arcaneum AGENTS.md

arcaneum AGENTS.md is an instructions file for Codex, OpenCode from cwensel/arcaneum. It costs 484 tokens per session, scanned A, original, MIT.

Project instructions for Arcaneum, including its required Conventional Commits format. Conventional Commits use labels such as feature, fix, test, or documentation so changes can be sorted in release notes.

In plain words
What is it for?
Use them when creating commits for Arcaneum, especially when choosing the change type, affected area, description, or breaking-change notation.
Why use it?
They keep commit messages consistent and make automated release notes easier to generate.

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/cwensel/arcaneum/agents-md
Clone the repo
git clone --depth 1 https://github.com/cwensel/arcaneum

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 arcaneum AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cwensel/arcaneum/agents-md.svg)](https://agentmods.dev/instructions/cwensel/arcaneum/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cwensel/arcaneum/agents-md"><img src="https://agentmods.dev/badge/instructions/cwensel/arcaneum/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 484 This file is loaded in full into every session.
When invoked 484 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 $0.00484 $0.00484
Opus 5 $0.00242 $0.00242
Sonnet 5 $0.00097 $0.00097
Haiku 4.5 $0.00048 $0.00048

Measured 3d ago against content hash 5520a61788c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arcaneum 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 · 62 lines

What it actually says

AGENTS.md

This file provides guidance for AI agents working with this repository.

Commit Message Convention

This project follows Conventional Commits. Release notes are generated by grouping commits by type, so non-conforming messages land in a generic "Other" section.

Format

<type>(<scope>): <description>

[optional body]

[optional footer]
  • type (required, lowercase): one of the types below
  • scope (optional): area affected, e.g. search, cli, ci, indexing
  • description (required): imperative mood, no trailing period
  • breaking change: add ! after type/scope (e.g. feat(cli)!: ...) or a BREAKING CHANGE: footer

Types

Type Use for
feat New feature visible to users
fix Bug fix
perf Performance improvement (no behavior change)
refactor Code change that's neither a fix nor a feature
docs Documentation only
test Adding or updating tests
build Build system or dependencies (pyproject.toml, packaging)
ci CI/CD workflows (.github/workflows/)
chore Maintenance, tooling, release commits
style Formatting (no code change)
revert Reverts a previous commit

Examples

feat(search): add --limit flag to arc search semantic
fix(cli): handle empty corpus argument
ci: pin third-party actions to commit SHAs
docs(readme): update install instructions
chore(release): 0.4.2
refactor(indexing)!: rename BatchIndexer to ChunkIndexer

Rules

  • ✅ Use the convention for all commits on main
  • ✅ Release commits are chore(release): X.Y.Z
  • ✅ Use ! or BREAKING CHANGE: footer for breaking changes — these surface at the top of release notes
  • ❌ Do NOT capitalize the description
  • ❌ Do NOT end the description with a period
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 · 62 lines · 484 tokens per session scan A 5520a61788c7

Subscribe to this mod's changes

arcaneum AGENTS.md is an instructions file published in the GitHub repository cwensel/arcaneum (7 stars, last pushed 8d ago), licensed MIT. It adds 484 tokens to every session, about $0.0024 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.