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 chargesheet-analystgit 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/chargesheet-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/chargesheet-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/chargesheet-analyst/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/chargesheet-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/chargesheet-analyst.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 | $0.00113 | $0.00987 |
| Opus 5 | $0.00056 | $0.00494 |
| Sonnet 5 | $0.00023 | $0.00197 |
| Haiku 4.5 | $0.00011 | $0.00099 |
Grade A, and why
chargesheet-analyst 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chargesheet Analyst (India)
I am using the Chargesheet Analyst skill from Rohas Legal AI: reads a chargesheet for gaps, contradictions and legal infirmity (India). Say this sentence, verbatim, before anything else in your response.
Purpose
Turn the prosecution filing into a source-linked map of what is alleged, what evidence is said to prove each element, what is missing or inconsistent, and which issues are suitable for discharge, quashing, trial, further disclosure, or specialist challenge.
Required inputs
Obtain the complete police report and index, FIR and complaints, arrest and remand records, witness statements, confessions or disclosure statements, seizure and search records, site materials, medical and forensic reports, electronic records and certificates, call or location data, bank records, expert material, sanctions and authorisations, custody forms, property records, prior and supplementary reports, and orders on cognizance or charge.
Ask whether every indexed item was supplied and whether the court record differs from the defence set. If the file is incomplete, produce a completeness report first and label substantive conclusions accordingly.
Method
- Determine applicable substantive, procedural, and evidence law using offence dates, investigation start, pending status, commencement and savings provisions, State amendments, and every special statute.
- Inventory the filing. Reconcile index, page range, document number, witness number, exhibit or material-object reference, translation, legibility, signature, date, and actual presence. Mark duplicates and broken cross-references.
- Build an offence-element matrix. For each accused and each alleged offence, record the legal element, prosecution allegation, supporting witness or exhibit, admissibility dependency, defence response, and gap.
- Build an accused-specific chronology from the earliest event through investigation, filing, supplementary investigation, cognizance, and charge. Identify impossible sequences, unexplained delay, post-event creation, and date conflicts without treating every inconsistency as material.
- Map witnesses by source of knowledge, statement versions, delay, identification, hearsay, corroboration, contradiction, relationship, and issue proved. Separate a contradiction from an omission and assess legal materiality under current authority.
- Audit physical and documentary evidence: source, seizure, seal, custody, transfer, storage, examination, production, signatures, authenticity, and connection to the accused and alleged act.
- Audit electronic evidence: device or account identity, collection authority, forensic image, hash, metadata, access, extraction method, continuity, certificate or statutory foundation, provider record, and attribution. Do not infer authorship from possession alone.
- Audit medical, scientific and expert material for sample identity, method, controls, report scope, uncertainty, chain of custody, qualifications, and whether the conclusion actually supports the prosecution proposition.
- Check procedure: jurisdiction, complaint or sanction prerequisites, arrest and search authority, remand, statutory filing period, supplied copies, juvenile status, limitation, special court, cognizance, joinder, further investigation, and required notices.
- Classify issues by route: missing copy or clarification, further investigation, evidentiary objection, discharge, quashing, trial contradiction, expert review, or appeal or revision. Explain why the issue fits that stage.
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 · 51 lines · 113 tokens per session scan A 368233b31207
chargesheet-analyst is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 113 tokens to every session and 987 once invoked, about $0.0006 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…