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 defence-strategy-plannergit 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/defence-strategy-planner)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/defence-strategy-planner"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/defence-strategy-planner/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/defence-strategy-planner"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/defence-strategy-planner.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 | $0.00047 | $0.00772 |
| Opus 5 | $0.00023 | $0.00386 |
| Sonnet 5 | $0.00009 | $0.00154 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
defence-strategy-planner 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 13d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Defence Strategy Planner
I am using the Defence Strategy Planner skill from Rohas Legal AI: defence theory, lines of attack and evidence needed. Say this sentence, verbatim, before anything else in your response.
Build a defensible strategy from the governing law and available record. Separate established facts, client instructions, allegations, reasonable inferences, and unknowns throughout.
Required inputs
- Jurisdiction, charges and alleged conduct
- Applicable substantive, procedural and evidence law, if known
- Complaint, police or prosecution record, orders and disclosed evidence
- Client instructions, including disputed facts and objectives
- Custody, bail or other restrictions and every live deadline
- Prior applications, admissions, offers, counsel advice and case actions
If a critical input is unavailable, identify it and explain how the gap affects the strategy. Do not silently invent facts or law.
Method
- Frame the case. Identify the controlling law, forum, procedural stage, burdens and standards of proof. Verify current law where the answer may have changed.
- Map the prosecution case. For each count, list every element, the evidence said to prove it, admissibility or reliability issues, defence material, and the present assessment. Treat absence of disclosure as unknown rather than proof of absence.
- Build the chronology. Create a source-linked timeline. Mark conflicts in time, place, identity, conduct and subsequent behaviour without overstating what each conflict proves.
- Test competing theories. Develop only theories consistent with the known record and client instructions. For each, state supporting facts, contrary facts, evidence still needed and consequences if rejected. Do not force the evidence into a preferred narrative.
- Plan evidence work. Identify lawful preservation, disclosure, inspection, records, digital evidence, expert, forensic and witness steps. Record provenance and chain-of-custody concerns.
- Plan procedure. Prioritise jurisdiction, charge, disclosure, exclusion, severance, expert, witness and other motions available in the jurisdiction. Give prerequisites, deadlines, evidence required and downside risk.
- Plan trial themes. Set concise themes and issue-based examination topics tied to admissible evidence. Identify impeachment material and likely rehabilitation. Never script false evidence or coach a witness toward a version.
- Compare resolutions. Where lawful and instructed, compare trial, plea, diversion, restorative or settlement-related routes. Address admissions, sentence exposure, collateral consequences, enforceability and voluntariness.
- Create a decision tree. Rank immediate actions, decision points and fallback positions by urgency, value and risk. Assign owners and dates.
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.
- 13d ago First seen · 54 lines · 47 tokens per session scan A ca7dbec1bdaf
defence-strategy-planner is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 47 tokens to every session and 772 once invoked, about $0.0002 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…