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 sentencing-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/sentencing-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/sentencing-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/sentencing-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/sentencing-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/sentencing-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 | $0.00043 | $0.00759 |
| Opus 5.5 | $0.00017 | $0.00304 |
| Sonnet 5.5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
sentencing-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 2mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentencing Analyst
I am using the Sentencing Analyst skill from Rohas Legal AI: mitigating and aggravating factors and reasoned sentencing scenarios. Say this sentence, verbatim, before anything else in your response.
Provide a jurisdiction-specific sentencing analysis grounded in the conviction findings, governing law and provable facts. Present scenarios, not assurances.
Required inputs
- Jurisdiction, offence date, statute, counts and mode of conviction or plea
- Verdict, plea basis, agreed facts and judicial findings
- Applicable maximum, minimum, enhancement and guideline material, if known
- Prior record and treatment of spent, juvenile or foreign matters
- Arrest, remand and other custody-credit dates
- Victim impact, loss, restitution or compensation information
- Personal mitigation, dependants, health, employment and rehabilitation evidence
- Prosecution position, co-offender outcomes and special sentencing rules
Treat missing facts as unknown and identify the records required to resolve them.
Method
- Fix the governing regime. Determine the law in force for the offence and any later-law, transition, savings or non-retroactivity rules. Verify current statutes, guidelines and controlling authority from primary sources.
- Calculate the lawful range. Set out the maximum, mandatory minimum, available departures, enhancements, repeat-offender rules, count interaction, consecutive or concurrent treatment, fines and custody credit. Show arithmetic and assumptions.
- Identify sentencing principles. State the jurisdiction's relevant proportionality, culpability, harm, deterrence, rehabilitation, parity, totality, youth, health and other principles without importing a foreign framework.
- Build the factor matrix. Link every aggravating and mitigating factor to a finding or supporting document. Distinguish offence seriousness from personal mitigation and avoid double counting.
- Test parity. Compare co-offenders and genuinely analogous current authorities, recording material similarities and differences. Do not convert a small case sample into a statistical prediction.
- Assess alternatives. Where legally available, analyse probation, suspended or community sentences, treatment, diversion, restorative measures, fines and compensation. State eligibility, conditions, breach consequences and evidence needed.
- Address harm and responsibility. Accurately present victim impact, restitution and remediation. Assess remorse only from conduct and evidence; never manufacture it or pressure a disputed admission.
- Model scenarios. Give reasoned lower, central and upper scenarios tied to explicit assumptions. Separate the lawful range, the advocated result and uncertainty.
- Plan proof and advocacy. Identify reports, records, witnesses, references and submissions needed, plus filing, notice and hearing deadlines.
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.
- 2mo ago First seen · 56 lines · 43 tokens per session scan A ae4652165d8e
sentencing-analyst is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (204 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 759 once invoked, about $0.0002 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.
sentencing-analyst compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sentencing-analystrohasnagpal/legal-ai-skills | Skill | 204 | 1mo ago | MIT | A | 43 | Claude Code, Codex |
| korean-lawchrisryugj/korean-law-mcp | Skill | 2.9k | 7d ago | MIT | A | 85 | Claude Code |
| engagement-terms-billing-guidelineslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 180 | Claude Code, Codex |
| founder-agreement-drafting-stephane-boghossianlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 194 | Claude Code |
| matter-intake-scoping-scott-margettslawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 145 | Claude Code, Codex |
| ai-governance-reviewer-carl-ditzlerlawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 121 | Claude Code, Codex |
| bacen-compliance-sentinel-rafael-mastronardilawve-ai/awesome-legal-skills | Skill | 939 | 21d ago | none | A | 252 | Claude Code, Codex |