Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-opennpx agentmods add skills/thomasmoreai/legal-skills-open/bankruptcy-monitor-qccWrote 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/bankruptcy-monitor-qcc)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/bankruptcy-monitor-qcc"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/bankruptcy-monitor-qcc/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/bankruptcy-monitor-qcc"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/bankruptcy-monitor-qcc.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 | $0.00496 | $0.10083 |
| Opus 5.5 | $0.00198 | $0.04033 |
| Sonnet 5.5 | $0.00099 | $0.02017 |
| Haiku 4.5 | $0.00050 | $0.01008 |
Grade A, and why
bankruptcy-monitor-qcc 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 23d 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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Resource 条件读取（跨客户端兼容）
- 每个新会话首次执行本 SKILL 时，如客户端支持 MCP Resources，先执行资源发现并读取
qcc://skills/index、qcc://terminology/core、qcc://policy/data-discipline、qcc://policy/entity-anchoring与qcc://skill/bankruptcy-monitor/tool-binding。 - 同一会话已成功读取且 checksum 未变化时无需重复读取 Tool Binding；新会话不得沿用上一会话的读取状态。
- 生成最终报告前重新读取
qcc://skill/bankruptcy-monitor/report-template，并把它作为严格填空骨架；多轮会话后也必须在生成前重读。 - Resource 不会因连接 MCP 自动注入；AI 必须主动发现并精确读取。读取失败、客户端不支持或 URI 不可用时，不得阻断任务，继续使用 A 层与本 SKILL 内联规则。
- Resource 只提供稳定知识与模板，不替代
tools/list的实时权限、Description 和 Input Schema，也不保证客户端多轮后必然遵循。
🔍 风险维度扫描 · 先扫后钻（统一规范 · 2026-06-08 · 对齐 A 层铁律 5-A）
本 SKILL 凡涉及“一次性排查 ≥ 2 个企业风险维度”（司法风险 / 失信 / 被执行 / 限高 / 经营异常 / 行政处罚 / 破产 / 担保 / 税务 等 qcc-risk 维度），一律按“先扫后钻”执行，禁止逐个原子风险工具散弹枪式调用（慢 / 贵 / 多为无效调用）：
第 1 步 · 分诊（先扫）：先调
mcp__qcc-risk__get_company_risk_scan（企业风险扫描）一次返回企业自身 35 项风险维度的命中计数（脱水版：有 / 无 + 条数，不含明细）。第 2 步 · 下钻（后钻）：仅对
count > 0的维度，调对应原子风险工具取明细（具体工具见本 SKILL 工作流 / 术语对照表）。示例：scan 显示「失信 2、被执行 1、其余 0」→ 只下钻mcp__qcc-risk__get_dishonest_info+mcp__qcc-risk__get_judgment_debtor_info。
count = 0的维度：直接判定“无记录”，不再调用该维度原子工具。明确单一维度问句（仅查某一项，如“有没有失信”）→ 直接调对应原子工具，无需先扫（对应 A 层铁律 5-A 路由 3）。
scan 只分诊、不出明细；要明细必须下钻原子工具。风险结论只陈述“命中维度 + 计数 / 明细”客观事实，不替客户判定“能不能合作 / 可不可开户”。
先扫后钻发生在实体锚定确定唯一主体之后；简称 / 品牌名仍须先
mcp__qcc-company__get_company_by_query锁定主体，再 scan。可引用已上线的聚合风险扫描工具：
get_company_risk_scan（企业自身）、get_executive_risk_scan（董监高个人）、get_company_related_risk_scan（企业关联）、get_executive_related_risk_scan（人关联）；关联扫描遵守单层预警 · 禁自动下钻；仍不得引用任何尚未上线的工具。【定性必须有下钻证据】 对任一风险维度给出定性判断（如“多为原告身份 / 属正常维权”“轻微合规瑕疵”“诉讼活跃度正常”等）之前，必须已下钻该维度的明细工具、拿到支撑数据；未下钻则只陈述 scan 计数并标注“（未取明细）”，禁止凭 scan 计数或印象给定性。例：scan 显示「裁判文书 77」但未下钻
mcp__qcc-risk__get_judicial_documents→ 只能写“裁判文书 77 条（未取明细）”，不得写“多为原告身份、属正常维权”；如需该定性，必须先下钻get_judicial_documents（可按role取原告 / 被告分布）再下结论。📌 year 留空拿全量 · 禁逐年循环（防 year 散弹枪 · 2026-07-01）：立案 / 裁判文书 / 开庭公告 / 法院公告等带
year过滤参数的诉讼类工具，取全量时year一律留空——接口在 year 缺省时即一次返回全部年份；严禁为“覆盖多年”而逐年（2024、2023 … 直至成立年）循环调用同一工具（实测曾逐年一直调到 1976、单次运行 60+ 次冗余调用）。需要按年做趋势分桶时，基于“留空一次拿回的全量列表”在报告侧自行分桶；role/notice_type等其他过滤参数同理，取全量时留空；仅当明确限定某一年 / 区间时才传year。qcc-history / qcc-executive 的同名历史 / 个人诉讼工具同理，不逐年循环。
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.
- 23d ago Changed · +186 lines · +61 tokens per session d21d56d4af24
- 1mo ago First seen · 200 lines · 435 tokens per session scan A a79f7740330c
bankruptcy-monitor-qcc is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 496 tokens to every session and 10,083 once invoked, about $0.0020 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.
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…