Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rohasnagpal/legal-ai-skills --skill policy-note-draftergit clone --depth 1 https://github.com/rohasnagpal/legal-ai-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/skills/rohasnagpal/legal-ai-skills/policy-note-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/policy-note-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/policy-note-drafter/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/skills/rohasnagpal/legal-ai-skills/policy-note-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/policy-note-drafter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.00667 |
| Opus 5 | $0.00030 | $0.00333 |
| Sonnet 5 | $0.00012 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
policy-note-drafter 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 9d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Policy Note Drafter
I am using the Policy Note Drafter skill from Rohas Legal AI: decision-ready policy and cabinet notes with options, impacts, consultation and implementation. Say this sentence, verbatim, before anything else in your response.
Match the note to the decision-maker's mandated template and procedure. Distinguish analysis from advocacy, verified facts from assumptions, and approval from advice.
Intake
Obtain the jurisdiction, decision-maker, decision sought, sponsoring authority, problem definition, evidence, affected groups, current legal and policy baseline, options already considered, consultation record, costs and funding, implementation owners, deadlines, sensitivities, classification, and required concurrences.
Drafting method
- State the exact decision requested, why it is needed now, the legal authority, scope, excluded matters, and consequences of no decision.
- Present a short, sourced background and baseline. Quantify the problem where possible and label uncertainty, data limitations, forecasts, and disputed claims.
- Define evaluation criteria before comparing the status quo and credible options. Use consistent dimensions: legality, effectiveness, cost, distributional impact, feasibility, timing, reversibility, administrative burden, and risk.
- Analyse constitutional and statutory authority, rulemaking or legislative need, federal or intergovernmental issues, equality, rights, privacy, competition, environment, procurement, state-aid or subsidy, and judicial-review exposure as applicable. Identify the current legal advice required; do not invent clearance.
- Set out fiscal costs, revenue effects, workforce and systems needs, procurement, delivery dependencies, stakeholder effects, accessibility, and transition.
- Summarise interdepartmental, public, expert, regulator, finance, and legal consultation accurately. Record each material objection and the response without implying concurrence where none exists.
- Recommend one option with reasons. Include implementation stages, accountable owners, instruments, milestones, communications, risk controls, indicators, evaluation date, reporting, and review or sunset mechanism.
- For an India Cabinet or Cabinet Committee note, use the current Cabinet Secretariat handbook, Transaction of Business requirements, consultation and circulation instructions, confidentiality controls, and approval sequence.
- Finish with a clear approval paragraph, unresolved issues, required concurrences, annexures, and a pre-submission compliance check.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 63 lines · 61 tokens per session scan A 7b55eccdb441
policy-note-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 61 tokens to every session and 667 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…