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 coffee-man666/mommy-chaogu --skill basket-analysisgit clone --depth 1 https://github.com/coffee-man666/mommy-chaoguWrote 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/coffee-man666/mommy-chaogu/basket-analysis)<a href="https://agentmods.dev/skills/coffee-man666/mommy-chaogu/basket-analysis"><img src="https://agentmods.dev/badge/skills/coffee-man666/mommy-chaogu/basket-analysis/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/coffee-man666/mommy-chaogu/basket-analysis"><img src="https://agentmods.dev/badge/skills/coffee-man666/mommy-chaogu/basket-analysis.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 | $0.00435 | $0.03826 |
| Opus 5 | $0.00217 | $0.01913 |
| Sonnet 5 | $0.00087 | $0.00765 |
| Haiku 4.5 | $0.00044 | $0.00383 |
Grade A, and why
basket-analysis scanned grade A with 2 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 12d 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.
- `retry_kline()` → built-in (used by agent when fetching K-line via urllib) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **`retry_with_backoff(fn, max_attempts=3, initial_delay=2, backoff_factor=2, max_delay=30, jitter=0.3)`** — generic decorator. Retries on `URLError`, `HTTPError`, `TimeoutError`, `ConnectionError`, `OSError`, `subproce How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Basket Analysis (通用 A 股主题篮子分析)
End-to-end pipeline that takes a trading day (default: today, Beijing time) and a theme name (e.g. 粮食安全, 半导体, 煤炭, 创新药), and produces a packaged set of analysis artifacts for that theme's basket.
主题配置 (theme config)
所有主题共用同一套技术方法 (10 步 procedure). 主题间的差异 (篮子, 4 变量触发, 全局背景, 搜索关键词) 都封装在 references/themes/{theme}.md 配置里.
当前内置主题:
references/themes/food-security.md— 粮食安全/危机 (35 只, FAO + 黑海 + 厄尔尼诺 + 399365 PE)references/themes/_template.md— 新主题模板 (复制此文件 + 改 4 变量即可)
加新主题: cp references/themes/_template.md references/themes/my-theme.md 然后填:
basket.source(mommy CLI / SQL group / 手动列表)trigger_variables(4 个变量 + 搜索 query)global_context_searches(必查的全局背景)domain_keywords(主题关键词, 用于篮子筛选)
Inputs to collect
Ask the user only what the procedure cannot infer:
- Theme name (default:
food-security). 必填, 决定 basket + 4 变量 + 报告标题. - Trading day (default: today Beijing time). Required if back-fill ("复盘 8/15").
- Run label (default: auto-timestamp).
- Mark as final (default: false if multiple runs already today, true if first or only run).
If the user is vague ("复现刚才的分析"), use the last-used theme + today's date.
Procedure
-
Resolve theme + trading day + data freshness
- Theme: from user input (or default
food-security). Loadreferences/themes/{theme}.mdto get basket source + 4 variable definitions + search queries. - Trading day:
today_bj = now(Asia/Shanghai).strftime("%Y-%m-%d")+now_bj_isowith+08:00. - Detect post-market: if
now_bj.time() > 15:05, markis_market_close=true. Otherwisemid-day (Beijing). - Why: theme drives everything downstream; data label is what readers see.
- Theme: from user input (or default
-
Verify basket exists for the theme
- Read the theme config's
basket.source. Ifmommy <cli>, runmommy <cli> listandmommy <cli> stats. Ifmanual, ensure the list is provided. Ifbasket_total≠len(pulled), may need to seed first. - Confirm 4 chain/subcategory (or whatever the theme config requires). If missing, run
mommy <cli> seedfirst. - Why: the basket is the canonical reference; missing seed → downstream flows are incomplete.
- Read the theme config's
What ships with it
11 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.
- references/data_sources.md 7.1 KB
- references/output_format.md 7.3 KB
- references/themes_api.md 2.4 KB
- references/themes/_template.md 4.7 KB
- references/themes/food-security.md 4.8 KB
- scripts/analyze.py 40 KB runs code
- scripts/html_render.py 78 KB runs code
- scripts/package_zip.py 7.1 KB runs code
- scripts/README-retry.md 4.2 KB
- scripts/retry.py 10 KB runs code
- scripts/text_render.py 15 KB runs code
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.
- 12d ago First seen · 203 lines · 435 tokens per session scan A 5a0138efd60a
basket-analysis is a skill published in the GitHub repository coffee-man666/mommy-chaogu (47 stars, last pushed today), licensed MIT. It adds 435 tokens to every session and 3,826 once invoked, about $0.0022 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.