lean-beam: Instructions file for Codex

AGENTS.md

lean-beam AGENTS.md is an instructions file for Codex, OpenCode from leanprover/lean-beam. It costs 1,901 tokens per session, scanned C, original, Apache-2.0.

Instructions for a pre-release Lean plugin, wrapper, and local broker. Lean is a programming language and proof assistant used to write code and verify mathematical proofs.

In plain words
What is it for?
Use them when changing the Beam plugin, its request handling, backend connection, synchronization, diagnostics, or public API.
Why use it?
They set priorities and API limits that help agents make small, stable, type-safe changes without exposing unnecessary internal details.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is leanprover/lean-beam's own configuration. It tells Codex and OpenCode how to work on lean-beam itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lean-beam configures →

Reuse

Borrowing it

Nothing to install: this file belongs to leanprover/lean-beam. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/leanprover/lean-beam/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/leanprover/lean-beam

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for lean-beam AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/leanprover/lean-beam/agents-md/github.svg)](https://agentmods.dev/instructions/leanprover/lean-beam/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/leanprover/lean-beam/agents-md"><img src="https://agentmods.dev/badge/instructions/leanprover/lean-beam/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lean-beam AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/leanprover/lean-beam/agents-md"><img src="https://agentmods.dev/badge/instructions/leanprover/lean-beam/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,901 This file is loaded in full into every session.
When invoked 1,901 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01901 $0.01901
Opus 5.5 $0.00760 $0.00760
Sonnet 5.5 $0.00380 $0.00380
Haiku 4.5 $0.00190 $0.00190

Measured 14d ago against content hash fc42fc2e28dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

lean-beam AGENTS.md scanned grade C with 1 finding 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 14d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`rm -rf` against repo-local `.beam`, install caches, or user homes as part of normal workflows
AGENTS.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Purpose

This repository hosts the pre-stable Beam Lean plugin, wrapper, and local broker tooling.

Treat the repo as public but still experimental: prefer conservative, well-tested changes over feature sprawl.

Current public status and limitations live in docs/STATUS.md. Compatibility policy lives in docs/COMPATIBILITY.md. User setup lives in docs/SETUP.md. Exact MCP behavior lives in docs/MCP.md, and exact sync/save/diagnostic behavior lives in docs/SYNC_AND_DIAGNOSTICS.md.

Product Priorities

In order:

  1. dead-simple public API
  2. rock-solid stability
  3. type-safe boundaries
  4. isolation of each request
  5. performance

Performance matters, but not at the cost of correctness or stability.

Public API Guardrails

The core public request should remain conceptually:

  • runAt(pos, "lean text")

Rules:

  • no required public mode flag for command vs tactic execution
  • backend selection is internal
  • keep request and response structures small and typed
  • use transport errors for invalid params, stale state, cancellation, and internal faults
  • avoid exposing internal execution details unless a concrete client need forces it

Follow-up handle APIs exist, but they are pre-stable extensions around the basic request, not the main story of the project.

Execution Model

Each request should behave like an isolated sandbox:

  • never mutate the document's real elaboration state
  • never depend on side effects from a previous request
  • never leak internal mutable state through the base API
  • discard derived execution state unless the request explicitly stores a follow-up handle

Cancellation Policy

Request cancellation is currently soft (cooperative) across Beam. Observe it at safe boundaries; do not promise immediate interruption, rollback, or a universal completion deadline. An active effect may need to settle before the request releases its resources or reports cancellation.

Read the full file on GitHub · 180 lines

Changes

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.

  1. 14d ago Changed · +15 lines · +159 tokens per session fc42fc2e28dd
  2. 15d ago Changed · +5 lines · +89 tokens per session 352150c1926e
  3. 20d ago Changed · +1 lines · +64 tokens per session 4f28051087c1
  4. 2mo ago Changed · -1 lines · -10 tokens per session 07cc3f4dc399
  5. 2mo ago First seen · 160 lines · 1,599 tokens per session scan C f0ef696ea68f

Subscribe to this mod's changes

lean-beam AGENTS.md is an instructions file published in the GitHub repository leanprover/lean-beam (45 stars, last pushed today), licensed Apache-2.0. It adds 1,901 tokens to every session, about $0.0076 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

lean-beam AGENTS.md compared with instructions from other repositories

lean-beam AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lean-beam AGENTS.mdleanprover/lean-beamInstructions file45todayApache-2.0C1,901Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode