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 EliasOulkadi/shokunin --skill legal-counselgit clone --depth 1 https://github.com/EliasOulkadi/shokuninWrote 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/eliasoulkadi/shokunin/legal-counsel)<a href="https://agentmods.dev/skills/eliasoulkadi/shokunin/legal-counsel"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/legal-counsel/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/eliasoulkadi/shokunin/legal-counsel"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/legal-counsel.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 | $0.00056 | $0.02578 |
| Opus 5.5 | $0.00022 | $0.01031 |
| Sonnet 5.5 | $0.00011 | $0.00516 |
| Haiku 4.5 | $0.00006 | $0.00258 |
Grade A, and why
legal-counsel 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMPORTANT DISCLAIMER: Reference information for educational and preliminary analysis. NOT legal advice. No attorney-client relationship. Laws vary by jurisdiction and change frequently. Always consult a qualified attorney.
Workflow
When asked a legal compliance question, follow these steps:
| Step | Action | Notes |
|---|---|---|
| 1 | Identify jurisdiction(s) | EU, US federal, US state(s), UK — may overlap |
| 2 | Map the Obligation Matrix | Core Analysis Framework (below) |
| 3 | Cross-reference enforcement | Fines, private right of action, regulator trends |
| 4 | Check effective dates | Phased enforcement is common (AI Act, HIPAA 2026) |
| 5 | Return applicable code | Use sub-sections below — do not invent thresholds |
| 6 | Append disclaimer | Always close with "verify with qualified attorney" |
Core Analysis Framework
| Lens | What it asks |
|---|---|
| Jurisdiction | Which law applies? (EU, UK, US federal, US state) |
| Obligation | What must you do? (mandatory vs recommended) |
| Risk | What happens if you don't? (fines, lawsuits, reputation) |
| Timeline | When must you comply? (deadlines, phased enforcement) |
Error Handling
| Scenario | What to do | Don't do |
|---|---|---|
| User asks "is this legal?" | Frame as checklist — never a yes/no opinion | Give definitive legal judgment |
| Jurisdiction unclear | Ask which country/state the business operates in | Assume US or EU by default |
| Threshold question (revenue, user count) | Clarify exact figures before answering | Give partial guidance |
| Law recently updated | Check effective date; note "proposed/not yet in force" if applicable | Cite outdated text as current |
| User asks about pending legislation | Flag "not yet law — monitor progress" | Present as binding requirement |
| Cross-border data transfer (EU→US) | Reference DPF / SCCs / BCRs | Oversimplify transfer mechanism |
3. EU Law
3.1 GDPR (Regulation EU 2016/679)
Applies to: Any organization processing personal data of EU residents. Lawful basis (6): Consent, contract, legal obligation, vital interest, public task, legitimate interest. Consent: Specific, informed, unambiguous, freely given, revocable. No pre-ticked boxes. DSAR: 30 days. Mostly free. Can extend 60 days for complex. Breach notification: 72 hours to authority. Notify subjects if high risk. DPIA: Required for high-risk processing (profiling, large-scale sensitive data). Fines: Up to 4% of annual global turnover or EUR 20M.
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 · 219 lines · 56 tokens per session scan A 34c4a2f8ca3a
legal-counsel is a skill published in the GitHub repository EliasOulkadi/shokunin (112 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,578 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 2026-08-30.
legal-counsel compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| legal-counselEliasOulkadi/shokunin | Skill | 112 | 1mo ago | MIT | A | 56 | Claude Code, Codex |
| prior-art-searchRobThePCGuy/Claude-Patent-Creator | Skill | 209 | 11d ago | MIT | A | 26 | Claude Code |
| mpep-searchRobThePCGuy/Claude-Patent-Creator | Skill | 209 | 11d ago | MIT | A | 32 | Claude Code |
| brand-protection-tiktoknexscope-ai/eCommerce-Skills | Skill | 1.3k | 2mo ago | MIT | A | 44 | Claude Code, Codex |
| brand-protection-ebaynexscope-ai/eCommerce-Skills | Skill | 1.3k | 2mo ago | MIT | A | 47 | Claude Code, Codex |
| telnyx-email-suppressions-curlteam-telnyx/ai | Skill | 224 | yesterday | MIT | B | 37 | Claude Code |
| company-incorporationnorman-finance/norman-mcp-server | Skill | 65 | 4d ago | MIT | A | 73 | Claude Code |