socket Mode and MCP stdio. A local TypeScript MCP server (Bun runtime) speaks Socket Mode to Slack and the Model Context Protocol over stdio to a Claude Code session. The whole codebase is a security substrate: every inbound message passes a five-layer prompt-injection defense, every tool call is gated by a declarative policy engine, and every decision is written to a hash-chained tamper-evident audit journal.
If you're helping a new user install this
Run them through /slack-channel:install (the install skill at skills/install/SKILL.md).
That skill handles prerequisite checks, Slack app creation, the silent-killer
add-bot-to-channel step, token configuration (delegates to /slack-channel:configure),
pairing (delegates to /slack-channel:access pair), and a verification round-trip.
Do NOT make a new user read CLAUDE.md or the design docs in 000-docs/ first —
those are maintainer reference, not onboarding. Point them at README.md for
the human-readable quick start, and use the install skill for hand-holding.
Critical setup gotchas (the silent killers)
These are the three failure modes that look like "the bot just doesn't work" but are actually unstated prerequisites:
- Slack bot must be ADDED to the channel after app install. Slack installs an app to a workspace WITHOUT joining any channels. The pairing DM works because DMs auto-route, but a channel test message will hit silence because the bot literally isn't in the channel to see the event. Fix: in Slack, open the channel → channel name → Integrations → Add an App → select the bot.
- Bun must be installed. README Option B falls back to Node.js via npx,
but requires editing
.mcp.json. Default path is Bun; install from https://bun.sh. - Claude Code must support Channels and use a supported Anthropic login.
The current Channels contract accepts either a
claude.aiaccount or an Anthropic Console API key. Team and Enterprise organizations must also have Channels enabled by an Owner or through managed settings. Channels are not available through Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry; do not misdiagnose those platform limits as a Slack token failure.
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.
- 1mo ago Changed · +1 lines · +20 tokens per session 55628ac2cf97
- 1mo ago Changed · +2 lines · +18 tokens per session 91916ba89a91
- 1mo ago First seen · 234 lines · 3,266 tokens per session scan A 69c188425514
claude-code-slack-channel AGENTS.md is an instructions file published in the GitHub repository jeremylongshore/claude-code-slack-channel (42 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,304 tokens to every session, about $0.0132 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.