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.
npx agentmods add instructions/ghoseb/pi-irc-messenger/agents-mdgit clone --depth 1 https://github.com/ghoseb/pi-irc-messengerWrote 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.
[](https://agentmods.dev/instructions/ghoseb/pi-irc-messenger/agents-md)<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="Measured on agentmods" height="20"></a>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 | $0.01092 | $0.01092 |
| Opus 5 | $0.00546 | $0.00546 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
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 5d 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.
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.jsonfor 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 });
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.
- 5d ago First seen · 145 lines · 1,092 tokens per session scan A 221966041993
pi-irc-messenger AGENTS.md is an instructions file published in the GitHub repository ghoseb/pi-irc-messenger (5 stars, last pushed 6mo ago), licensed MIT. It adds 1,092 tokens to every session, about $0.0055 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).