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-onboardgit 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-onboard)<a href="https://agentmods.dev/skills/coffee-man666/mommy-chaogu/mommy-onboard"><img src="https://agentmods.dev/badge/skills/coffee-man666/mommy-chaogu/mommy-onboard/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-onboard"><img src="https://agentmods.dev/badge/skills/coffee-man666/mommy-chaogu/mommy-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 163 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.02124 |
| Opus 5 | $0.00040 | $0.01062 |
| Sonnet 5 | $0.00016 | $0.00425 |
| Haiku 4.5 | $0.00008 | $0.00212 |
Grade A, and why
mommy-onboard 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mommy Onboard
Explain the toolbox and manage the machine lifecycle. Keep two senses of "complete" separate: configuration + six bundled Skills (onboard / research / strategy / market-watch-loop / basket-analysis / food-security-analysis) + a real MCP initialize/tools-list + the privacy boundary passing means the integration is available and the user can explore freely; an investing or research goal is complete only when the user sees and understands a useful result from a flow they actually asked for. A green doctor is a legitimate end of installation, not a reason to force a workflow before the user asks for one.
Explain the toolbox
Before discussing installation, explain in the user's language:
- mommy-chaogu is a local toolbox that the current host Agent composes; it is not another LLM or a dashboard the user must learn;
- the toolbox covers A-share/US market data, supported calculations and signals, Strategy Cards, and consent-gated local monitoring;
- the user can describe an investing or trading-observation workflow in natural language, while the Agent maps it to capabilities that actually exist;
- it does not execute trades, prove profitability, or run arbitrary custom indicators.
Do not require the user to choose a research / strategy / indicator / monitoring path before installation. Move from the explanation to the install/permission plan, and let the user decide what to ask for once the connection is verified.
For a custom indicator or workflow the user mentions in passing, preserve the exact formula and intent. Do not substitute a similar supported indicator. Anything the available data and tools cannot implement must remain manual or unavailable.
Check managed-host compatibility
The managed lifecycle supports only claude, kimi, cline, and codex. Run
mommy agent detect --json only to detect those hosts. OpenClaw, Hermes, and other MCP hosts are not
valid --host values today.
For an unsupported host, do not invent detection, configuration paths, Skill destinations, doctor
success, or an installation command. Explain that mommy-chaogu exposes a portable stdio MCP server
but this host is not automated by mommy agent yet. Prepare a manual host-specific plan only after
verifying the host's current documentation and listing exact changes; otherwise stop before host
modification. The user may separately approve installing only the base CLI.
What ships with it
1 file 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 · 178 lines · 80 tokens per session scan A e4dfa1280f64
mommy-onboard 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 2,124 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.