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/khairold/pibun/claude-mdgit clone --depth 1 https://github.com/khairold/pibunWrote 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/khairold/pibun/claude-md)<a href="https://agentmods.dev/instructions/khairold/pibun/claude-md"><img src="https://agentmods.dev/badge/instructions/khairold/pibun/claude-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 | $0.03749 | $0.03749 |
| Opus 5 | $0.01875 | $0.01875 |
| Sonnet 5 | $0.00750 | $0.00750 |
| Haiku 4.5 | $0.00375 | $0.00375 |
Grade A, and why
pibun CLAUDE.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 4d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Identity
PiBun — A desktop GUI for the Pi coding agent, built with Electrobun.
- Runtime: Bun (monorepo with workspaces)
- Language: TypeScript (strict)
- Server: Bun HTTP + WebSocket — thin bridge to Pi's RPC mode
- Web: React 19 + Vite + Zustand + Tailwind CSS v4
- Desktop: Electrobun (Bun-native webview, no Chromium)
- No Effect, no Schema — plain TypeScript + Zustand everywhere
Architecture
┌─────────────┐ WebSocket ┌──────────────┐ stdio/JSONL ┌─────────┐
│ React UI │ ◄──────────────────►│ Bun Server │ ◄──────────────────►│ pi --rpc│
│ (Vite) │ │ │ │ │
│ Chat, Tools│ │ piRpcManager │ │ LLM API │
│ Sessions │ │ wsServer │ │ Tools │
└─────────────┘ └──────────────┘ └─────────┘
▲ ▲
└──────── Electrobun webview ──────┘
Core principle: Pi handles state. The server is a thin bridge. Don't reimplement what Pi already does.
Pi manages: session persistence, model registry, API keys, auto-compaction, auto-retry, tool execution, extensions, skills, prompt templates. The server spawns pi --mode rpc subprocesses, pipes JSONL events to WebSocket clients, and translates WebSocket requests into Pi RPC commands. That's it.
Agent-First Architecture
The system that builds the thing should shape the thing.
This codebase is maintained by AI coding agents, not humans with IDEs. Every structural decision optimizes for how agents work: tool calls to read files, exact-text edits to change them, and context windows to reason about them.
Deep Modules Over Small Files
Humans navigate with Cmd+P and jump-to-definition — file granularity is free. Agents navigate with tool calls — every file read costs time, every cross-file edit is a failure point. So we use deep modules: fewer files, richer interfaces, self-contained units.
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.
- 4d ago First seen · 274 lines · 3,749 tokens per session scan A 794e5970d7ff
pibun CLAUDE.md is an instructions file published in the GitHub repository khairold/pibun (19 stars, last pushed 5mo ago), licensed MIT. It adds 3,749 tokens to every session, about $0.0187 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
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.