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.
curl -O https://raw.githubusercontent.com/hrubymar10/aimebu/master/AGENTS.mdgit clone --depth 1 https://github.com/hrubymar10/aimebuWrote 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.
[](https://agentmods.dev/instructions/hrubymar10/aimebu/agents-md)<a href="https://agentmods.dev/instructions/hrubymar10/aimebu/agents-md"><img src="https://agentmods.dev/badge/instructions/hrubymar10/aimebu/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.
<a href="https://agentmods.dev/instructions/hrubymar10/aimebu/agents-md"><img src="https://agentmods.dev/badge/instructions/hrubymar10/aimebu/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.08003 | $0.08003 |
| Opus 5.5 | $0.03201 | $0.03201 |
| Sonnet 5.5 | $0.01601 | $0.01601 |
| Haiku 4.5 | $0.00800 | $0.00800 |
Grade C, and why
aimebu AGENTS.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
kill "$(cat /tmp/probe.pid)"; rm -rf "$AIMEBU_CONFIG_DIR" How it starts
The opening of the file, as written. The whole thing — 610 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aimebu — AI Message Bus
Note:
CLAUDE.mdin 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--authoror setGIT_AUTHOR_*. The author must inherit the repo's configured identity so author == committer.
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.
- 11d ago Changed · +11 lines · +181 tokens per session c54a10e95509
- 12d ago Changed · +8 lines · +116 tokens per session 8948f4b9ed49
- 16d ago Changed · +1 lines · +24 tokens per session 2cf7bdf057ee
- 1mo ago First seen · 590 lines · 7,682 tokens per session scan C bb623912233e
aimebu AGENTS.md is an instructions file published in the GitHub repository hrubymar10/aimebu (6 stars, last pushed 9d ago), licensed MIT. It adds 8,003 tokens to every session, about $0.0320 per session on Opus 5.5. 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.
Other instructions, from other repositories
skill-doctor github-automation.instructions.md
Instructions for evilstar2016/skill-doctor, covering github-automation, description, when to use and instructions.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).