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 ThomasMoreAI/legal-skills-open --skill wcc-bih-jeannesulzergit clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-openWrote 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/thomasmoreai/legal-skills-open/wcc-bih-jeannesulzer)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/wcc-bih-jeannesulzer"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/wcc-bih-jeannesulzer/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/thomasmoreai/legal-skills-open/wcc-bih-jeannesulzer"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/wcc-bih-jeannesulzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00247 | $0.04160 |
| Opus 5.5 | $0.00099 | $0.01664 |
| Sonnet 5.5 | $0.00049 | $0.00832 |
| Haiku 4.5 | $0.00025 | $0.00416 |
Grade A, and why
wcc-bih-jeannesulzer 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 20d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WCC-BiH — War Crimes Chamber of the Court of Bosnia and Herzegovina
This skill governs every output that touches the War Crimes Chamber of the Court of Bosnia and Herzegovina — known formally as Section I (War Crimes) of the Criminal Division of the State Court of Bosnia and Herzegovina (Sud Bosne i Hercegovine). The discipline is simple and the reason for it is concrete: the WCC-BiH is the largest national war crimes prosecution apparatus in the former Yugoslavia and operates as the principal complement to the ICTY's Completion Strategy. Its caseload — referrals from the ICTY under Rule 11 bis, plus locally-initiated cases — has produced the most substantial body of contemporary national jurisprudence on Yugoslav-conflict crimes.
The discipline in one paragraph
For any case-specific document — judgment, decision, indictment, filing — verify before citing. "Verify" means web_fetch (or equivalent retrieval) to the Court of BiH official website (sudbih.gov.ba) or to a Tier 1 mirror (the OSCE Mission to BiH archive, ICTY referral documents on the IRMCT/ICTY archives, the ICC Legal Tools Database) in the current conversation. Foundational texts in project knowledge (Law on the Court of BiH 2002, Criminal Code of BiH 2003, Criminal Procedure Code of BiH 2003) are the exception; they may be cited directly. Nothing else.
Verification is gradient, not binary
WCC-BiH has produced a very substantial caseload (hundreds of cases since 2005). Three levels:
- Existence verified. Case name, parties, date, chamber and document type confirmed against an authoritative source.
- Content verified. The fetched text confirms the proposition in substance.
- Paragraph verified. The specific cited paragraph or page contains the cited proposition.
Label the level where relevant. WCC-BiH judgments are typically structured by paragraph numbers in both BCS and English versions.
Standard workflow
Step 0 — Identify the document. Before anything else, distinguish:
What ships with it
9 files 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.
- CHANGELOG.md 5.5 KB
- examples/example-audit.md 3.7 KB
- examples/example-verification.md 3.6 KB
- LICENSE 2.0 KB
- references/authoritative-sources.md 4.9 KB
- references/citation-format.md 4.5 KB
- references/foundational-texts.md 6.4 KB
- references/jurisprudence-map.md 6.6 KB
- references/verification-workflow.md 8.5 KB
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.
- 20d ago Changed f73c2e6bbf2b
- 26d ago First seen · 192 lines · 247 tokens per session scan A 9c72a9b4ee2a
wcc-bih-jeannesulzer is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 247 tokens to every session and 4,160 once invoked, about $0.0010 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 2026-10-02.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…