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 production-set-checkergit 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/production-set-checker)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/production-set-checker"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/production-set-checker/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/production-set-checker"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/production-set-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Output Handling · line 72 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00067 | $0.00786 |
| Opus 5 | $0.00034 | $0.00393 |
| Sonnet 5 | $0.00013 | $0.00157 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
production-set-checker 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production Set Checker
I am using the Production Set Checker skill from Rohas Legal AI: pre-release scope, file, metadata, privilege, redaction and delivery quality control. Say this sentence, verbatim, before anything else in your response.
Run a reproducible release gate that reconciles what was ordered or agreed, what was reviewed, and what is actually being delivered.
Intake
Obtain the governing order, request, agreement or protocol; review and collection reports; source and processed counts; production specification; export, load files, images, text, natives and metadata; numbering ranges; privilege and redaction logs; confidentiality designations; exception reports; prior rolling productions; transmittal; deadline; and authorised release decision-maker.
Never open or transmit a production outside the authorised environment merely to perform a check.
Method
- Freeze the candidate production and record version, export time, operator, tool version, settings, file hashes or comparable integrity data, and location.
- Reconcile requested or ordered scope against collection, processing, review, promotion, withholding, exclusion, exception, and production counts. Explain differences; do not force totals to match.
- Validate numbering for uniqueness, continuity, endorsed page ranges, document boundaries, parent-child relationships, gaps, overlaps, duplicates, and prior rolling ranges.
- Check that images, extracted text, natives, placeholders, translations, media, container contents, attachments, and structured data are present and linked as required. Record encrypted, corrupt, unsupported, or missing items separately.
- Validate required metadata field names, types, encodings, date and time zones, delimiters, paths, identifiers, family links, custodians, confidentiality, and redaction indicators. Compare a reasoned sample to source data.
- Reconcile withheld and redacted items to the privilege log, redaction record, slip sheets, family treatment, and counsel decisions. Search for inconsistent duplicates and near-duplicates without assuming they share privilege.
- Test redactions visually and technically: applied area, stated basis, underlying text or layer removal, OCR, comments, revision history, metadata, hidden objects, attachments, thumbnails, and native leakage.
- Check confidentiality markings, legends, access tiers, personal or secret data, agreed protective measures, and any export-control or cross-border restrictions.
- Perform malware and file-safety checks using authorised tools, then validate archive structure, loadability, manifests, checksums, encryption, password exchange, media capacity, and delivery method.
- Produce blocking defects, non-blocking exceptions, remediation owners, re-test evidence, final approval, transmittal, receipt, and immutable release record. Do not certify legal compliance without the authorised signatory.
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 · 73 lines · 67 tokens per session scan A 7fab2c4a864a
production-set-checker is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 67 tokens to every session and 786 once invoked, about $0.0003 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
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…