What is slack-mcp CLAUDE.md?

A project guide for building and checking a Slack integration. It explains the available commands, code layout, conventions, and the risks of tests that change a real Slack workspace.

Use it to run unit, integration, lint, type, and security checks, and to understand how Slack-related code should be organized and tested.

It helps developers run the right checks without accidentally using or changing an important workspace. It also gathers project rules in one place.

How karbassi/slack-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to karbassi/slack-mcp. 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/karbassi/slack-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/karbassi/slack-mcp

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/karbassi/slack-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/karbassi/slack-mcp/claude-md)

Your own site

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

Per session 726 This file is loaded in full into every session.

When invoked 726 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	$0.00726	$0.00726
Opus 5	$0.00363	$0.00363
Sonnet 5	$0.00145	$0.00145
Haiku 4.5	$0.00073	$0.00073

Measured 9d ago against content hash bfb3381f47dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

slack-mcp 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 9d 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Commands

mise run test              # unit tests
mise run test:integration  # integration tests (requires .env tokens)
mise run lint              # ruff linter
mise run typecheck         # ty type checker
mise run security          # semgrep security + AI best practices + custom rules
mise run check             # all checks (test + lint + typecheck + security)

Testing

⚠️ Integration tests hit a LIVE Slack workspace and mutate it (create channels, messages, reminders, files, user groups, …) as the owner of the tokens in .env. There is NO sandbox. NEVER point .env at a workspace you use — only a dedicated throwaway workspace.
.env is authoritative for the tokens it defines: load_dotenv(override=True) overrides inherited/exported values, but only per-variable. Define all of SLACK_XOXP_TOKEN/SLACK_XOXC_TOKEN/SLACK_XOXD_TOKEN in .env — a var missing from .env still falls back to the exported environment and could point at the wrong workspace.
Run integration tests after adding or modifying any tool — but only once .env is confirmed to point at the throwaway workspace.
Tests that need a channel must create a temp channel and archive it after — see temp_channel fixture in test_chat_integration.py
Many integration tests are skipped — they require a bot token (xoxb), Slack Connect, or interactive triggers, or would mutate a live workspace (see the skip reason on each). Adding a bot token is a future TODO

Code Layout

src/slack_mcp/
├── server.py        # FastMCP app, caching + name resolution middleware
├── client.py        # SlackClient — api_call, session_call, session_call_form, session_call_multipart
└── tools/           # One file per API family, @mcp.tool decorated
    ├── undocumented.py  # Session-only endpoints (xoxc/xoxd)
    ├── legacy.py        # Undocumented endpoints for existing API families
    └── *.py             # Official Slack Web API methods

Conventions

One tool per Slack API method, one file per API family
Official methods use client.api_call; undocumented use client.session_call
Unit tests in tests/test_tools/test_<family>.py, integration in test_<family>_integration.py
admin.* endpoints are intentionally excluded

Read the full file on GitHub · 59 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.

9d ago First seen · 59 lines · 726 tokens per session scan A bfb3381f47dc

Subscribe to this mod's changes

slack-mcp CLAUDE.md is an instructions file published in the GitHub repository karbassi/slack-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 726 tokens to every session, about $0.0036 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.

ai-agents fastmcp mcp mcp-server model-context-protocol slack

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 tokens

slack-mcp: Instructions file for Claude Code