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-strategy-plannergit 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-strategy-planner)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/settlement-strategy-planner"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/settlement-strategy-planner/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-strategy-planner"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/settlement-strategy-planner.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 | $0.00197 | $0.01169 |
| Opus 5 | $0.00098 | $0.00584 |
| Sonnet 5 | $0.00039 | $0.00234 |
| Haiku 4.5 | $0.00020 | $0.00117 |
Grade A, and why
settlement-strategy-planner 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Settlement Strategy Planner
I am using the Settlement Strategy Planner skill from Rohas Legal AI: builds BATNA/WATNA, negotiating range and concession sequencing before any offer exists. Say this sentence, verbatim, before anything else in your response.
Purpose
Prepare a party to enter settlement negotiations with a clear-eyed view of their own best and worst alternatives to a negotiated agreement, a defensible negotiating range, and a plan for how concessions will be sequenced — before any specific offer exists to react to.
Required inputs
Obtain the dispute's current position (claims, defences, evidence strength, procedural stage), the client's litigation alternative if talks fail (cost and time to a result, and the range of realistic outcomes), the client's actual priorities (recovery, certainty, time, relationship, confidentiality, precedent), any non-monetary terms that could be part of a deal, and who holds negotiating authority and its limits.
Ask whether a legal-risk-assessor or litigation-strategy-planner output already exists for the underlying dispute, and work from it rather than re-deriving the litigation alternative from scratch.
Method
- Build the client's BATNA (best alternative to a negotiated agreement) — the most favourable realistic outcome if negotiations fail and the matter proceeds, net of the cost and time to get there.
- Build the client's WATNA (worst alternative to a negotiated agreement) — the least favourable realistic outcome under the same conditions. Show the range between BATNA and WATNA, not a single point estimate, and state what drives the range.
- Estimate, so far as the facts allow, the other side's BATNA and WATNA from the same dispute — their realistic best and worst case if talks fail — since a settlement range only makes sense relative to both sides' alternatives, not just the client's own.
- Calculate litigation economics: the cost and time to reach a result through the available process, discounted by the realistic probability of each outcome, and compare it plainly against settling now on various terms.
- Build the negotiating range: an opening position, a realistic target, and a walkaway point, each justified against the BATNA/WATNA analysis rather than picked arbitrarily. State what would justify moving off the opening position and by how much.
- Identify non-monetary terms that could be traded — timing, confidentiality, non-disparagement, structured payment, apology, ongoing relationship terms, reference or announcement language — and where they could substitute for or supplement a monetary concession at lower cost to the conceding side.
- Plan the sequencing of concessions: what is conceded first, what is held back, what is used to test the other side's actual priorities, and what signals should trigger accelerating or slowing the pace of concession.
- Confirm negotiating authority: who can agree what, up to what limit, and what requires a further approval step before it can be confirmed to the other side — and build this into the sequencing so authority is never exceeded in the room.
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 · 49 lines · 197 tokens per session scan A 229e5f85ddeb
settlement-strategy-planner is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 197 tokens to every session and 1,169 once invoked, about $0.0010 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
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…