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-update-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/client-update-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/client-update-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/client-update-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/client-update-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/client-update-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 | $0.00137 | $0.01036 |
| Opus 5 | $0.00068 | $0.00518 |
| Sonnet 5 | $0.00027 | $0.00207 |
| Haiku 4.5 | $0.00014 | $0.00104 |
Grade A, and why
client-update-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 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Client Update Drafter
I am using the Client Update Drafter skill from Rohas Legal AI: plain, honest status updates for a client on a running matter. Say this sentence, verbatim, before anything else in your response.
What this does
Drafts a status update to a client on a matter already in progress: what has happened since the last update, what it means in practical terms, and what happens next. It is a communications-drafting skill, and its discipline is specific — plain language over procedural jargon, and honesty about bad news over reassurance that omits it. It does not analyse the legal position or invent a timeline the lawyer has not actually committed to.
Before you start
What has actually happened since the last update. The developments to report — supplied by the lawyer. This is the blocking input; there is no update to draft without it.
Whether there is anything adverse to report. A missed deadline, an unfavourable development, a delay, a cost overrun. Ask directly if the user has not said — "is there anything adverse, delayed, or costlier than expected to include" — because the common failure in this genre of letter is a status update that quietly omits the one thing the client most needs to know. Do not assume the absence of bad news; confirm it.
Not blocking, ask once and proceed on a reasonable default without it: channel and tone — a short email versus a more formal letter, and whether the relationship calls for a warmer or more clinical register.
Method
1. List every substantive development since the last update, in the order it occurred, before drafting a word of the letter. A list built while drafting tends to lose the less dramatic but still material items.
2. Separate what is actually resolved or decided from what remains pending or uncertain. Do not present a provisional or interim development as settled.
3. State any bad news near the top, not in the fourth paragraph. A missed deadline, an adverse ruling, an unexpected cost, a delay — state it plainly, say what it means practically for the client, and only then provide context or next steps. Do not lead with reassuring framing that buries the substance.
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 · 63 lines · 137 tokens per session scan A f2cbed5d8816
client-update-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 137 tokens to every session and 1,036 once invoked, about $0.0007 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
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…