Borrowing it
Nothing to install: this file belongs to zosmaai/pi-llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zosmaai/pi-llm-wiki/main/AGENTS.mdgit clone --depth 1 https://github.com/zosmaai/pi-llm-wikiWrote 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/zosmaai/pi-llm-wiki/agents-md)<a href="https://agentmods.dev/instructions/zosmaai/pi-llm-wiki/agents-md"><img src="https://agentmods.dev/badge/instructions/zosmaai/pi-llm-wiki/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 | $0.00594 | $0.00594 |
| Opus 5 | $0.00297 | $0.00297 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
pi-llm-wiki 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 6d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI agents working on this codebase.
Project
@zosmaai/pi-llm-wiki — A package that implements Andrej Karpathy's LLM Wiki pattern as a self-maintaining knowledge base. It loads under two hosts: pi (@mariozechner/pi-coding-agent) and oh-my-pi (omp).
Tech Stack
- TypeScript (ES2022, ESM)
- Vitest for testing
- Biome for linting/formatting
- GitHub Actions for CI
- npm for publishing
File Layout
├── extensions/llm-wiki/ # TypeScript extension (14 tools + 3 opt-in trajectory tools + guardrails)
│ ├── index.ts # Entry point
│ └── lib/ # tools.ts, metadata.ts, guardrails.ts, utils.ts, source-packet.ts, host.ts
├── skills/llm-wiki/ # SKILL.md + templates
├── prompts/ # slash command templates (source of truth; pi reads these)
├── commands/ # generated mirror of prompts/ (oh-my-pi reads these) — do not hand-edit
├── test/ # Vitest tests
├── docs/ # Documentation
└── scripts/ # release.js, build-mcp.js, build-commands.js
Conventions
- Use
node:fs/promisesfor async file I/O, not sync - Prefer small, pure functions in
lib/ - Extension tools must have: name, label, description, promptSnippet, promptGuidelines, parameters (TypeBox), execute
- Guardrails block
.llm-wiki/raw/**and.llm-wiki/meta/**edits at the tool_call hook level - Metadata auto-rebuilds on
turn_endafter.llm-wiki/wiki/**edits - Source IDs:
SRC-YYYY-MM-DD-NNN - Page filenames:
kebab-case.md - Wikilinks: folder-qualified, e.g.
[[concepts/retrieval-augmented-generation]] - Never resolve
.pi/.ompconfig paths by hand — go throughlib/host.ts - After editing anything in
prompts/, runpnpm build:commands(a test enforces parity)
Testing
pnpm test # run tests
pnpm test:coverage # run with coverage
pnpm typecheck # TypeScript check
pnpm lint # biome check
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.
- 6d ago First seen · 61 lines · 594 tokens per session scan A e0f84e13e0e6
pi-llm-wiki AGENTS.md is an instructions file published in the GitHub repository zosmaai/pi-llm-wiki (558 stars, last pushed yesterday), licensed MIT. It adds 594 tokens to every session, about $0.0030 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
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).
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).
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.
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.