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/earendil-works/pi-chat/agents-mdgit clone --depth 1 https://github.com/earendil-works/pi-chatWrote 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/earendil-works/pi-chat/agents-md)<a href="https://agentmods.dev/instructions/earendil-works/pi-chat/agents-md"><img src="https://agentmods.dev/badge/instructions/earendil-works/pi-chat/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 | $0.01446 | $0.01446 |
| Opus 5 | $0.00723 | $0.00723 |
| Sonnet 5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
pi-chat 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-chat
Pi extension bridging Discord and Telegram to a sandboxed pi session via Gondolin micro-VMs.
Architecture
Discord/Telegram ←→ Live Adapter ←→ Runtime (log, jobs, slices) ←→ pi agent
↕
Gondolin VM (Alpine + bash)
/workspace /shared
- One VM per connection. Started on
/chat-connect, closed on/chat-disconnect./chat-spawn-alllaunches one detached tmux/pi worker per configured channel using the--chat-conversation <account/channel>extension flag./chat-workers,/chat-open-all, and/chat-kill-allmanage those workers through tmux. Workers write status JSON to~/.pi/agent/chat/worker-status/; thechat_workerstool reads it. - One JSONL log per channel. Append-only event stream: inbound, outbound, job lifecycle.
- Trigger-based dispatch. Mentions in channels, every message in DMs. Triggers queue jobs; jobs produce slices of inbound records for the agent.
- Tools run inside the VM.
read,write,edit,bashare routed through Gondolin.chat_historyandchat_attachrun on the host.
Entry point
index.ts — Extension factory. Registers tools, commands, event handlers, connection lifecycle, and tmux spawning.
Key files
Core types
src/core/config-types.ts— Config, account, channel, secret, and resolved conversation types.src/core/runtime-types.ts— Log record types, job types, dispatch types.src/core/discovery-types.ts— Discovery snapshot types (channels, users, roles).src/core/keys.ts— Channel key derivation.
Config & storage
src/config.ts— Load/save config, resolve conversations, storage paths. Everything under~/.pi/agent/chat/.src/discovery-store.ts— Read/write discovery snapshots (cached channel/user/role lists).src/log.ts— JSONL log read/write, locking, attachment materialization, directory setup.
Runtime
src/runtime.ts—ConversationRuntime: log state machine, job queue, slice construction, prompt building, checkpoint management. Owns trigger logic, access policy, control command parsing.
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 · 121 lines · 1,446 tokens per session scan A b9d0554bf8bf
pi-chat AGENTS.md is an instructions file published in the GitHub repository earendil-works/pi-chat (389 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,446 tokens to every session, about $0.0072 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.
Other instructions, from other repositories
antislop AGENTS.md
Instructions for drunkrhin0/antislop, covering agents, agent skills, issue tracker, triage labels and domain docs.
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.
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.
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.