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 agentmods add skills/opencue/cuecards/cn-statsnpx skills add opencue/cuecards --skill cn-statsgit clone --depth 1 https://github.com/opencue/cuecardsWrote 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/opencue/cuecards/cn-stats)<a href="https://agentmods.dev/skills/opencue/cuecards/cn-stats"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/cn-stats.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00996 |
| Opus 5 | $0.00017 | $0.00498 |
| Sonnet 5 | $0.00007 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
cn-stats scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
ROOT_ID=$(curl "$BASE_URL/new/queryIndexTreeAsync?pid=&code=1" | jq -r '.data[0]._id') This is a copy
100% identical to cn-stats — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
国家统计局
# 全局环境变量
BASE_URL='https://data.stats.gov.cn/dg/website/publicrelease/web/external'
# 获取指标分类根节点ID
ROOT_ID=$(curl "$BASE_URL/new/queryIndexTreeAsync?pid=&code=1" | jq -r '.data[0]._id')
# code: {1:月度数据, 2:季度数据, 3:年度数据, 4:分省月度数据, 5:分省季度数据, 6:分省年度数据}
# {7:主要城市月度价格, 8:主要城市年度数据, 9:港澳台月度数据, 10:港澳台年度数据}
# {12:三大经济体月度数据, 13:国际市场月度商品价格, 14:主要国家年度数据}
# 获取指标分类子节点
curl "$BASE_URL/new/queryIndexTreeAsync?pid=$ROOT_ID&code=1" | jq -r '.data[] | {_id, name, type, isLeaf}'
# 获取指标列表
curl "$BASE_URL/new/queryIndicatorsByCid?cid=$NODE_ID&dt=&name="
# 搜索指标列表
curl "$BASE_URL/new/queryIndicatorsByCid" -G --data-urlencode "cid=&dt=&name=<关键词>&rootId=$ROOT_ID"
# 获取统计数据 - 多指标
curl "$BASE_URL/getEsDataByCidAndDt" \
-H 'Content-Type: application/json;charset=UTF-8' \
-H 'Referer: https://data.stats.gov.cn/dg/website/page.html' \
--data-raw '{
"cid": "分类ID",
"indicatorIds": ["指标ID1","指标ID2"],
"daCatalogId": "",
"das": [{"text":"全国","value":"000000000000"}],
"showType": "1",
"dts": "",
"rootId": "根节点ID"
}' | jq -r '
.data[] |
.name as $year |
.values[] |
[$year, ._name, .value // "-", .du_name] |
@tsv
'
# 获取地区分类
curl "$BASE_URL/getDaCatalogTreeByIndicatorCid?indicatorCid=$NODE_ID"
# 获取地区列表
curl "$BASE_URL/getDasByDaCatalogId?daCid=$DA_CATELOG_ID&rootId=$ROOT_ID" | jq -r '.data[] | [.name_value,.name_text] | @tsv'
# 获取国内全部省份
curl "$BASE_URL/getDasByDaCatalogId?daCid=a10dceae75d245008bf4b9a0e6fe1d55" | jq -r '.data[] | [.name_value,.name_text] | @tsv'
# 获取国内大中城市
curl "$BASE_URL/getDasByDaCatalogId?daCid=44016f1bffeb4ea49fe34e100c6415fb" | jq -r '.data[] | [.name_value,.name_text] | @tsv'
# 获取统计数据 - 多地区
curl "$BASE_URL/getEsDataByCidAndDt" \
-H 'Content-Type: application/json;charset=UTF-8' \
-H 'Referer: https://data.stats.gov.cn/dg/website/page.html' \
--data-raw '{
"cid": "分类ID",
"indicatorIds": ["指标ID"],
"daCatalogId": "",
"das":[{"text":"上海市","value":"310000000000"},{"text":"北京市","value":"110000000000"}],
"showType": "3",
"dts": ["202301MM-202605MM"],
"rootId": "根节点ID"
}' | jq -r '
.data[] |
.name as $year |
.values[] |
[$year, ._name, .value // "-", .du_name] |
@tsv
'
# 全局数据查询
curl "$BASE_URL/query" -G --data-urlencode 'search=<关键词>&code=&pagenum=1&pageSize=15'
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 · 87 lines · 34 tokens per session scan A 51a7513f4b79
cn-stats is a skill published in the GitHub repository opencue/cuecards (5 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 996 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to cn-stats, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
release
Cut a paad release — pick the semver bump from what is in [Unreleased], run make release, merge, tag, and verify the published plugin.
backlog
EXPERIMENTAL. Use when working the project-wide out-of-scope backlog at paad/code-reviews/backlog.md — cleaning it of entries that are already fixed or gone, or picking the next entry and fixing it end-to-end. Not for producing backlog entries — that is /agentic-review — and not for reviewing a branch diff.
agentic-architecture
Use when assessing the architectural health of a codebase — before a major refactor, when onboarding to an unfamiliar repo, after rapid growth, when planning a redesign, or to surface structural strengths and risks before they become expensive. Not for fixing what it finds, and not for reviewing a branch diff.
agentic-review
Use when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review. Not for codebase structure, not for code style, and not for fixing what it finds.
ccg-annotate
AI-driven annotation workflow for adding structured metadata to code. Annotations are indexed and searchable via FTS.
ccg-docs
Generate Markdown documentation from code graphs, build RAG indexes for AI consumption, and lint documentation quality.