aru AGENTS.md

aru AGENTS.md is an instructions file for Codex, OpenCode from narumiruna/aru. It costs 1,055 tokens per session, scanned A, original, MIT.

Repository instructions for the aru project, covering where rules apply, how to communicate, how to document decisions, and how to style code. They also define limits on actions such as publishing or pushing changes.

In plain words
What is it for?
Use them when working anywhere in the aru repository, especially before planning, coding, documenting, or running project checks.
Why use it?
They give an AI coding agent clear boundaries and project conventions before it edits anything. This helps keep changes focused and avoids unauthorized release or repository operations.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/narumiruna/aru/agents-md
Clone the repo
git clone --depth 1 https://github.com/narumiruna/aru

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 aru AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/narumiruna/aru/agents-md.svg)](https://agentmods.dev/instructions/narumiruna/aru/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/narumiruna/aru/agents-md"><img src="https://agentmods.dev/badge/instructions/narumiruna/aru/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,055 This file is loaded in full into every session.
When invoked 1,055 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01055 $0.01055
Opus 5 $0.00528 $0.00528
Sonnet 5 $0.00211 $0.00211
Haiku 4.5 $0.00105 $0.00105

Measured 3d ago against content hash 0642111df1ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aru 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 3d 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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidance

Scope and Authority

This file applies to the entire repository. Add a nested AGENTS.md only when a subtree has materially different rules.

For explanation, review, diagnosis, or planning requests, inspect and report without changing files. For requested implementation or documentation work, make bounded local changes and run proportionate non-destructive checks. Do not push, open or merge pull requests, create tags, dispatch workflows, publish releases, use aru's destructive --force takeover, or materially expand scope unless explicitly requested.

Communication & Documentation

  • Lead with the most important relevant information and omit anything unnecessary or repeated.
  • Use clear structure, familiar words, and concise sentences.
  • Explain the main idea simply before adding necessary detail.
  • Keep information accurate.
  • Make documented rules specific and verifiable.
  • In documentation, put each prose sentence on its own source line.
  • Draw diagrams using Mermaid syntax.

Code Style

  • Follow KISS (Keep It Simple) and YAGNI (You Aren't Gonna Need It).
  • Prefer simple, minimal solutions over unnecessary complexity.
  • Split source files over 1,000 lines along clear responsibility boundaries, or document why they must remain intact.

Project Map

  • src/cli.rs defines the Clap command contract.
  • src/app.rs and src/app/ orchestrate commands.
  • src/manifest.rs and src/lockfile.rs own persisted formats.
  • src/resolver.rs, src/registry.rs, and src/source/ resolve package inputs.
  • src/target/ owns target-specific projections.
  • Keep target capability differences in src/target/ instead of scattering target checks through orchestration code.
  • src/instruction/, src/skill.rs, and src/sync.rs implement discovery and reconciliation.
  • src/ownership.rs and src/transaction.rs protect user content and atomic multi-file updates.
  • tests/*.rs exercise the public CLI.
  • tests/fixtures/contracts/ contains byte-stable format fixtures.
  • Registry and instruction fixtures live under their corresponding fixture directories.

Read the full file on GitHub · 94 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. 3d ago First seen · 94 lines · 1,055 tokens per session scan A 0642111df1ee

Subscribe to this mod's changes

aru AGENTS.md is an instructions file published in the GitHub repository narumiruna/aru (5 stars, last pushed 10d ago), licensed MIT. It adds 1,055 tokens to every session, about $0.0053 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.