Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/jtalk22/slack-mcp-server/claude-mdgit clone --depth 1 https://github.com/jtalk22/slack-mcp-serverWrote 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/jtalk22/slack-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/jtalk22/slack-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jtalk22/slack-mcp-server/claude-md.svg" alt="Measured on agentmods" 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 | $0.02198 | $0.02198 |
| Opus 5 | $0.01099 | $0.01099 |
| Sonnet 5 | $0.00440 | $0.00440 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
slack-mcp-server 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 6d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides maintainer-oriented context for automated edits in this repository.
Project Scope
Session-based Slack MCP server. Works with any MCP client via stdio transport, or via hosted HTTP for browser-based clients.
Build and Run
npm install
npm start # MCP server on stdio
npm run web # REST API + Web UI (localhost:3000)
npm run tokens:auto # Auto-extract from Chrome (macOS)
npm run tokens:status # Check token health
Installation Paths
npx -y @jtalk22/slack-mcp # package entrypoint
docker pull ghcr.io/jtalk22/slack-mcp-server:latest
MCP Tools (19 total)
Slack reads (12):
| Tool | Purpose |
|---|---|
slack_health_check |
Verify token validity and show workspace info |
slack_token_status |
Token age, health, cache stats |
slack_refresh_tokens |
Auto-extract fresh tokens from Chrome (macOS) |
slack_list_conversations |
List DMs and channels with resolved names |
slack_conversations_history |
Get messages from a channel or DM |
slack_get_full_conversation |
Export full history with threads |
slack_search_messages |
Search across workspace |
slack_get_thread |
Get thread replies |
slack_users_info |
Get user details |
slack_list_users |
List workspace users (paginated, 500+) |
slack_users_search |
Search by name, display name, or email |
slack_conversations_unreads |
Channels/DMs with unread messages |
Slack writes (4): slack_send_message, slack_add_reaction, slack_remove_reaction, slack_conversations_mark — all carry MCP destructive safety annotation.
Workflow primitives (2): slack_workflow_save, slack_workflows — bind a workflow_kind (incident_room, exec_brief, support_inbox, product_launch_watch, custom) to channels + priority people + retention + cadence. Stored locally at ~/.slack-mcp-workflows.json.
Local catch-up (1): slack_catch_me_up — reads a saved profile's scope and returns structured evidence (lib/catch-up.js). There are no hosted upgrade stubs in the package since 5.0.0; every advertised tool runs locally.
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.
- 6d ago First seen · 161 lines · 2,198 tokens per session scan A 083fbf57bd04
slack-mcp-server CLAUDE.md is an instructions file published in the GitHub repository jtalk22/slack-mcp-server (29 stars, last pushed yesterday), licensed MIT. It adds 2,198 tokens to every session, about $0.0110 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 2026-08-30.
Other instructions, from other repositories
mcp-unity AGENTS.md
AGENTS.md instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
rails-ai-context AGENTS.md
AGENTS.md instructions for crisnahine/rails-ai-context, covering rails-ai-context, agent skills, issue tracker, triage labels and domain docs.
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
inspecto CLAUDE.md
Claude Code instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.
imagine-mcp AGENTS.md
AGENTS.md instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.