Borrowing it
Nothing to install: this file belongs to pa1nrui1/legal-skills. 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/pa1nrui1/legal-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/pa1nrui1/legal-skillsWrote 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/pa1nrui1/legal-skills/agents-md)<a href="https://agentmods.dev/instructions/pa1nrui1/legal-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/pa1nrui1/legal-skills/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/pa1nrui1/legal-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/pa1nrui1/legal-skills/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 | $0.00635 | $0.00635 |
| Opus 5 | $0.00318 | $0.00318 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
legal-skills 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 13d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
Legal Formal Deliverable Hard Gate
When a legal task involves a document, report, memo, case compilation, pleading, evidence list, legal opinion, client-facing material, court-facing material, or any .docx output, classify the deliverable before writing substantive content:
工作草稿: internal draft only; may be Markdown; must be named with草稿or未出稿审查if not reviewed.律师内部报告: internal strategy analysis; may include risk assessment and litigation suggestions; must still include source boundary, reading review, and legal verification when it cites materials, cases, or law.提交法院/客户的正式材料: court-facing or client-facing; must follow the applicable legal Skill template, stay clean and professional, and include required source boundary records.Word正式交付物: any formal.docx; must pass the full legal export chain before being called final or formal.
For every legal .docx or formal legal deliverable, stop and verify these gate items before export:
- Current matter matches
【自定义工作目录】/_系统记录/当前事项.md; if it does not, switch/build the matter first or ask before continuing. - The correct legal Skill has been selected, including whether the output is a 法官版、律师版、诉讼文书、证据目录、法律意见 or other type.
- Before writing substantive content, the corresponding legal template/reference file has been identified and recorded, with its key format requirements stated. After generation, run a reverse structure check against that template. For
证据目录, the controlling template is诉讼文书起草/templates/证据目录格式.md; it must use grouped textual paragraphs with第一组证据and证明目的, and must not be output as a table unless the user expressly overrides this template. - All cited case/material files have a
读取复查摘要. - All cited statutes, regulations, judicial interpretations, or current legal rules have a
法规校验摘要. - A
来源边界记录exists and states verified, unverified, and output boundaries. - Any user choice that changes scope, version, strategy, amount, claim, authorization, or whether to include/exclude negative cases is recorded in
用户确认记录. - Formal Word output has
draft.html,preflight-meta.json,draft_checked.html,出稿前审查报告.md, and the report status isPASSorFIXED_PASS. - Formal Word output is generated only through
法律文书模板与导出(html_to_docx.py) and passeshealth_check.py.
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.
- 13d ago First seen · 25 lines · 635 tokens per session scan A 7b7841e1a8ed
legal-skills AGENTS.md is an instructions file published in the GitHub repository pa1nrui1/legal-skills (85 stars, last pushed 2mo ago), licensed MIT. It adds 635 tokens to every session, about $0.0032 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 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).