decompose: Instructions file for Codex

AGENTS.md

decompose AGENTS.md is an instructions file for Codex, OpenCode from sciyoshi/decompose. It costs 1,664 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for the decompose project. It explains the Rust project's structure and the commands and coding rules contributors and coding agents should follow.

In plain words
What is it for?
Use it as guidance when changing source code, integration tests, configuration, documentation, or CI-related files in this repository.
Why use it?
It gives an agent the project-specific context needed to build, test, format, lint, and edit the right files consistently.

Instructions file for CodexOpenCode

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

This is sciyoshi/decompose's own configuration. It tells Codex and OpenCode how to work on decompose 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 decompose configures →

Reuse

Borrowing it

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

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 decompose AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sciyoshi/decompose/agents-md"><img src="https://agentmods.dev/badge/instructions/sciyoshi/decompose/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,664 This file is loaded in full into every session.
When invoked 1,664 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 $0.01664 $0.01664
Opus 5.5 $0.00666 $0.00666
Sonnet 5.5 $0.00333 $0.00333
Haiku 4.5 $0.00166 $0.00166

Measured yesterday against content hash 30869faa2ec7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

decompose 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.

AGENTS.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for agents (human or automated) contributing to decompose.

Project overview

decompose is a Rust process orchestrator for local development. See README.md for the pitch and CLAUDE.md for design notes.

Repo structure

src/
  main.rs      Entry point; calls run_cli()
  lib.rs       CLI command handlers, log streaming
  cli.rs       Clap argument definitions
  config.rs    YAML parsing, merging, .env loading, variable interpolation
  daemon.rs    Daemon lifecycle, supervisor loop, IPC handlers
  model.rs     Core types (ProcessStatus, HealthProbe, etc.)
  ipc.rs       Request/Response protocol, socket helpers
  output.rs    JSON/table output formatting
  paths.rs     XDG path management, instance ID generation

tests/         Integration tests (spawn the binary end-to-end)
examples/      Sample compose files
assets/        Logo and static assets
.github/       CI and release workflows
flake.nix      Nix dev shell + package

Build, test, lint

All commands are expected to pass locally and in CI:

cargo build --locked --all-targets
cargo test --locked --all-targets
cargo fmt --all -- --check
cargo clippy --locked --all-targets -- -D warnings
cargo doc --locked --no-deps

Use nix develop to get a toolchain-pinned shell if you prefer.

For book changes, run mdbook build docs/ (CI uses mdBook 0.5.4), then python3 scripts/check-docs.py after building the binary. The checker validates local HTML links and anchors, then runs the quickstart and migration examples extracted from docs/src, plus the documented multiple-file invocation. It needs Python 3, a POSIX shell, and permission to bind local sockets. It uses temporary HOME/XDG directories and unused ports, and shuts down its daemons on failure. Keep these selected examples runnable; the checker deliberately does not execute arbitrary shell blocks elsewhere in the book.

After changing Cargo.lock (including a package version bump), Cargo.toml, flake.lock, or the vendoring derivation, verify the Nix vendor hash:

Read the full file on GitHub · 156 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. yesterday First seen · 156 lines · 1,664 tokens per session scan A 30869faa2ec7

Subscribe to this mod's changes

decompose AGENTS.md is an instructions file published in the GitHub repository sciyoshi/decompose (7 stars, last pushed 12d ago), licensed Apache-2.0. It adds 1,664 tokens to every session, about $0.0067 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 2026-11-07.

Related

decompose AGENTS.md compared with instructions from other repositories

decompose AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
decompose AGENTS.mdsciyoshi/decomposeInstructions file712d agoApache-2.0A1,664Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot