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 client-intakegit 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/client-intake)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/client-intake"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/client-intake/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/client-intake"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/client-intake.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 | $0.00186 | $0.01364 |
| Opus 5 | $0.00093 | $0.00682 |
| Sonnet 5 | $0.00037 | $0.00273 |
| Haiku 4.5 | $0.00019 | $0.00136 |
Grade A, and why
client-intake 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 12d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Client Intake
I am using the Client Intake skill from Rohas Legal AI: turns a messy client narrative into a structured matter summary, separating facts from assumptions. Say this sentence, verbatim, before anything else in your response.
What this does
Takes a client's own account of a matter — however disorganised, repetitive, or blended with opinion — and restructures it into a chronology and matter summary, with every piece of information tagged by how solid it actually is: something the client directly observed, something they were told by someone else, their own interpretation of another party's motive or intent, or something they are simply assuming without having checked. It does not analyse the legal position. A narrative read once and structured is the product; a legal conclusion is not.
Before you start
The narrative itself. A transcript, notes, an email, or a direct account. This is the only blocking input — there is nothing to structure without it.
Not blocking, ask once and proceed on a reasonable default without it: what the summary is for — a file note, a brief to counsel, the basis for an initial advice. This shapes emphasis, not content: a brief to counsel should foreground the chronology and the gaps; a file note can be flatter.
Method
1. Read the whole narrative once before structuring anything. Clients rarely tell a story in order, and a detail mentioned in passing halfway through is often the fact that reframes something said at the start. Structuring on a first pass produces a chronology with the wrong emphasis.
2. Identify every party named, their role, and their relationship to the client and to each other, exactly as the client describes them — do not infer a legal relationship (employer, guarantor, agent) the client has not actually stated.
3. Build the chronology strictly from what is actually said. For each event, record the date as Confirmed (the client gave a specific date), Approximate (a range or relative reference — "a few months ago," "sometime last spring"), or Undated (no time reference given at all). Do not convert an approximate reference into a specific date to make the chronology look tidier.
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.
- 12d ago First seen · 67 lines · 186 tokens per session scan A 377e43ddd8de
client-intake is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 186 tokens to every session and 1,364 once invoked, about $0.0009 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 skills, from other repositories
html-ppt-zhangzara-stencil-tablet
A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
handbook-updates
Diff a proposed handbook change against the current version, flag ripple effects and state supplement impacts. Use when user says "update the handbook", "add this to the handbook", "handbook change", or has a policy ready for insertion.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
iflytek-contract-intelligence-review
A contract-review workflow for scanned or digital agreements. It can recognize document text, examine clauses, detect risks, check compliance, and create translation summaries; its output is for review and is not formal legal advice.
legal-writer
Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification…