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 compliance-obligations-mappergit 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/compliance-obligations-mapper)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/compliance-obligations-mapper"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/compliance-obligations-mapper/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/compliance-obligations-mapper"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/compliance-obligations-mapper.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 | $0.00177 | $0.01103 |
| Opus 5 | $0.00088 | $0.00551 |
| Sonnet 5 | $0.00035 | $0.00221 |
| Haiku 4.5 | $0.00018 | $0.00110 |
Grade A, and why
compliance-obligations-mapper 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compliance Obligations Mapper
I am using the Compliance Obligations Mapper skill from Rohas Legal AI: turns a regulation's text into an owners-and-deadlines obligations register. Say this sentence, verbatim, before anything else in your response.
Purpose
Take a specific regulatory text and turn it into something an organisation can actually implement: who owns each obligation, what triggers it, what evidence proves it was met, and by when — rather than leaving the regulation as prose that everyone assumes someone else is handling.
Required inputs
Obtain the specific law, rule, or regulation to be mapped — the actual text or a reliable current source, not a summary from memory. Obtain also the entity's structure, activities, and sector, since obligations often turn on entity type, size, or activity thresholds stated in the regulation itself.
Ask whether the user wants the mapping alone, or also wants their current practice checked against it — if current practice is described, this skill will flag gaps as part of its output; if not, it produces the obligations register only, without asserting a compliance status.
Treat the actual current, official text of the regulation as blocking. Do not map a regulation from a summary or from memory of an earlier version — retrieve or request the current text, and flag amendments or commencement questions for verification where currency cannot be confirmed this session.
Method
- Read the regulation's operative provisions in full before extracting anything. Note its scope provisions (who it applies to) and any threshold, exemption, or phased-commencement provision that gates individual obligations.
- Extract every distinct obligation the regulation imposes, in one structured list, before organising it further — a registration, a notice, a disclosure, a record-keeping duty, a consent requirement, a reporting obligation, a technical or organisational measure, a prohibition.
- For each obligation, state its trigger precisely — what activity, threshold, or event activates it, since many regulatory obligations are conditional rather than universal.
- For each obligation, propose an owner — the function or role that would naturally be responsible (legal, compliance, IT, HR, finance) — flagged as a proposed allocation for the user to confirm, not an assertion about the user's actual organisational structure.
- State what evidence would demonstrate compliance with each obligation — a filed document, a maintained register, a documented process, a training record — distinguishing genuine evidence from a bare policy statement.
- State the deadline or frequency for each obligation — one-off, periodic, or continuous — and flag where the regulation itself is ambiguous about timing.
- Propose the control that should exist to meet each obligation on an ongoing basis, not just once — a process, a checklist, a review cadence — appropriately generic where the specific implementation is the user's own operational choice to make.
- Where the user has described current practice, compare it against the obligations register and flag each obligation as met, partially met, not met, or status unclear from what was described — without asserting more confidence than the description supports.
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 · 48 lines · 177 tokens per session scan A d5e7ee883008
compliance-obligations-mapper is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 177 tokens to every session and 1,103 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 2026-08-30.
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…