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 Jack-mi/vibelawyer --skill vibelawyer-reviewgit clone --depth 1 https://github.com/Jack-mi/vibelawyerWrote 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/jack-mi/vibelawyer/vibelawyer-review)<a href="https://agentmods.dev/skills/jack-mi/vibelawyer/vibelawyer-review"><img src="https://agentmods.dev/badge/skills/jack-mi/vibelawyer/vibelawyer-review/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/jack-mi/vibelawyer/vibelawyer-review"><img src="https://agentmods.dev/badge/skills/jack-mi/vibelawyer/vibelawyer-review.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 | $0.00090 | $0.01322 |
| Opus 5 | $0.00045 | $0.00661 |
| Sonnet 5 | $0.00018 | $0.00264 |
| Haiku 4.5 | $0.00009 | $0.00132 |
Grade A, and why
vibelawyer-review 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
刑事案件阅卷（宿主 Agent + vibelawyer MCP）
卷宗 PDF 只在用户本机处理。你（宿主 Agent）负责推理与编排；vibelawyer MCP（入口 uvx vibelawyer / 别名 vibelawyer-mcp）提供读卷、登记、校验、导出工具。
前置：接入 MCP
任选一种（command 相同）：
Cursor / 通用 mcp.json：
{
"mcpServers": {
"vibelawyer": {
"command": "uvx",
"args": ["vibelawyer"]
}
}
}
已 pip install vibelawyer 时可用 "command": "vibelawyer"（或别名 vibelawyer-mcp）、args 留空。
Kimi Code / OpenCode / Codex 等：在各自 MCP 配置里填入同一 command。
FastMCP 调用约定
- 先
create_case(case_dir="/绝对路径/到卷宗目录")→ 得到case_id。 - 读卷/登记/校验类工具签名：
tool_name(case_id, args={...})。 例：read_pages(case_id="...", args={"volume": "主卷", "start_page": 1, "end_page": 5})。 - 也可用
start_review(case_id)拉取结构化 playbook（不会启动后台 LLM job）。 - 进度看
get_case_status/get_workspace_summary的登记计数，不要相信口头「已完成」。
铁律
- 严禁幻觉：只能基于
read_pages实际读到的内容登记，绝不臆测。 - 来源必标：每条记录必须带真实卷宗名与页码区间；拿不准就再读一遍。
- 交付物 = 工具调用：必须实际调用
record_*/add_*写入工作区；只在回复里复述不算完成。 - 扫描件：
read_pages已含本地中文 OCR；仍不清则标注「OCR识别不清/待核查」，勿空转要图。 - 高效：先
get_volume_outline，再read_pages精读；用search_volumes防遗漏。 - 每步收尾：
get_workspace_summary或get_case_status核实计数后再进入下一步。
标准步骤（严格按序）
0. 建案
create_case(case_dir=...)（可选defendant_hint/charge_hint/output_dir）- 可选：
start_review(case_id)获取完整 playbook
1. 编制阅卷目录（case-indexer）
- 工具：
list_volumes→get_volume_outline→add_catalog_entry（逐文件） - 完成判据：目录条目 > 0，且已定位起诉书/起诉意见书卷页
2. 起诉书与当事人（indictment-reader）
- 工具：
search_volumes/read_pages→set_case_basic→record_party→record_indictment→add_charged_fact record_party只登本案被告人，不是同案人；职务犯罪填任职- 完成判据：案件基本信息、当事人、起诉书已登记
3. 被告人供述（defendant-statement-extractor）
record_statement，args.role = "defendant"；必须含 full_text 逐字问答全文- 一份讯问笔录一次调用；按时间逐份登记
4. 同案人供述（codefendant-statement-extractor）
- 无同案人则注明并跳过；有则
role = "codefendant"，同样要 full_text
5. 证人证言（witness-statement-extractor）
role = "witness"；金额/账户/日期等细节原样保留在 full_text
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 · 109 lines · 90 tokens per session scan A 19ae9bafbd15
vibelawyer-review is a skill published in the GitHub repository Jack-mi/vibelawyer (0 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,322 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
extract-nda-and-generate-checklist
Extract key terms from a non-disclosure agreement, then generate a compliance checklist spreadsheet tracking obligations and deadlines.
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
document-python-direct
Use direct Python execution for reliable spreadsheet and document/PDF generation operations.
kordoc
A command-line and server tool for reading and creating Korean official documents, including HWP, HWPX, PDF, DOCX, and spreadsheet files. It can convert documents to Markdown and create or update HWPX files.