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 witness-statement-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/witness-statement-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/witness-statement-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/witness-statement-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/witness-statement-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/witness-statement-drafter.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 | $0.00060 | $0.00614 |
| Opus 5.5 | $0.00024 | $0.00246 |
| Sonnet 5.5 | $0.00012 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
witness-statement-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 1mo 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Witness Statement Drafter
I am using the Witness Statement Drafter skill from Rohas Legal AI: witness-owned factual evidence, exhibits, uncertainty and formalities. Say this sentence, verbatim, before anything else in your response.
Preserve the witness's evidence, vocabulary, uncertainty, and independence. A statement is not written submissions in the witness's voice.
Intake and interview
Obtain the forum rules and order, issues, pleadings, prior accounts, interview notes or recording, relevant documents, chronology, witness role and capacity, language and literacy, memory aids, source of information, exhibits, disclosure status, privilege boundaries, vulnerabilities, deadline, and statement of truth or oath requirements.
Drafting method
- Explain purpose, disclosure and cross-examination consequences, truth duty, privilege limits, document preservation, and the witness's right to correct the draft.
- Establish identity, role, relationship to the parties, relevant experience, and how the statement was prepared.
- Organise evidence chronologically or by issue in numbered first-person paragraphs.
- State only facts the witness could properly give orally. Identify personal observation, refreshed recollection, usual practice, inference, and information or belief with its source.
- Use the witness's own words and level of certainty. Preserve “I do not know,” “I do not recall,” estimates, reconstructed dates, and qualified recollection.
- Link documents and exhibits with accurate identifiers. Do not imply the witness created, sent, received, read, or understood a document without a basis.
- Reconcile material differences from prior statements, pleadings, documents, and other accounts; record the witness's explanation rather than conceal it.
- Exclude legal argument, commentary on others' motives, inadmissible hearsay, expert opinion, privileged content, and unnecessary personal data unless proper.
- Record interpreter, translation, accessibility, interview, drafting, document-review, and remote-signing circumstances where required.
- Have the witness review the full statement and exhibits, make genuine corrections, and sign or swear only the approved final version.
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.
- 1mo ago First seen · 59 lines · 60 tokens per session scan A 735b96302e53
witness-statement-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 614 once invoked, about $0.0002 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 2026-09-21.
witness-statement-drafter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| witness-statement-drafterrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 60 | Claude Code, Codex |
| korean-lawchrisryugj/korean-law-mcp | Skill | 2.9k | 7d ago | MIT | A | 85 | Claude Code |
| engagement-terms-billing-guidelineslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 180 | Claude Code, Codex |
| founder-agreement-drafting-stephane-boghossianlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 194 | Claude Code |
| matter-intake-scoping-scott-margettslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 145 | Claude Code, Codex |
| ai-governance-reviewer-carl-ditzlerlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 121 | Claude Code, Codex |
| bacen-compliance-sentinel-rafael-mastronardilawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 252 | Claude Code, Codex |