aimebu: Instructions file for Codex

AGENTS.md

aimebu AGENTS.md is an instructions file for Codex, OpenCode from hrubymar10/aimebu. It costs 7,682 tokens per session, scanned C, original, MIT.

Repository instructions for aimebu, an AI message bus. They cover documentation, commit messages, testing, and supported coding-agent setups.

In plain words
What is it for?
Use them before changing aimebu to read the README and relevant documentation, update docs when behaviour changes, follow commit rules, and use the supported test harnesses.
Why use it?
They help keep code, documentation, commits, and tests consistent when changes are made to the repository.

Instructions file for CodexOpenCode

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

This is hrubymar10/aimebu's own configuration. It tells Codex and OpenCode how to work on aimebu 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 aimebu configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hrubymar10/aimebu. 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/hrubymar10/aimebu/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/hrubymar10/aimebu

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 aimebu AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hrubymar10/aimebu/agents-md.svg)](https://agentmods.dev/instructions/hrubymar10/aimebu/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hrubymar10/aimebu/agents-md"><img src="https://agentmods.dev/badge/instructions/hrubymar10/aimebu/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,682 This file is loaded in full into every session.
When invoked 7,682 The same file — it is already loaded in full.
Security scan C 1 finding. 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 5.1 $0.07682 $0.07682
Opus 5 $0.03841 $0.03841
Sonnet 5 $0.01536 $0.01536
Haiku 4.5 $0.00768 $0.00768

Measured 6d ago against content hash bb623912233e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

aimebu AGENTS.md scanned grade C with 1 finding 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 6d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

kill "$(cat /tmp/probe.pid)"; rm -rf "$AIMEBU_CONFIG_DIR"
AGENTS.md · 590 lines

How it starts

The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aimebu — AI Message Bus

Note: CLAUDE.md in this repo is a symlink to this file (AGENTS.md).

Documentation discipline

Before changing code, read the docs that touch it: README.md, this file, and everything under docs/ (currently docs/claude-code.md, docs/codex.md, docs/fleet.md, docs/github-copilot.md, docs/leaderboards.md, docs/memory.md, docs/mistral.md, docs/ollama-cloud.md, docs/pi.md, docs/retention.md, docs/sqlite.md, docs/switcher.md, docs/tls.md, docs/usages.md, and docs/vibe.md). When your change makes any of those drift from reality — flags, env vars, tool names, config snippets, behaviour descriptions — update the docs in the same commit. Don't ship code changes and "fix the docs later".

If while reading docs (or code) you spot something weird, wrong, or inconsistent that isn't part of your current task, ask the user before fixing it. A separate cleanup is usually welcome, but the user decides scope — don't silently widen the diff.

Commit messages

Use long-form commit messages for any non-trivial change. Title-only commits are not acceptable when the diff changes behavior, adds tests, updates docs, or otherwise needs rationale captured in history.

Rules:

  • Subject line in conventional-commit style where it fits, kept to roughly 50-72 characters.
  • Blank line after the subject.
  • Body wrapped at roughly 72 characters explaining the why: failure mode, design choice, tradeoff, or scope boundary that justified the change.
  • If the diff is substantive, record enough context in the body that a future reader can understand the change without reconstructing the whole discussion from chat logs.
  • Commit with plain git commit — never pass --author or set GIT_AUTHOR_*. The author must inherit the repo's configured identity so author == committer.

Read the full file on GitHub · 590 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. 6d ago First seen · 590 lines · 7,682 tokens per session scan C bb623912233e

Subscribe to this mod's changes

aimebu AGENTS.md is an instructions file published in the GitHub repository hrubymar10/aimebu (5 stars, last pushed 19d ago), licensed MIT. It adds 7,682 tokens to every session, about $0.0384 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.