What is slagent AGENTS.md?

A set of project instructions for slagent, a Go library that streams agent sessions into Slack threads, plus its slaude command-line tool for Claude Code. It describes the project structure, tasks, and commit rules.

Use it when modifying slagent, its Slack integration, credential handling, channel tools, command-line program, or permission server.

It gives a coding agent the project-specific context needed to work in the right files and follow the repository's conventions.

How sttts/slagent configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sttts/slagent. 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/sttts/slagent/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sttts/slagent

Made for: Codex, OpenCode.

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/sttts/slagent/agents-md/github.svg)](https://agentmods.dev/instructions/sttts/slagent/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sttts/slagent/agents-md"><img src="https://agentmods.dev/badge/instructions/sttts/slagent/agents-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/sttts/slagent/agents-md"><img src="https://agentmods.dev/badge/instructions/sttts/slagent/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,178 This file is loaded in full into every session.

When invoked 2,178 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	$0.02178	$0.02178
Opus 5.5	$0.00871	$0.00871
Sonnet 5.5	$0.00436	$0.00436
Haiku 4.5	$0.00218	$0.00218

Measured 1mo ago against content hash 3c5dafae5f88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

slagent 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 1mo 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

slagent — Agent Rules

Project

Go library for streaming agent sessions to Slack threads, plus slaude CLI that wraps Claude Code.

Structure

slagent.go, thread.go, turn.go   — Root library: Thread, Turn, NewSlackClient
compat.go, native.go             — Compat (postMessage/update) and native (chat.startStream) backends
mrkdwn.go, reply.go              — Markdown→mrkdwn, reply polling

credential/                      — Load, Save, Extract tokens from Slack desktop app
  credential.go                  — Credentials struct, Load, Save, Path
  extract.go, leveldb.go         — Extract() orchestrator, LevelDB token reading
  cookie.go, decrypt.go, paths.go

channel/                         — Resolve, List
  channel.go                     — Client, ResolveByName, ResolveUser, List

cmd/slaude/                      — CLI (auth, channels, share, status, start)
  main.go
cmd/slaude/internal/
  session/session.go             — Session orchestration
  claude/process.go, events.go   — Claude subprocess, stream-JSON parsing
  terminal/terminal.go           — Terminal UI
  perms/server.go, listener.go   — MCP permission server for Slack-based tool approval

cmd/slagent-demo/                — Demo CLI
  main.go

contrib/                         — Project assets
  logo.png                       — Project logo (update here, not root)

Module: github.com/sttts/slagent

Tasks

Use the task system (TaskCreate/TaskUpdate/TaskList) for everything the user asks.
Mark tasks in_progress before starting, completed when done.

Commit Rules

Title convention: area/subarea: short what has been done
Commit in sensible chunks. Don't mix topics.
Add files individually (not git add -A).
Do git add and git commit in one command.
Don't push without being asked.
Before committing, simplify the code. Look deeply at changes.

Build

ALWAYS build binaries into the repo root after ANY code change: go build -o slaude ./cmd/slaude/ && go build -o slagent-demo ./cmd/slagent-demo/ && go build -o claude-command-classifier-hook ./cmd/claude-command-classifier-hook/
Build each binary individually. go build ./... only checks compilation, it doesn't produce binaries.
The user runs ./slaude from the repo root. If you don't rebuild, they test stale code.

Read the full file on GitHub · 151 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.

1mo ago First seen · 151 lines · 2,178 tokens per session scan A 3c5dafae5f88

Subscribe to this mod's changes

slagent AGENTS.md is an instructions file published in the GitHub repository sttts/slagent (22 stars, last pushed 6mo ago), licensed MIT. It adds 2,178 tokens to every session, about $0.0087 per session on Opus 5.5. 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.

Claude Code slack

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 · 9,649 tokens

slagent: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

slagent — Agent Rules

Project

Structure

Tasks

Commit Rules

Build

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

deno copilot-instructions.md