pure-borrow: Instructions file for Claude Code

AGENTS.md

pure-borrow AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from SoftwareFoundationGroupAtKyotoU/pure-borrow. It costs 7,023 tokens per session, scanned A, original, BSD-3-Clause.

An AGENTS.md instruction file for the pure-borrow Haskell library, including its language requirements, commands, tests, and design constraints. The library implements Rust-like ownership and memory-safety ideas in Linear Haskell.

In plain words
What is it for?
Use it when developing, testing, benchmarking, or reviewing changes to pure-borrow and its Haskell code.
Why use it?
It gives coding agents the repository's source of truth before they modify a released, paper-backed library. It highlights compatibility and soundness rules that changes must preserve unless deliberately changed.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PostToolUse hook event, but also the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is SoftwareFoundationGroupAtKyotoU/pure-borrow's own configuration. It tells Claude Code, Codex and OpenCode how to work on pure-borrow 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 pure-borrow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SoftwareFoundationGroupAtKyotoU/pure-borrow. 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/SoftwareFoundationGroupAtKyotoU/pure-borrow/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/SoftwareFoundationGroupAtKyotoU/pure-borrow

Made for: Claude Code, 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 pure-borrow AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/softwarefoundationgroupatkyotou/pure-borrow/agents-md/github.svg)](https://agentmods.dev/instructions/softwarefoundationgroupatkyotou/pure-borrow/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/softwarefoundationgroupatkyotou/pure-borrow/agents-md"><img src="https://agentmods.dev/badge/instructions/softwarefoundationgroupatkyotou/pure-borrow/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 pure-borrow AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/softwarefoundationgroupatkyotou/pure-borrow/agents-md"><img src="https://agentmods.dev/badge/instructions/softwarefoundationgroupatkyotou/pure-borrow/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,023 This file is loaded in full into every session.
When invoked 7,023 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.07023 $0.07023
Opus 5.5 $0.02809 $0.02809
Sonnet 5.5 $0.01405 $0.01405
Haiku 4.5 $0.00702 $0.00702

Measured 1mo ago against content hash cf79fcff0962, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pure-borrow 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 1mo 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.

AGENTS.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the source of truth for coding-agent guidance in this repository. Keep agent-agnostic project instructions here, and keep tool-specific files as thin adapters. CLAUDE.md is intentionally a symlink to this file so Claude Code and Codex read the same repository policy.

Overview

pure-borrow realizes Rust-style borrowing in Linear Haskell, purely — compile-time ownership and memory safety with no runtime overhead, plus safe deterministic parallelism. It is the artifact of the paper Pure Borrow: Linear Haskell Meets Rust-Style Borrowing (Y. Matsushita & H. Ishii, PLDI 2026; arXiv:2604.15290). The package is already released on Hackage (latest release 0.1.0.0); current work is incremental improvement (notably performance) of a published, paper-backed library — so preserve the public API and the soundness invariants unless a change is deliberate.

Control.Monad.Borrow.Pure is the umbrella module and carries the full Haddock tutorial; read it before designing changes to the core.

Language & toolchain

  • GHC 9.10.2+ required (Linear Types); 9.12.4+ recommended — pinned locally to ghc-9.12.4 via cabal.project.local. tested-with: 9.10.3 || 9.12.4 || 9.14.1.
  • default-language: GHC2021, with LinearTypes enabled by default everywhere.
  • Interpreter caveat: GHC < 9.12.3 segfaults evaluating some linear programs in GHCi / the HLS eval plugin (a compiler bug). Compiled code is fine on 9.10.2+. Use 9.12.3+ if you need the REPL. The pure-borrow-doctests suite is disabled for GHC < 9.12.3.
  • Cabal nix-style builds only; cabal.project (+ cabal.project.local) is the source of truth. Do not use stack or invoke ghc directly. cabal-install ≥ 3.14.2 recommended.

Build / test / bench / run

cabal.project sets the +examples flag and cabal.project.local enables tests+benchmarks, so locally every component below is buildable.

cabal build all                       # build the library + all enabled components
cabal build pure-borrow               # just the library

cabal test                            # run all test suites
cabal test pure-borrow-test           # main tasty suite only
cabal test pure-borrow-doctests       # doctests (needs GHC >= 9.12.3)

cabal bench qsort-bench               # parallel quicksort benchmark (tasty-bench)
cabal bench fft-bench                 # parallel FFT benchmark (tasty-bench)
cabal bench pure-borrow-bench         # all single-threaded micro-benchmarks (needs -j1)

cabal run qsort -- --help             # quicksort demo executable (needs +examples)
cabal run fft   -- --help             # FFT demo executable (needs +examples)

Read the full file on GitHub · 311 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. 1mo ago Changed · +1 lines · +80 tokens per session cf79fcff0962
  2. 1mo ago Changed · +10 lines · +390 tokens per session c51416094a46
  3. 1mo ago First seen · 300 lines · 6,553 tokens per session scan A e88314e8d561

Subscribe to this mod's changes

pure-borrow AGENTS.md is an instructions file published in the GitHub repository SoftwareFoundationGroupAtKyotoU/pure-borrow (63 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 7,023 tokens to every session, about $0.0281 per session on Opus 5.5. 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 2026-10-02.

Related

pure-borrow AGENTS.md compared with instructions from other repositories

pure-borrow AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pure-borrow AGENTS.mdSoftwareFoundationGroupAtKyotoU/pure-borrowInstructions file631mo agoBSD-3-ClauseA7,023Claude Code, Codex, 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