openab: Instructions file for Codex

AGENTS.md

openab AGENTS.md is an instructions file for Codex, OpenCode from openabdev/openab. It costs 1,580 tokens per session, scanned A, original, MIT.

A repository instruction guide for OpenAB, a Rust program that connects chat services such as Discord and Slack to coding tools. It describes the project’s architecture, message flow, configuration, and compatibility rules.

In plain words
What is it for?
Use it when working on OpenAB modules such as adapters, configuration, scheduling, media handling, formatting, speech-to-text, or setup.
Why use it?
It gives coding agents the project-specific context needed to make changes that fit the existing design and preserve backward-compatible behavior.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is openabdev/openab's own configuration. It tells Codex and OpenCode how to work on openab itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything openab configures →

Reuse

Borrowing it

Nothing to install: this file belongs to openabdev/openab. 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/openabdev/openab/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/openabdev/openab

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.

agentmods badge for openab AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/openabdev/openab/agents-md/github.svg)](https://agentmods.dev/instructions/openabdev/openab/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/openabdev/openab/agents-md"><img src="https://agentmods.dev/badge/instructions/openabdev/openab/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.

agentmods 80×15 button for openab AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/openabdev/openab/agents-md"><img src="https://agentmods.dev/badge/instructions/openabdev/openab/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,580 This file is loaded in full into every session.
When invoked 1,580 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01580 $0.01580
Opus 5.5 $0.00632 $0.00632
Sonnet 5.5 $0.00316 $0.00316
Haiku 4.5 $0.00158 $0.00158

Measured 2mo ago against content hash 1c6b46cd4181, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openab 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 2mo 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 · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenAB — Agent Guidelines

You are contributing to OpenAB, a lightweight Rust-based ACP harness bridging Discord, Slack, and webhook platforms to coding CLIs over stdio JSON-RPC.

Architecture

src/
├── main.rs           # entrypoint, multi-adapter startup, graceful shutdown
├── adapter.rs        # ChatAdapter trait, AdapterRouter (platform-agnostic)
├── config.rs         # TOML config + ${ENV_VAR} expansion
├── discord.rs        # DiscordAdapter (serenity EventHandler)
├── slack.rs          # SlackAdapter (Socket Mode)
├── gateway.rs        # Custom Gateway WebSocket adapter
├── cron.rs           # Config-driven + usercron scheduler
├── media.rs          # Image resize/compress + STT download
├── format.rs         # Message splitting, thread name shortening
├── markdown.rs       # Discord markdown rendering
├── reactions.rs      # Emoji status controller (debounce, stall detection)
├── bot_turns.rs      # Bot turn tracking
├── error_display.rs  # User-facing error formatting
├── stt.rs            # Speech-to-text (Whisper API)
├── setup/            # Interactive setup wizard
│   ├── config.rs     # Setup config helpers
│   ├── validate.rs   # Input validation
│   └── wizard.rs     # CLI setup flow
└── acp/
    ├── protocol.rs   # JSON-RPC types + ACP event classification
    ├── connection.rs # Spawn CLI, stdio JSON-RPC, env_clear whitelist
    └── pool.rs       # Session key → AcpConnection map + lifecycle

Helm chart: charts/openab/ — Go templates, values.yaml, NOTES.txt Gateway: gateway/ — standalone Rust binary for Telegram/LINE/Teams Docs: docs/ — user-facing guides, ADRs, config reference

Message Flow

Discord/Slack event
  → channel allowlist check
  → user allowlist check (bot messages bypass this)
  → bot message filter (off/mentions/all)
  → thread detection (thread_metadata = thread, NOT parent_id)
  → bot ownership check (bot_owns = thread creator matches bot user ID)
  → multibot detection (allowUserMessages mode)
  → handle_message → pool.get_or_create → ACP JSON-RPC

Read the full file on GitHub · 160 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. 2mo ago First seen · 160 lines · 1,580 tokens per session scan A 1c6b46cd4181

Subscribe to this mod's changes

openab AGENTS.md is an instructions file published in the GitHub repository openabdev/openab (831 stars, last pushed 6d ago), licensed MIT. It adds 1,580 tokens to every session, about $0.0063 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.

Related

openab AGENTS.md compared with instructions from other repositories

openab AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
openab AGENTS.mdopenabdev/openabInstructions file8316d agoMITA1,580Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode