slack-agent-cli AGENTS.md

A set of instructions for using slack-agent-cli, a command-line tool for managing Slack workspaces. Slack is a team messaging service.

In plain words
What is it for?
Listing channels, reading and managing Slack messages, working with direct messages, adding reactions, looking up users, and searching when the needed token is available.
Why use it?
It explains how to install the tool, provide the required access tokens, and confirm that it works, so an agent can use Slack from a terminal.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/bcharleson/slack-agent-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/bcharleson/slack-agent-cli

Made for: Codex, OpenCode.

Per session 2,455 This file is loaded in full into every session.
When invoked 2,455 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce 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

Measured 2d ago against content hash ee3ad5d9e56c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 285 lines

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-cli to 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:

  1. --bot-token / --user-token flags (per-command override)
  2. SLACK_BOT_TOKEN / SLACK_USER_TOKEN environment variables (recommended for agents)
  3. .env file in the working directory (via python-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

Read the full file on GitHub · 285 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.

  1. 2d ago First seen · 285 lines · 2,455 tokens per session scan A ee3ad5d9e56c

Subscribe to this mod's changes

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.