magpie: Instructions file for Codex

AGENTS.md

magpie AGENTS.md is an instructions file for Codex, OpenCode from magpie-lang/magpie. It costs 1,442 tokens per session, scanned A, original, MIT.

Repository instructions for Magpie, a Rust programming-language project with compiler, runtime, tooling, and code-generation components. They describe its workspace structure, build commands, tests, and development conventions.

In plain words
What is it for?
Use them when building Magpie, running workspace or targeted tests, inspecting the compiler pipeline, or changing one of its Rust crates.
Why use it?
They help an agent find the right crate and use the project’s expected Cargo commands, instead of guessing how the multi-part codebase works.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is magpie-lang/magpie's own configuration. It tells Codex and OpenCode how to work on magpie 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 magpie configures →

Reuse

Borrowing it

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

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 magpie AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/magpie-lang/magpie/agents-md"><img src="https://agentmods.dev/badge/instructions/magpie-lang/magpie/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,442 This file is loaded in full into every session.
When invoked 1,442 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 $0.01442 $0.01442
Opus 5.5 $0.00577 $0.00577
Sonnet 5.5 $0.00288 $0.00288
Haiku 4.5 $0.00144 $0.00144

Measured 2mo ago against content hash a7e7e37b4b5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

magpie 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 2mo 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

Magpie is a Rust workspace (Cargo.toml at repo root) with compiler/tooling crates in crates/. Core flow is split across frontend crates (magpie_lex, magpie_parse, magpie_ast), analysis crates (magpie_sema, magpie_hir, magpie_types, magpie_own), and backend crates (magpie_mpir, magpie_arc, magpie_codegen_llvm, magpie_codegen_wasm). CLI entrypoint is crates/magpie_cli/src/main.rs.
Pipeline orchestration is centered in magpie_driver; runtime and platform/tooling crates (for example magpie_rt, magpie_pkg, magpie_memory, magpie_web, magpie_gpu) are also workspace-critical. Use root Cargo.toml workspace members as the source of truth for full crate inventory.
Language fixtures live in tests/fixtures/*.mp, integration tests in tests/integration_test.rs, and standard library modules in std/std.*/*.mp.

Build, Test, and Development Commands

Use Cargo from repo root:

cargo build -p magpie_cli              # build CLI
cargo build --workspace                # build all crates
cargo run -p magpie_cli -- --help      # inspect CLI
cargo test --workspace                 # full test suite
cargo test --test integration_test     # fixture-driven integration tests
cargo test -p magpie_parse snapshot_hello_parser_output

For CLI usage, global flags must come before subcommands:

cargo run -p magpie_cli -- --entry tests/fixtures/hello.mp --emit mpir,llvm-ir build

Toolchain notes (important for backend/link workflows):

  • lli is needed for common magpie run LLVM-IR execution flow.
  • clang (and often llc) is needed for --emit exe / native linking.
  • Missing native tools usually surface as link diagnostics such as MPLINK01 / MPLINK02.
  • In --llm mode, builds may auto-run formatting unless --no-auto-fmt; expect possible source rewrites when this mode is enabled.

CLI path resolution pitfall:

  • --entry is resolved relative to the current working directory (CWD), not always the repo root.
  • If a command fails to find sources, check CWD first before changing code.

Read the full file on GitHub · 93 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. 2mo ago First seen · 93 lines · 1,442 tokens per session scan A a7e7e37b4b5b

Subscribe to this mod's changes

magpie AGENTS.md is an instructions file published in the GitHub repository magpie-lang/magpie (60 stars, last pushed 8mo ago), licensed MIT. It adds 1,442 tokens to every session, about $0.0058 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 2026-08-30.

Related

magpie AGENTS.md compared with instructions from other repositories

magpie AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
magpie AGENTS.mdmagpie-lang/magpieInstructions file608mo agoMITA1,442Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode