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 settlement-documentergit 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/settlement-documenter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/settlement-documenter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/settlement-documenter/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/settlement-documenter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/settlement-documenter.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 | $0.00182 | $0.01900 |
| Opus 5.5 | $0.00073 | $0.00760 |
| Sonnet 5.5 | $0.00036 | $0.00380 |
| Haiku 4.5 | $0.00018 | $0.00190 |
Grade A, and why
settlement-documenter 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 2mo 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Settlement Documenter
I am using the Settlement Documenter skill from Rohas Legal AI: records a session outcome, or drafts complete binding settlement terms, once agreement is reached. Say this sentence, verbatim, before anything else in your response.
Before you start
Determine which mode is needed: a session outcome record (what actually happened and was agreed today, including partial or no agreement), or full settlement terms (the complete, executable instrument recording a settlement already agreed). These are not the same document and the first is never a substitute for the second — a full settlement reached in a session still needs to be converted into formal terms, and this skill flags that explicitly rather than treating the record as done.
Mode A — Session outcome record
Before you start
What actually happened and was discussed in the session, from the user's account or notes. Blocking — this is a record, not a reconstruction, and it cannot be built from inference.
Not blocking, determined from the facts rather than assumed in advance: whether the session reached full settlement, partial agreement, or no agreement. Let the record's structure follow from what actually happened.
Method
- Record what was actually agreed, precisely and only as instructed. Do not round out an ambiguous or incomplete agreement into something that reads as more definite than it was — if the parties agreed to something "in principle" without settling the mechanics, record it as agreed-in-principle, not as final.
- Separate three categories clearly: points fully agreed; points where the parties narrowed the gap without reaching agreement (record where each side's position moved to, since this matters for any future round); and points that remain entirely open.
- Note every condition attached to what was agreed — subject to board approval, subject to formal documentation, subject to a specific party's confirmation — precisely, since these conditions determine whether what was agreed is actually binding yet.
- Record next steps and, where given, timing — who does what, by when.
- If a full settlement was reached, flag plainly that it still needs to be converted into a formal binding document under Mode B below. Do not treat this outcome record itself as the binding settlement agreement unless the user has explicitly confirmed that is what is intended.
- Flag the confidentiality and without-prejudice status of this record as it applies to what was discussed. Whether this document — or what it records — is admissible or otherwise usable later depends on the mediation/conciliation agreement and the governing law; flag this as a verification point rather than asserting a specific protection applies.
- Where no agreement was reached, record that plainly, along with whether the parties intend to continue negotiating and anything learned during the session that is useful for that. Do not use this as an opportunity to plan the next session's strategy — that belongs to a caucus or negotiation-planning skill; this documents what already happened.
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.
- 2mo ago First seen · 73 lines · 182 tokens per session scan A aafa156b662f
settlement-documenter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 182 tokens to every session and 1,900 once invoked, about $0.0007 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 2026-09-03.
settlement-documenter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| settlement-documenterrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 182 | 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 |