What is slack-claude-code-integration CLAUDE.md?

A project guide for a Slack integration that lets teams use Claude Code through a Slack bot and the Model Context Protocol, a standard for connecting software tools to AI systems.

Use it to install dependencies, build or watch the TypeScript code, run tests and quality checks, start the test mode, or manage the Docker services.

It collects the setup, build, test, formatting, linting, Docker, and development commands in one place.

How engineers-hub-ltd-in-house-project/slack-claude-code-integration c

Reuse

Borrowing it

Nothing to install: this file belongs to engineers-hub-ltd-in-house-project/slack-claude-code-integration. 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/engineers-hub-ltd-in-house-project/slack-claude-code-integration/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/engineers-hub-ltd-in-house-project/slack-claude-code-integration

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/engineers-hub-ltd-in-house-project/slack-claude-code-integration/claude-md/github.svg)](https://agentmods.dev/instructions/engineers-hub-ltd-in-house-project/slack-claude-code-integration/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/engineers-hub-ltd-in-house-project/slack-claude-code-integration/claude-md"><img src="https://agentmods.dev/badge/instructions/engineers-hub-ltd-in-house-project/slack-claude-code-integration/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/engineers-hub-ltd-in-house-project/slack-claude-code-integration/claude-md"><img src="https://agentmods.dev/badge/instructions/engineers-hub-ltd-in-house-project/slack-claude-code-integration/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 964 This file is loaded in full into every session.

When invoked 964 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	$0.00964	$0.00964
Opus 5.5	$0.00386	$0.00386
Sonnet 5.5	$0.00193	$0.00193
Haiku 4.5	$0.00096	$0.00096

Measured 2mo ago against content hash 9aca1e13bf40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

slack-claude-code-integration 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 · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Slack integration system that enables teams to use Claude Code through Slack using the Model Context Protocol (MCP). The architecture follows:

Slack → Slack Bot → Claude Code MCP Server → Claude Code CLI

Essential Commands

Development

# Initial setup (installs all dependencies)
npm run setup

# Build TypeScript code
npm run build         # One-time build
npm run build:watch   # Watch mode for development

# Run in development mode (builds and watches)
npm run dev

# Run tests (currently placeholder)
npm test

# Code quality
npm run lint          # Check TypeScript and JavaScript files
npm run lint:fix      # Auto-fix lint errors  
npm run format        # Format all code with Prettier
npm run format:check  # Check formatting

# Start in test mode (uses echo instead of Claude CLI)
./start-test.sh

Docker Operations

npm run docker:build  # Build Docker images
npm run docker:up     # Start services
npm run docker:down   # Stop services

Git Hooks

Lefthook is configured to run pre-commit checks automatically. To manually install:

npx lefthook install

Architecture

Component Structure

claude-code-mcp/: MCP server that wraps Claude Code CLI (TypeScript)
- Source: claude-code-mcp/index.ts
- Built to: dist/claude-code-mcp/index.js
- Implements stdio-based MCP protocol
- Handles tools/list and tools/call methods
- Spawns Claude CLI or echo (test mode) as child process
slack-bot/: Slack Bolt application (TypeScript)
- Source: slack-bot/index.ts
- Built to: dist/slack-bot/index.js
- Connects to MCP server as client
- Handles app mentions, DMs, and slash commands
- Manages project path switching via --project flag

Key Integration Points

MCP Communication: The Slack bot creates a StdioClientTransport to communicate with the MCP server, which runs as a separate Node.js process.

Read the full file on GitHub · 117 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 · 117 lines · 964 tokens per session scan A 9aca1e13bf40

Subscribe to this mod's changes

slack-claude-code-integration CLAUDE.md is an instructions file published in the GitHub repository engineers-hub-ltd-in-house-project/slack-claude-code-integration (11 stars, last pushed 1y ago), licensed MIT. It adds 964 tokens to every session, about $0.0039 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.

slack-claude-code-integration CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
slack-claude-code-integration CLAUDE.mdengineers-hub-ltd-in-house-project/slack-claude-code-integration	Instructions file	11	1y ago	MIT	A	964	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

slack-claude-code-integration: Instructions file for Claude Code