Borrowing it
Nothing to install: this file belongs to s0fractal/warrant. 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/s0fractal/warrant/master/AGENTS.mdgit clone --depth 1 https://github.com/s0fractal/warrantWrote 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/s0fractal/warrant/agents-md)<a href="https://agentmods.dev/instructions/s0fractal/warrant/agents-md"><img src="https://agentmods.dev/badge/instructions/s0fractal/warrant/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/s0fractal/warrant/agents-md"><img src="https://agentmods.dev/badge/instructions/s0fractal/warrant/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 | $0.00786 | $0.00786 |
| Opus 5.5 | $0.00314 | $0.00314 |
| Sonnet 5.5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
warrant 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents and contributors
This repository keeps work as signed records; its git history and commit trailers are provenance too. The rules below protect that provenance.
Read first: docs/AGENT.md (the agent interface and its configuration), docs/V3.md (the specification) and docs/REPOSITORY.md (this repository's records, tools, review loop and merge gate).
Hard rules
-
Never commit to
master. Work on a branch and open a pull request.masteradvances only by a merge: the owner's, or the merge gate's (tools/gate.py) when the review loop accepted the pull request (docs/V3.md §14). A pull request that changes an owner path is merged by the owner. -
Never claim review authority you do not hold. A trailer such as
Reviewed-by: Xor a sentence saying "independently reviewed" is false provenance unless X filed that review. A review is a record signed by its reviewer: anattestor afinding@1challenge by apr/acceptoron the head version. Sign only as your own actor, with your own key; never as another actor or as a checker (claims-checker,review-replayer), whose seeds only the owner and the waker hold. -
An independent review hunts for counterexamples. Green suites are necessary, not sufficient: every real review of this project found defects the suites did not cover. Running the suites is not a review.
-
Record provenance honestly. Say exactly what was checked (which suites, which mutants, which reviewer) and what was not. Do not upgrade "the suites are green" into "reviewed", or "filed" into "accepted".
-
A counterexample is recorded, not staged as red CI. The test and the fix land in the same change, and CI stays green. The regression case names the defect it catches; the commit message names the commit it was observed on, what was observed and what was expected. Show that a new check can fail by a mutant in
tests/mutants.pythat fails its own case. A change to a rule of docs/V3.md files the claim's new version (docs/REPOSITORY.md); earlier records are never rewritten.
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.
- 7d ago Changed · +4 lines · +97 tokens per session 988f9817698d
- 9d ago Changed · +5 tokens per session 6cc13196bb36
- 12d ago Changed · -52 lines · -699 tokens per session 3031df5ce024
- 21d ago Changed · +2 lines · +80 tokens per session 3bdcbb3a650d
- 22d ago Changed · +36 lines · +516 tokens per session 1c8f8781ab75
- 23d ago Changed · +11 lines · +179 tokens per session 912e5fda6afb
- 2mo ago Changed · -62 lines · -957 tokens per session c5ef626ca0cd
- 2mo ago First seen · 110 lines · 1,565 tokens per session scan A 90de25ea8eed
warrant AGENTS.md is an instructions file published in the GitHub repository s0fractal/warrant (5 stars, last pushed 2d ago), licensed MIT. It adds 786 tokens to every session, about $0.0031 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 2026-08-31.
warrant AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| warrant AGENTS.mds0fractal/warrant | Instructions file | 5 | 2d ago | MIT | A | 786 | 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 | 5,649 | 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 |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |