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 zhanglunet/qcc --skill qcc-basic-profilegit clone --depth 1 https://github.com/zhanglunet/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/zhanglunet/qcc/qcc-basic-profile)<a href="https://agentmods.dev/skills/zhanglunet/qcc/qcc-basic-profile"><img src="https://agentmods.dev/badge/skills/zhanglunet/qcc/qcc-basic-profile/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/zhanglunet/qcc/qcc-basic-profile"><img src="https://agentmods.dev/badge/skills/zhanglunet/qcc/qcc-basic-profile.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 | $0.00206 | $0.01017 |
| Opus 5.5 | $0.00082 | $0.00407 |
| Sonnet 5.5 | $0.00041 | $0.00203 |
| Haiku 4.5 | $0.00021 | $0.00102 |
Grade A, and why
qcc-basic-profile 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 1mo 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.
What it actually says
qcc-basic-profile — 工商基础摘要
何时用
- 第一次接触某家公司,需要 5 分钟内了解概貌
- 给合同 / 招标 / 入库 / 法务对接 准备资料
- 校验对方提交的"营业执照副本扫描件"信息真伪
- 把多个工商字段(8 个 tool)一次性聚合,免去逐字段逐工具调用
不用的场景
- 只是想知道一个具体字段(如法定代表人) → 可以直接调
qcc-company:get_company_registration_info - 需要历史变更轨迹 → 用
qcc-ownership-trace(里面会调get_change_records) - 需要司法 / 失信 / 限消查询 → 用
qcc-risk-screen
调用流程
步骤 0(如用户输入非 USCC):走 qcc-anchor 拿到 USCC。
步骤 1-8(均以 USCC 作 searchKey,可并行):
| 序 | tool | 输出字段(节选) | 用途 |
|---|---|---|---|
| 1 | get_company_registration_info |
法代 / 注册资本 / 实缴 / 类型 / 注册地址 / 经营范围 / 登记机关 | 核心 — 唯一不能省 |
| 2 | get_company_profile |
QCC 自有简介 + 行业归类 | 业务一句话理解 |
| 3 | get_contact_info |
电话 / 邮箱 / 网址列表(含 ICP) | 客服 / 法务 / BD 对接 |
| 4 | get_key_personnel |
董事 / 监事 / 经理 / 财务负责人 | 看治理结构 |
| 5 | get_tax_invoice_info |
纳税人识别号 / 开户行 / 账号 | 开发票 / 转账校验 |
| 6 | get_branches |
分支机构(存续 / 注销 / 负责人 / 地区) | 看实际经营布局 |
| 7 | get_listing_info |
A股 / 港股 / 美股 / 新三板 | 看是否上市 / 上市主体 |
| 8 | get_annual_reports |
历年年报(社保人数 / 联系信息历史) | 人员规模趋势 + 自报口径 |
输出契约
basic_info: {法定代表人, 注册资本, 实缴, 成立日期, 登记状态, 企业类型, 经营期限, 国标行业}
profile: {简介, QCC 行业归类}
addresses: {注册地址, 通信地址, 登记机关}
contacts: {电话: [...], 邮箱: [...], 网址: [...]}
key_people: [{姓名, 职务, 持股}]
tax: {纳税人识别号, 开户行, 账号, 纳税人资质}
branches: {存续: [...], 注销: [...]}
listing: null | {上市地, 代码, 简称}
annual: {社保趋势: [{年度, 人数}], 资产负债: [企业是否公示]}
注意
- 母公司常常把"营业总收入 / 利润 / 资产"选择不公示,如需财务数字优先用
qcc-operation-pulse(融资 / 招标 / 资质)或外部审计报告 - 大公司的"参保人数"是单体母公司口径,不代表集团总人数(子公司各自单算)
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.
- 1mo ago First seen · 61 lines · 206 tokens per session scan A f5edbf070161
qcc-basic-profile is a skill published in the GitHub repository zhanglunet/qcc (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 206 tokens to every session and 1,017 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
legal-drafting
A guide for drafting common legal documents used in mainland China, including court filings, lawyer letters, legal opinions, and contract drafts. It marks facts, amounts, legal grounds, and other details that still need verification.
legal-due-diligence
A legal review aid for examining a batch of transaction or due-diligence documents in a consistent format. Due diligence is the process of checking documents and risks before a deal or other important decision.
legal-compliance
A China-mainland compliance review guide for products, business activities, and marketing claims. It checks areas such as the Personal Information Protection Law (PIPL), data security, intellectual property, third parties, industry rules, and AI governance.
legal-reasoning
A legal-analysis aid that organizes a case into issue, rule, application, and conclusion, a method often called IRAC. It separates rules that have been verified from general legal ideas that still need checking.
contract-review
A contract review guide that examines agreements for risky or missing terms. It explains concerns in plain language and suggests possible changes, but is not a lawyer’s final legal opinion.
legal-search
A research aid for finding and citing current mainland Chinese laws, administrative regulations, judicial interpretations, and guiding cases. It distinguishes binding legal rules from cases that courts should refer to but are not legally binding in the same way.