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 caucus-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/caucus-strategy-planner)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/caucus-strategy-planner"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/caucus-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/caucus-strategy-planner"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/caucus-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 | $0.00148 | $0.01153 |
| Opus 5 | $0.00074 | $0.00576 |
| Sonnet 5 | $0.00030 | $0.00231 |
| Haiku 4.5 | $0.00015 | $0.00115 |
Grade A, and why
caucus-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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caucus Strategy Planner
I am using the Caucus Strategy Planner skill from Rohas Legal AI: what to disclose and hold back in private session. Say this sentence, verbatim, before anything else in your response.
What this does
Plans what a party should disclose in a private mediation caucus, what to keep for the mediator's understanding only, and what to explicitly authorise the mediator to convey to the other side. It treats the party's bottom line as protected by default, and treats the mediation's own confidentiality rules — whether the mediator may pass caucus information along unless told not to, or may not pass it along unless told to — as something to confirm, never assume, since getting this backwards can mean information the client wanted kept private is conveyed by mistake.
Before you start
The underlying dispute facts and the party's actual position and interests. Blocking — there is nothing to plan disclosure around without this. Where a party-interest-analyst output already exists, work from it rather than re-deriving it.
What the client wants this caucus round to accomplish. Blocking — the disclosure plan depends on what progress the party is actually trying to make.
The confidentiality default of this specific mediation. Whether the mediator may convey caucus information to the other side unless told otherwise, or may not convey it unless specifically authorised. Ask; do not assume. Where this is not confirmed, build the plan on the conservative assumption — nothing is conveyed unless the client says otherwise — and flag the confirmation as still needed.
Method
1. Confirm the confidentiality default before building anything else. This single fact changes how every other part of the plan should be built, and assuming it wrong risks a genuine disclosure error, not just a drafting inconvenience.
2. List every piece of information the party could disclose, categorised as: must disclose (needed to make any progress this round), advantageous to disclose (helps build the case or build trust with the mediator), neutral, or must not disclose (weakens the position, reveals the bottom line prematurely, or is otherwise protected).
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 · 65 lines · 148 tokens per session scan A 589a14cf1f9f
caucus-strategy-planner is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 148 tokens to every session and 1,153 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…