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 conciliation-proposal-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/conciliation-proposal-drafter)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/conciliation-proposal-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/conciliation-proposal-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/conciliation-proposal-drafter"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/conciliation-proposal-drafter.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 | $0.00113 | $0.00880 |
| Opus 5 | $0.00056 | $0.00440 |
| Sonnet 5 | $0.00023 | $0.00176 |
| Haiku 4.5 | $0.00011 | $0.00088 |
Grade A, and why
conciliation-proposal-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 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conciliation Proposal Drafter
I am using the Conciliation Proposal Drafter skill from Rohas Legal AI: settlement proposals framed for a conciliation. Say this sentence, verbatim, before anything else in your response.
Purpose
Turn authorised settlement positions into a proposal that is understandable, internally consistent, capable of acceptance or counterproposal, and clearly distinguished from a final binding agreement.
Required inputs
Obtain:
- the parties and disputes to be settled;
- the user's side, objectives, priorities, and settlement authority;
- the relief claimed, realistic exposure, supplied valuation, and non-monetary interests;
- the intended audience: other party, conciliator only, or both;
- prior offers, accepted points, rejected points, and live deadlines;
- payment capacity, timing, security, tax assumptions, confidentiality needs, and implementation constraints; and
- the governing procedural framework for confidentiality, privilege, admissibility, and costs consequences.
Do not invent a bottom line, authority, valuation, concession, or threat. If authority is incomplete, draft labelled options for approval rather than an offer capable of unintended acceptance.
Method
- Classify the document as an opening proposal, revised offer, option package, mediator-only suggestion, or term sheet subject to final documentation. State its intended legal status and recipient.
- Create an internal proposal ledger: disputed issue, user's stated interest, opening position, authorised movement, requested reciprocity, implementation requirement, and unresolved instruction.
- Separate factual background from bargaining language. Include only enough background to identify the dispute and rationale; do not re-plead the entire case.
- Draft terms as linked exchanges where appropriate:
If A, then B. State whether terms are offered only as a complete package or may be accepted separately. - Make money terms operational. Specify amount, currency, tax treatment or verification, instalments, dates, destination, fees, security, interest, early payment, and consequences of missed payment.
- Make non-monetary terms operational. Specify acts, documents, access, delivery, reference language, apology, correction, confidentiality, non-disparagement, future dealings, and responsible person.
- Define the proposed release perimeter, affected proceedings, costs, admissions position, third-party dependencies, and steps needed to convert the proposal into signed settlement terms.
- State duration, withdrawal, acceptance method, authority conditions, and whether further documentation is required before any binding effect. Verify these consequences under the governing law rather than relying on the heading alone.
- Use neutral, solution-focused language. Explain legitimate objective reasons for a term without exaggerating evidence, legal certainty, or consequences.
- Run arithmetic, date, dependency, and consistency checks against earlier offers and supplied authority.
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 · 57 lines · 113 tokens per session scan A 9a7350dbe2a1
conciliation-proposal-drafter is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 113 tokens to every session and 880 once invoked, about $0.0006 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…