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/bcharleson/slack-agent-cli/agents-mdgit clone --depth 1 https://github.com/bcharleson/slack-agent-cliWhat 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 | $0.02455 | $0.02455 |
| Opus 5 | $0.01228 | $0.01228 |
| Sonnet 5 | $0.00491 | $0.00491 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
slack-agent-cli 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 2d 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Agent CLI — AI Agent Guide
This file helps AI agents (Claude, Cursor, GPT, Gemini, OpenClaw) install, authenticate, and use
slack-agent-clito manage Slack workspaces via terminal commands or MCP tools.
Quick Start
# Install (requires Node 18+ and Python 3.10+)
npm install -g slack-agent-cli
# Authenticate (non-interactive — best for agents)
export SLACK_BOT_TOKEN="xoxb-your-bot-token"
export SLACK_USER_TOKEN="xoxp-your-user-token" # optional; required for search
# Verify
slack --version
slack channels list --pretty
Alternative (Python-only, from source):
git clone https://github.com/bcharleson/slack-agent-cli.git
cd slack-agent-cli
python3 -m venv venv && source venv/bin/activate
pip install -e .
slack channels list
Authentication
Two tokens, resolved in this order:
--bot-token/--user-tokenflags (per-command override)SLACK_BOT_TOKEN/SLACK_USER_TOKENenvironment variables (recommended for agents).envfile in the working directory (viapython-dotenv)
| Token | Prefix | Used for |
|---|---|---|
| Bot token | xoxb- |
Channels, messages, DMs, reactions, most user lookups |
| User token | xoxp- |
Search (search.* commands/tools) — bot token cannot search |
Create tokens at Slack API Apps → your app → OAuth & Permissions → Install to workspace.
Minimum bot scopes: channels:read, channels:write, channels:history, groups:read, groups:write, groups:history, chat:write, im:read, im:write, im:history, mpim:read, mpim:write, mpim:history, users:read, users:read.email, reactions:read, reactions:write.
For search, add user scope: search:read.
Output Format
All commands return JSON — stdout on success, stderr on error:
# Default: compact JSON (agent-optimized)
slack channels list
# → {"channels":[{"id":"C0123","name":"general",...}],"total":42}
# Pretty-printed
slack channels list --pretty
# or
slack --output pretty channels list
# Exit code only (automation)
slack --quiet channels list
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.
- 2d ago First seen · 285 lines · 2,455 tokens per session scan A ee3ad5d9e56c
slack-agent-cli AGENTS.md is an instructions file published in the GitHub repository bcharleson/slack-agent-cli (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,455 tokens to every session, about $0.0123 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
slack-mcp CLAUDE.md
Instructions for aaronsb/slack-mcp, covering slack mcp server, build, architecture, tools and environment.
slack-mcp CLAUDE.md
Instructions for karbassi/slack-mcp, covering claude.md, commands, testing, code layout and conventions.
slack-mcp-server CLAUDE.md
Claude Code instructions for mynghn/slack-mcp-server, covering slack-mcp-server development guidelines, active technologies, project structure, commands and code style.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.