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 desirecore/market --skill ccgp-gov-procurementgit clone --depth 1 https://github.com/desirecore/marketWrote 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/desirecore/market/ccgp-gov-procurement)<a href="https://agentmods.dev/skills/desirecore/market/ccgp-gov-procurement"><img src="https://agentmods.dev/badge/skills/desirecore/market/ccgp-gov-procurement/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/desirecore/market/ccgp-gov-procurement"><img src="https://agentmods.dev/badge/skills/desirecore/market/ccgp-gov-procurement.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 | $0.00111 | $0.02335 |
| Opus 5 | $0.00056 | $0.01167 |
| Sonnet 5 | $0.00022 | $0.00467 |
| Haiku 4.5 | $0.00011 | $0.00233 |
Grade A, and why
ccgp-gov-procurement scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Key advantage**: a browser session naturally avoids the IP throttling applied to direct curl calls How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CCGP Government Procurement Search
L0: One-Sentence Summary
Input a company name (short name recommended, e.g. "华为" instead of the full legal name), search ccgp.gov.cn via Kimi WebBridge browser automation, and return a structured list of procurement announcements.
L1: Overview
- Data source: China Government Procurement search (
search.ccgp.gov.cn) - Auth: none (public search)
- Invocation: Kimi WebBridge browser automation (navigate + evaluate)
- Prerequisites: Kimi WebBridge daemon running (
127.0.0.1:10086) + browser extension connected - Key advantage: a browser session naturally avoids the IP throttling applied to direct curl calls
L2: Procedure
1. Check the WebBridge daemon
curl -s -X POST "http://127.0.0.1:10086/command" \
-H "Content-Type: application/json" \
-d '{"action":"list_tabs","session":"ccgp-query"}' --max-time 10
If unreachable, start the daemon:
~/.kimi-webbridge/bin/kimi-webbridge.exe start
2. Navigate to the search results page
Windows approach (write JSON to a temp file to avoid encoding issues):
Write C:\tmp\ccgp-nav.json:
{
"action": "navigate",
"args": {
"url": "https://search.ccgp.gov.cn/bxsearch?searchtype=1&page_index=1&bidSort=0&pinMu=0&bidType=0&dbselect=bidx&kw={company-short-name-URL-encoded}",
"newTab": true,
"group_title": "政府采购网查询"
},
"session": "ccgp-query"
}
curl.exe -s -X POST "http://127.0.0.1:10086/command" \
-H "Content-Type: application/json" \
--data-binary "@C:\tmp\ccgp-nav.json" --max-time 30
Wait 5 seconds before continuing.
3. Extract the announcement list
Write C:\tmp\ccgp-extract.json:
{
"action": "evaluate",
"args": {
"code": "(function(){var txt=document.body.innerText||'';var total=(txt.match(/共找到\\s*(\\d+)\\s*条/)||[])[1]||'?';var items=[];document.querySelectorAll('a').forEach(function(a){var t=(a.innerText||'').replace(/\\s+/g,' ').trim();if(t.includes('{company-keyword}')&&t.length>10){var li=a.closest('li')||a.closest('div');var date='';if(li){var m=(li.innerText||'').match(/\\d{4}[-:]\\d{2}[-:]\\d{2}/);if(m)date=m[0];}items.push({title:t.slice(0,80),href:(a.href||'').slice(0,100),date:date});}});return JSON.stringify({total:total,count:items.length,items:items.slice(0,10)});})()"
},
"session": "ccgp-query"
}
What ships with it
2 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.
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.
- 4d ago First seen · 204 lines · 111 tokens per session scan A 76a7d2b12f6f
ccgp-gov-procurement is a skill published in the GitHub repository desirecore/market (2 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 2,335 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
001-Frank-AI需求拆解工具
A Chinese-language workflow for turning raw customer notes, emails or chat messages into a structured list of project requirements. It separates business, feature, technical and non-functional needs, and marks their priority and dependencies.
002-Frank-AI方案润色优化工具
A Chinese-language editor for improving the wording, structure, terminology, and audience fit of sales proposals without changing their core content.
003-Frank-AI标书自查纠错工具
A Chinese-language checklist for checking a government or business bid document before submission. It reviews spelling, required responses, technical details, calculations, signatures, seals, and dates.
004-Frank-AI项目PPT智能生成工具
A Chinese-language aid for turning an AI or digital-project proposal into a presentation outline with slide titles, key points, visual suggestions, and speaking notes.
005-Frank-AI竞品分析智能拆解工具
A Chinese-language aid for researching named competitors and comparing them with your own product or proposal across areas such as functions, technology, price, service, and compliance.
006-Frank-AI数据可视化方案工具
A Chinese-language aid for turning project data into chart plans, including chart type, colors, titles, notes, insights, and drawing instructions.