agent-slack AGENTS.md

A set of instructions for keeping an agent’s project guidance and installed skills aligned with its code and README.

In plain words
What is it for?
Maintaining AGENTS.md files and writing concise guidance for agents that perform Slack-related tasks.
Why use it?
It helps an agent follow the project’s actual workflow without repeating general documentation or relying on outdated instructions.

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/stablyai/agent-slack/agents-md
Clone the repo
git clone --depth 1 https://github.com/stablyai/agent-slack

Made for: Codex, OpenCode.

Per session 116 This file is loaded in full into every session.
When invoked 116 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 $0.00116 $0.00116
Opus 5 $0.00058 $0.00058
Sonnet 5 $0.00023 $0.00023
Haiku 4.5 $0.00012 $0.00012

Measured 3d ago against content hash 9172d378ae53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-slack 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 3d 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 · 10 lines

What it actually says

AGENTS.md

Skills

This repo includes an installable skill at skills/agent-slack/SKILL.md. Keep it aligned with the code and README.

  • Write the skill for an agent executing Slack tasks, not as user-facing documentation.
  • Keep it token-efficient: do not add tables of contents, exhaustive command/flag catalogs, or duplicate the README and CLI help.
  • Treat the installed agent-slack --help and subcommand help as authoritative. Keep only non-obvious workflow, safety, targeting, and output behavior in the skill.
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. 3d ago First seen · 10 lines · 116 tokens per session scan A 9172d378ae53

Subscribe to this mod's changes

agent-slack AGENTS.md is an instructions file published in the GitHub repository stablyai/agent-slack (530 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session, about $0.0006 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.