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/minmax/pi-cli-mcp/agents-mdgit clone --depth 1 https://github.com/minmax/pi-cli-mcpWhat 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 | $0.00457 | $0.00457 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
pi-cli-mcp 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 yesterday.
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.
What it actually says
AGENTS.md
For agents working on this repository. What the server does is in README.md; how to
release, validate, test, or touch pi's contract is in
.agents/skills/README.md — read the relevant skill first.
House rules
This is an adapter. It carries pi's capabilities across MCP and adds none of its own. No automatic messages, no injected instructions, no git or filesystem logic layered on top. If a behaviour would surprise someone reading pi's own docs, it does not belong here.
Zero runtime dependencies. pi's packages are devDependencies reached only through import type.
Adding a runtime import is a design change, not a convenience.
Borrow pi's shapes, never copy them. Alias its types so a change upstream breaks the build instead of the answer.
Fail closed on anything from pi. An unknown stopReason, a missing field, an unparseable
stream — report it. Never normalize the unrecognized into success.
The answer is the contract. Return pi's settled answer and aggregate stats. Never the transcript, tool arguments, or raw stdout: they carry prompts and say nothing a caller can act on.
Strict in the base, guards on top. Correctness comes from the protocol, not from pattern matching. Anything defensive is a separate, switchable layer — and if it parses, it uses the parse rather than throwing it away for a boolean.
No process outlives its request. Every path — timeout, cancellation, shutdown, clean exit — leaves nothing behind.
Tests drive the real server. The fake is pi, never our own code. Wait for conditions; a fixed sleep before an assertion is a flake with a delay on it.
Check the artifact, not the number. A version, a green tick and a tag can all agree while the published bytes differ. Unpack it, run it.
Fix it, do not note it. A violated rule found in passing gets fixed in the same change, whatever introduced it. And do not commit or push unless asked.
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.
- yesterday First seen · 40 lines · 457 tokens per session scan A 372bfd79c087
pi-cli-mcp AGENTS.md is an instructions file published in the GitHub repository minmax/pi-cli-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 457 tokens to every session, about $0.0023 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.
buildNext
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).
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.
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).
spec-kit 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
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.