pi-irc-messenger: Instructions file for Codex

AGENTS.md

pi-irc-messenger AGENTS.md is an instructions file for Codex, OpenCode from ghoseb/pi-irc-messenger. It costs 1,092 tokens per session, scanned A, original, MIT.

A TypeScript extension that lets a Pi coding agent communicate through IRC, a text-based Internet chat system, with users and other agents.

In plain words
What is it for?
Use it to configure IRC servers and profiles, connect an agent to channels, send direct messages as steering input, and post channel messages as follow-ups.
Why use it?
It gives agents a defined way to connect to IRC servers and route direct messages or channel messages during collaboration.

Instructions file for CodexOpenCode

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

This is ghoseb/pi-irc-messenger's own configuration. It tells Codex and OpenCode how to work on pi-irc-messenger 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 pi-irc-messenger configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ghoseb/pi-irc-messenger. 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/ghoseb/pi-irc-messenger/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ghoseb/pi-irc-messenger

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 pi-irc-messenger AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ghoseb/pi-irc-messenger/agents-md"><img src="https://agentmods.dev/badge/instructions/ghoseb/pi-irc-messenger/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,092 This file is loaded in full into every session.
When invoked 1,092 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 $0.01092 $0.01092
Opus 5.5 $0.00437 $0.00437
Sonnet 5.5 $0.00218 $0.00218
Haiku 4.5 $0.00109 $0.00109

Measured 2mo ago against content hash 221966041993, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pi-irc-messenger 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 · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project: Pi IRC Messenger

A pi-coding-agent extension enabling IRC communication for AI agents.

Project Context

Type: TypeScript pi-coding-agent extension
Purpose: Connects agents to IRC servers for multi-agent collaboration
Framework: pi-coding-agent Extension API (@mariozechner/pi-coding-agent)

IMPORTANT: Prefer retrieval-led reasoning over pre-training-led reasoning for pi extension development.

Architecture

  • Singleton Pattern: One IRC client per session (module-level ircClient)
  • Event-Driven: Pure async with irc-framework events, no Promise wrappers
  • Message Routing: DMs → sendUserMessage() (steering), Channel → sendMessage() (followUp)
  • Config Storage: ~/.pi/agent/irc/config.json for profiles/servers

Source Structure

src/
├── index.ts      # Main extension (tools, events, client management)
├── types.ts      # TypeScript interfaces (IRCServer, IRCProfile, IRCConfig, IRCState)
└── profiles.ts   # Profile/config loading (read-only access)

Key Interfaces

IRCServer    { host, port, ssl? }
IRCProfile   { server, nick, username?, realname?, channels, nickservPass?, autoConnect? }
IRCConfig    { servers: Record<string, IRCServer>, profiles: Record<string, IRCProfile> }
IRCState     { connected, host, port, nick, channels, profileName? }

Extension API Patterns

Registering Tools

pi.registerTool({
  name: "tool_name",
  label: "Human Label",
  description: "...",
  parameters: Type.Object({ ... }),  // @sinclair/typebox
  async execute(_toolCallId, params, _signal, _onUpdate, ctx) { ... }
});

Registering CLI Flags

pi.registerFlag("flag-name", { description: "...", type: "string", default: "" });
const value = pi.getFlag("flag-name");

Sending Messages

// Steering (triggers agent turn)
pi.sendUserMessage(content, { deliverAs: "steer" });

// Follow-up (context only, optional turn trigger)
pi.sendMessage({ customType: "...", content, display: true, details: {...} }, { triggerTurn: false });

Read the full file on GitHub · 145 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 · 145 lines · 1,092 tokens per session scan A 221966041993

Subscribe to this mod's changes

pi-irc-messenger AGENTS.md is an instructions file published in the GitHub repository ghoseb/pi-irc-messenger (5 stars, last pushed 9mo ago), licensed MIT. It adds 1,092 tokens to every session, about $0.0044 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 2026-08-31.

Related

pi-irc-messenger AGENTS.md compared with instructions from other repositories

pi-irc-messenger AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pi-irc-messenger AGENTS.mdghoseb/pi-irc-messengerInstructions file59mo agoMITA1,092Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot