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 redaction-reviewergit 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/redaction-reviewer)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/redaction-reviewer"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/redaction-reviewer/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/redaction-reviewer"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/redaction-reviewer.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 | $0.00070 | $0.00781 |
| Opus 5 | $0.00035 | $0.00391 |
| Sonnet 5 | $0.00014 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
redaction-reviewer 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.
Redaction Reviewer
I am using the Redaction Reviewer skill from Rohas Legal AI: legal-basis, consistency and technical-permanence review of redactions. Say this sentence, verbatim, before anything else in your response.
Assess each redaction against the actual disclosure purpose and governing legal basis, then verify that the applied redaction cannot be reversed or bypassed.
Intake
Obtain the jurisdiction, forum and audience; governing rules, order, protocol or publication standard; complete unredacted source; proposed redacted version; production or filing format; redaction log; privilege and confidentiality decisions; protective measures; document families and duplicates; personal-data and secrecy constraints; and the authorised approver.
Keep unredacted material in the authorised environment. If only the redacted copy is available, limit the review to visible and technical defects and state that the substantive basis cannot be verified.
Method
- Identify the precise purpose and audience: party disclosure, public filing, court inspection, freedom-of-information release, regulator production, investigation report, or publication. Do not transfer a redaction standard from one setting to another.
- Build a basis key from current governing authority and orders. Distinguish privilege, personal data, secrecy, confidentiality, irrelevance, trade secrets, protected identities, security, and court-ordered treatment.
- Compare source and redacted versions by stable document and page or field locators. Record the content category, asserted basis, decision-maker, extent, label, and whether a less extensive protective measure is sufficient.
- Test necessity and proportionality. Avoid hiding context needed to understand disclosed material and avoid redacting a fact merely because it is adverse, embarrassing, commercially inconvenient, or already confidential.
- Reconcile treatment across duplicates, near-duplicates, email threads, attachments, versions, translations, exhibits, structured data, and prior disclosures. Do not assume an earlier mistake authorises repetition.
- Check partial redactions, legends, confidentiality markings, page numbering, cross-references, indexes, bookmarks, filenames, and the separation of public, confidential, sealed, and counsel-only versions.
- Test technical permanence using authorised inspection: selectable text, OCR, layers, annotations, comments, revision history, hidden cells or slides, metadata, thumbnails, attachments, embedded objects, alternate renditions, search indexes, and copy-paste or extraction.
- Reconcile the final redaction log and privilege log to the released set. Record over-redaction, under-redaction, unexplained inconsistency, leakage, and items requiring counsel or court determination.
- Preserve the clean source, approved redacted version, tool and method, operator, date, verification results, approver, release recipient, and challenge history.
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 · 70 tokens per session scan A 84cf38f6121a
redaction-reviewer is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 70 tokens to every session and 781 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…