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 zj-unicom-ai/UniEmployee --skill unicom-presale-faqgit clone --depth 1 https://github.com/zj-unicom-ai/UniEmployeeWrote 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/zj-unicom-ai/uniemployee/unicom-presale-faq)<a href="https://agentmods.dev/skills/zj-unicom-ai/uniemployee/unicom-presale-faq"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/unicom-presale-faq/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/zj-unicom-ai/uniemployee/unicom-presale-faq"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/unicom-presale-faq.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 | $0.00063 | $0.00568 |
| Opus 5 | $0.00032 | $0.00284 |
| Sonnet 5 | $0.00013 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
unicom-presale-faq 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 7d 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
浙江联通售前咨询规程
适用范围
用户询问以下内容时使用本技能：
- 套餐资费（5G 套餐、融合宽带、互联网卡、孝心卡/校园卡等特色套餐）
- 办理条件与流程（新入网、套餐变更、合约期规则、违约金）
- 携号转网（资格查询、授权码、办理流程）
- 靓号规则（预存、最低消费、协议期）
- 销户/异地办理、话费与积分、充值优惠
- 政企业与集团业务（统付、专线、物联网）
- 增值业务与国际漫游（流量包、5G 消息、视频彩铃）
不适用范围（这些场景走其他路径）
- 用户明确投诉、表达不满 → 登记工单（create_ticket）
- 需要人工办理的复杂业务 → 引导至营业厅 / 10010 / 联通 APP
执行步骤
- 理解用户需求，定位主题（套餐资费 / 办理流程 / 政策规则）
- 调用 kb_search 检索知识库，关键词取自用户问题中的业务名和主题 （如"5G套餐 资费"、"携号转网 流程"、"大王卡 免流"）
- 仅依据检索结果回答，资费数字、流程步骤必须与知识库一致，禁止编造
- 检索不到时，明确告知"这个信息我需要核实"，建议拨打 10010 或到营业厅确认
- 涉及合约、违约金、靓号协议等有法律效力的内容时，提醒用户以办理时的协议条款为准
回答风格
- 先给直接结论（多少钱/能不能办），再给条件和流程
- 套餐对比用表格呈现（月费/流量/通话/合约期）
- 主动给出下一步行动建议（如"可以在联通 APP 首页搜索 XX 直接办理"）
- 资费可能随时间调整，涉及具体价格时提示"以办理页面实时展示为准"
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.
- 7d ago First seen · 35 lines · 63 tokens per session scan A 11f3a5109dc1
unicom-presale-faq is a skill published in the GitHub repository zj-unicom-ai/UniEmployee (93 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 568 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
action-contract-execution-feedback-loop
A specification method for making a business action into a tool an AI agent can call safely. It defines the action’s inputs, outputs, permissions, preconditions, expected effects, error handling, and audit information.
five-ring-ontology-engineering-lifecycle
A five-stage method for planning an enterprise ontology, a structured model of the concepts and relationships used across a business, from source material through ongoing use.
ontology-ai-application-pattern-selection
A method for choosing how an AI system should handle a business problem after deciding that an ontology—a structured map of concepts and relationships—is suitable. It compares patterns such as workflow automation, decision support, knowledge answering, collaboration, and continuous planning.
ontology-ai-scenario-fit-and-spike
A method for deciding whether an ontology is suitable for an enterprise AI scenario and testing that choice with a small end-to-end sample. An ontology is a structured model of concepts, rules, and relationships.
ontology-constraint-and-knowledge-injection
A method for deciding how an ontology’s knowledge should reach an AI model: directly in its instructions, through RAG, or through fine-tuning. RAG retrieves relevant information at answer time; fine-tuning changes the model using training examples.
ontology-golden-case-testing
A testing method for an ontology, which is a structured model of business concepts and rules. It starts with real business questions and expected answers, then adds boundary, missing-data, conflict, permission, and regression tests.