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 mommy-researchgit 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/mommy-research)<a href="https://agentmods.dev/skills/coffee-man666/mommy-chaogu/mommy-research"><img src="https://agentmods.dev/badge/skills/coffee-man666/mommy-chaogu/mommy-research/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/mommy-research"><img src="https://agentmods.dev/badge/skills/coffee-man666/mommy-chaogu/mommy-research.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 | $0.00080 | $0.01672 |
| Opus 5 | $0.00040 | $0.00836 |
| Sonnet 5 | $0.00016 | $0.00334 |
| Haiku 4.5 | $0.00008 | $0.00167 |
Grade A, and why
mommy-research 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mommy Research
Use the mommy-chaogu MCP server as the source of truth for current market data and local
research memory. Let the current Coding Agent do the reasoning; do not invoke another LLM through
shell commands or APIs.
Choose the workflow
- Market overview: call
research_market_brief（A 股大盘 + 板块）或research_us_market（美股三大指数 + VIX + 10Y 利率）。 - One stock: resolve a six-digit code, then call
research_stock（美股用字母代码，如 AAPL）。 - US index / rate / VIX: call
get_quotewith a^-prefixed code（^GSPC/^IXIC/^DJI/^VIX/^TNX等）。 - Sector or theme: call
research_sectorwith the user's keyword. - Money flow: call
research_money_flowwith a six-digit code. - Portfolio: call
research_portfolioonly when the tool is published and the user requested personal analysis. - Unsupported or highly specific questions: compose the primitive
get_*tools directly.
Prefer one high-level research_* call over manually recreating the same sequence. The returned
evidence pack is deterministic and contains no hidden LLM summary.
At the first research call in a session, call get_memory_health when it is available. In a
personal connection, use task-scoped holdings, watchlists, alerts, and memory when they help the
request; do not fetch unrelated personal data. Treat status=degraded as usable: exact code/scope
and keyword retrieval still work without an embedding model. Pass record_session=false unless the
user has explicitly asked to keep the research process. Saving a conclusion is a separate choice.
美股研究（US Stocks）
代码约定（Yahoo 风格）：
- 美股个股：字母代码，如
AAPL/NVDA/BRK.B（research_stock直接可用）。 - 指数 / 利率 / VIX：
^前缀——^GSPC标普500、^IXIC纳指综合、^DJI道指、^VIX恐慌指数、^TNX10 年期美债利率、^FVX5 年、^TYX30 年、^IRX13 周国库券。
数据源与限制：
- 个股走 Massive/Polygon（需
MASSIVE_API_KEY）；^前缀指数/利率/VIX 走 Yahoo Finance（无需 key）， 二者在 fallback 链中自动切换，agent 无需感知。 - 美股没有资金流（money flow）、板块、龙虎榜、基本面这些 A 股概念——
research_stock对美股返回的 证据包里对应条目会缺失或为空，属正常，不要当成故障。 - 美股大盘概览用
research_us_market：返回标普500 / 纳指综合 / 道指 / VIX / 10 年期美债利率的证据包； 更细的个股用research_stock（字母代码）。
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.
- 12d ago First seen · 114 lines · 80 tokens per session scan A eeb31a522c95
mommy-research is a skill published in the GitHub repository coffee-man666/mommy-chaogu (47 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,672 once invoked, about $0.0004 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 2026-08-30.
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.