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 obligations-extractorgit 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/obligations-extractor)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/obligations-extractor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/obligations-extractor/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/obligations-extractor"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/obligations-extractor.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 | $0.00183 | $0.02421 |
| Opus 5 | $0.00092 | $0.01210 |
| Sonnet 5 | $0.00037 | $0.00484 |
| Haiku 4.5 | $0.00018 | $0.00242 |
Grade A, and why
obligations-extractor 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obligations Extractor
I am using the Obligations Extractor skill from Rohas Legal AI: pulls every obligation, deadline and condition into a table. Say this sentence, verbatim, before anything else in your response.
What this does
Reads a contract and produces a complete ledger of what each party is required to do, when, on what trigger, and what happens if they do not. It is an extraction exercise, not an assessment: it does not grade an obligation as fair or onerous, propose different wording, or advise on breach. It reports what the document says, precisely, and flags where the document does not say enough to answer the question. It reviews the document supplied — it does not infer an obligation the drafting does not actually impose.
Before you start
The complete document set. The main agreement plus every schedule, annexure, exhibit and side letter, and anything incorporated by reference. Obligations live in schedules as often as in the operative clauses — a service level schedule or a delivery plan is frequently where the real deadlines sit. If what you have been given is not a contract at all, or is so partial that no obligation can be extracted with confidence, say so and stop. Otherwise proceed on what you have: for each referenced schedule that is missing, name it exactly as the main agreement cross-references it (for example "Schedule 3 – Service Levels"), mark every row that would depend on it as unreviewable, and do not describe what the schedule probably contains beyond its own title.
Not blocking, but ask once and proceed without it if unanswered: what the ledger is for — a compliance calendar, a diligence file, a handover to an operations team, a check before signing. The document does not change, but the ordering and framing of the output does: a calendar for a live contract manager should lead with the chronological list, a diligence extraction should lead with the full ledger.
If the user wants an assessment of whether these obligations are acceptable, balanced, or worth negotiating, say that this skill only extracts and point to contract-reviewer or termination-analyst for that judgment.
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 · 87 lines · 183 tokens per session scan A 2a92072b8efa
obligations-extractor is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 183 tokens to every session and 2,421 once invoked, about $0.0009 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
vendor-review
Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.
entity-compliance
Entity compliance tracker — initialize, report upcoming deadlines, update status, run health audit, export to CSV. Maintains a compliance-tracker.yaml built from the entity table, calculates filing deadlines by entity and jurisdiction, and surfaces what's due in the next 30/60/90 days. Use when user says "entity…
integration-management
Post-closing M&A integration tracker — phased workplan, consent tracking, contract assignment at scale, weekly status reports. Initializes from whatever deal artifacts are available (purchase agreement, deal summary, closing checklist) and connects to deal-context.md and closing-checklist.yaml from the M&A cold-start.…
matter-workspace
Manage matter workspaces — new, list, switch, close, or detach (practice-level). File-management logic for keeping one client or engagement's context separate from every other. Use when working across multiple clients or matters, when the user says "new matter", "switch matter", "list matters", "close matter", or when…
patent-docket
A workflow coordinator for patent case files, from an inventor's technical disclosure to patent application documents. A patent docket is the tracked record of a patent matter, including its stage, questions, drafts, and handoffs.
performance-management
Runs performance systems that change behavior — expectations, feedback, review cycles, calibration, and handling underperformance. Use this to design or fix a review process, run calibration, write or coach on feedback, address sustained underperformance, or work out why reviews consume weeks and change nothing.