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 | $0.02514 |
| Opus 5.5 | $0.00073 | $0.01006 |
| Sonnet 5.5 | $0.00037 | $0.00503 |
| Haiku 4.5 | $0.00018 | $0.00251 |
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 17d 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 — 91 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.
- 17d ago Changed · +4 lines e29e0d480c36
- 1mo 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 (193 stars, last pushed 17d ago), licensed MIT. It adds 183 tokens to every session and 2,514 once invoked, about $0.0007 per session on Opus 5.5. 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
founder-agreement-drafting-stephane-boghossian
A drafting-and-review copilot for a founders' / co-founders' agreement — the terms fixing equity, vesting, IP, roles, control, deadlock, and departure between cofounders. Jurisdiction-agnostic, anchored on the Delaware C-corp default. Two modes: DRAFT (intake → equity & vesting → clauses → blocker triage →…
local-counsel-manager-scott-margetts
End-to-end external local counsel lifecycle management for multi-jurisdiction legal matters. LC selection criteria and capability assessment, engagement setup and instruction design, performance monitoring and check-in cadence, scope enforcement, and relationship escalation. Use when selecting local counsel for a…
collaboration-platform-advisor-scott-margetts
Collaboration platform configuration methodology for legal matter sites. Site architecture, workflow identification, dashboard design, data quality governance, and user adoption for SharePoint, Teams, and equivalent platforms. M365 is the reference implementation — outputs are platform-agnostic enough to brief IT or…
matter-allocation-instruction
Firm-matter matching, matter instruction drafting, firm onboarding checklist, and instruction audit for in-house legal ops teams. Match a new matter to the right panel firm by practice area, jurisdiction, complexity, and cost tier. Produce a structured matter instruction with scope, timeline, budget, staffing, and…
meeting-briefing-anthropic
Prepare structured briefings for meetings with legal relevance and track resulting action items. Use when preparing for contract negotiations, board meetings, compliance reviews, or any meeting where legal context, background research, or action tracking is needed.
rfp-pitch-management
RFP creation, distribution, evaluation, and shortlisting for in-house legal teams selecting outside counsel. Draft a new legal services RFP from scratch, evaluate firm responses against weighted criteria, produce a shortlist recommendation with selection rationale for GC sign-off, or design the end-to-end RFP process…