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 party-interest-analystgit 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/party-interest-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/party-interest-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/party-interest-analyst/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/party-interest-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/party-interest-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 42 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00145 | $0.01015 |
| Opus 5 | $0.00072 | $0.00508 |
| Sonnet 5 | $0.00029 | $0.00203 |
| Haiku 4.5 | $0.00015 | $0.00102 |
Grade A, and why
party-interest-analyst 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Party Interest Analyst
I am using the Party Interest Analyst skill from Rohas Legal AI: separates stated positions from underlying interests on both sides. Say this sentence, verbatim, before anything else in your response.
What this does
Maps each party's stated position against their actual underlying interests, for both sides of a dispute — the classic distinction between what a party says they want and why they actually want it. It works with real uncertainty about the other side's interests, labelling every inference as an inference rather than presenting a guess as a fact, and it identifies where positions conflict but interests might not — the openings a mediation can actually use — without pretending every point of conflict has an integrative solution when some genuinely do not.
Before you start
What is known about each party's stated position and the facts of the dispute. Blocking — the analysis has to start from what has actually been said or observed, not from a general sense of the dispute.
Not blocking: how much is actually known about the other party's interests. This is often limited. Work with that uncertainty directly rather than filling gaps with confident-sounding guesses — every inference about the other side gets labelled as an inference in the output.
Method
1. State each party's stated position precisely, for both sides — what they say they want, in their own terms as far as they are known.
2. For the instructing party's own interests, work from direct instructions — the actual reasons behind the position: cost, time, certainty, relationship, precedent, reputation, or a specific practical need. Distinguish interests the client has stated clearly from ones being inferred from context, and label the difference.
3. For the other party's interests, work from whatever is actually known or can reasonably be inferred from their conduct and statements — and label every one of these as an inference, never as a fact. Presenting a guess about the other side's motivations as established is the single most common way this kind of analysis misleads.
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 · 61 lines · 145 tokens per session scan A a379362d2c0b
party-interest-analyst is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 145 tokens to every session and 1,015 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 2026-09-03.
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…