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 tradecatlabs/fatecat --skill meihua-divination-maingit clone --depth 1 https://github.com/tradecatlabs/fatecatWrote 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/tradecatlabs/fatecat/meihua-divination-main)<a href="https://agentmods.dev/skills/tradecatlabs/fatecat/meihua-divination-main"><img src="https://agentmods.dev/badge/skills/tradecatlabs/fatecat/meihua-divination-main/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/tradecatlabs/fatecat/meihua-divination-main"><img src="https://agentmods.dev/badge/skills/tradecatlabs/fatecat/meihua-divination-main.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 | $0.00086 | $0.01151 |
| Opus 5.5 | $0.00034 | $0.00460 |
| Sonnet 5.5 | $0.00017 | $0.00230 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
meihua-divination 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 1mo 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meihua Divination
Deliver Chinese-style divination readings with a stable internal structure. Treat the reading as symbolic trend analysis, not infallible prophecy.
Core workflow
- Classify the question using
references/question-types.md. - Extract the minimum necessary inputs:
- question topic
- current situation
- desired outcome
- main obstacle or hesitation
- optional time horizon
- Generate a stable symbolic frame with
scripts/generate_reading_seed.pyandscripts/cast_symbols.py. - Interpret the frame using:
references/symbol-system.mdreferences/element-relations.mdreferences/reasoning-patterns.mdreferences/scenario-patterns.mdwhen the question matches a common real-life scene
- Calibrate tone and density with
references/examples.md,references/signature-lines.md, andreferences/traditional-meihua-notes.md. - Prefer using
scripts/render_reading.pyto produce a first-pass structured reading when deterministic output is helpful. - After logic or phrasing changes, run
scripts/smoke_test.shas a quick regression check. - Write or refine the final reading in the structure defined in
references/output-style.md. - Apply
references/safety-boundaries.mdbefore finalizing.
Reading modes
Support these modes in v0.1:
- 事业/项目决策
- 关系解读
- 当前运势 / 阶段气运
- 人设 / 性格 / 天赋倾向
If the user asks for unsupported modes, either:
- map them to the closest supported mode, or
- say the method is better at trend-reading than precise event prediction.
Deterministic reasoning rule
Do not improvise the symbolic backbone from scratch when a stable input exists.
- If enough text context exists, derive a stable seed first.
- Use the seed to generate the same symbolic frame for the same input.
- Variation should come from richer user context, not random drift.
This keeps the reading coherent across retries.
Required reasoning shape
Every full reading should contain these layers:
- 总断 — one-sentence overall judgment
- 断因 — why the situation looks this way
- 断势 — short-term / medium-term tendency
- 断法 — practical advice on what to do or avoid
- 签语 — one concise Chinese-style closing line
What ships with it
20 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.
- .gitignore 27 B
- assets/phrase-library.json 16 KB
- assets/templates/deep-reading.md 253 B
- assets/templates/quick-reading.md 64 B
- assets/templates/standard-reading.md 160 B
- README.md 9.7 KB
- references/element-relations.md 2.0 KB
- references/examples.md 3.4 KB
- references/output-style.md 1.7 KB
- references/question-types.md 1.4 KB
- references/reasoning-patterns.md 5.0 KB
- references/safety-boundaries.md 1.2 KB
- references/scenario-patterns.md 5.3 KB
- references/signature-lines.md 1011 B
- references/symbol-system.md 2.5 KB
- references/traditional-meihua-notes.md 4.4 KB
- scripts/cast_symbols.py 3.0 KB runs code
- scripts/generate_reading_seed.py 760 B runs code
- scripts/render_reading.py 35 KB runs code
- scripts/smoke_test.sh 3.3 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.
- 1mo ago First seen · 154 lines · 86 tokens per session scan A 34df6baddb16
meihua-divination is a skill published in the GitHub repository tradecatlabs/fatecat (201 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,151 once invoked, about $0.0003 per session on Opus 5.5. 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
geo-optimizer-skill
Run geo audit first. It scores the site 0–100 across 9 categories and generates a prioritized action list.
technocore-chat
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…
yueyuan
A specialised BaZi analysis system, where BaZi is a Chinese birth-chart method based on birth date and time. It is designed for structured analysis with explicit uncertainty and requires the user to check the chart before deeper interpretation.
liki
A Chinese-language traditional divination and naming toolkit covering systems such as Bazi, Ziwei Doushu, Liuyao, Qimen, Feng Shui, and Chinese name selection. It presents these as traditional-culture interpretations, not professional advice.
bazi
A reference skill describing the rules and concepts of BaZi, or Four Pillars, a traditional Chinese birth-chart system. It covers areas such as chart structure, useful elements, relationships between chart components, and time periods.
liki-bazi
A Chinese traditional fortune-reading tool using BaZi, a birth-chart system based on birth details, and Zi Wei Dou Shu, another Chinese astrology system. It can examine life areas and yearly trends, but its conclusions are for cultural reference, not professional advice.