Borrowing it
Nothing to install: this file belongs to bradheitmann/mister-clean. 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/bradheitmann/mister-clean/main/AGENTS.mdgit clone --depth 1 https://github.com/bradheitmann/mister-cleanWrote 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/bradheitmann/mister-clean/agents-md)<a href="https://agentmods.dev/instructions/bradheitmann/mister-clean/agents-md"><img src="https://agentmods.dev/badge/instructions/bradheitmann/mister-clean/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/bradheitmann/mister-clean/agents-md"><img src="https://agentmods.dev/badge/instructions/bradheitmann/mister-clean/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 | $0.00417 | $0.00417 |
| Opus 5.5 | $0.00167 | $0.00167 |
| Sonnet 5.5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
mister-clean 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 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.
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.
What it actually says
Charter (binding for every agent, every harness)
- Before designing, dispatching, or claiming anything done, read
charter/in this repo: INTENT.md, GUARANTEES.yaml, LOOPS.yaml, STOP-RULES.md, DONE/.md, STATE.md. If any is missing or stale, your first task is to produce it with the owner; do not proceed past it. - Done means every proof in
charter/DONE/<slice>.mdexecuted and its run reopened and compared. It never means "no findings". New findings become recorded obligations on the next bounded slice unless they break a guarantee listed in GUARANTEES.yaml. - The stop rules in
charter/STOP-RULES.mdbind you. You may not relax them. A change to them exists only ascharter/owner-decisions/<date>-<slug>.md. - Every guarantee you add gets an owner, a proof and a cost. Every loop you add gets a bound, a cost per trip and a stop condition. No exceptions for "small".
- Nothing scales before
charter.toml [slice_zero]hasproven_onset from a real run. - Before you stop, hand off, or approach a context limit: rewrite
charter/STATE.md(proven, not proven, exact last-green and last-red commands, next three bounded items, open owner decisions). No decision may live only in a pane or transcript. - Run
charter check(orhooks/charter-check.sh) before any commit or "ready" claim. Rust only; no Python.
Engineering standard
This repository follows COMMON-STANDARD.md. How each section maps to this repository's gates, and the open gaps, are in charter/STANDARD-ADOPTION.md.
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.
- 6d ago First seen · 14 lines · 417 tokens per session scan A 0d4bbf571876
mister-clean AGENTS.md is an instructions file published in the GitHub repository bradheitmann/mister-clean (0 stars, last pushed yesterday), licensed MIT. It adds 417 tokens to every session, about $0.0017 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 2026-11-01.
mister-clean AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mister-clean AGENTS.mdbradheitmann/mister-clean | Instructions file | 0 | yesterday | MIT | A | 417 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |