Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/godisego/hot-moneynpx agentmods add skills/godisego/hot-money/deep-analysisWrote 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/godisego/hot-money/deep-analysis)<a href="https://agentmods.dev/skills/godisego/hot-money/deep-analysis"><img src="https://agentmods.dev/badge/skills/godisego/hot-money/deep-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/godisego/hot-money/deep-analysis"><img src="https://agentmods.dev/badge/skills/godisego/hot-money/deep-analysis.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00242 | $0.15541 |
| Opus 5 | $0.00121 | $0.07770 |
| Sonnet 5 | $0.00048 | $0.03108 |
| Haiku 4.5 | $0.00024 | $0.01554 |
Grade A, and why
deep-analysis 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 9d 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.
This is a copy
94% identical to deep-analysis — 117 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 — 1,042 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stock Deep Analysis · 深度分析工作流 v2.2
你正在扮演一位首席股票分析师。你身边有一套完整的量化工具箱,但最终的判断和叙事必须你来写。 脚本负责算数,你负责推理和下结论。
🎯 角色定位(非常重要)
- 你不是脚本的搬运工 — 不要只把
cat xxx.json的结果往报告里贴。 - 你是分析师 — 你读原始数据 + 量化结果,然后用自己的判断串起一个有冲突感、有洞察的叙事。
- 脚本给你提供 5 类产物:
- 原始数据 (Task 1 · 22 维 fetcher)
- 机构建模结果 (Task 1.5 · DCF/Comps/LBO/3-Stmt/IC Memo/Porter 等 17 种方法的计算输出)
- 51 人评委量化裁决 (Task 3 · 每人引用具体规则)
- 数据完整性报告 (哪些字段缺失 / 哪些降级)
- 可审计的 methodology_log (每一步计算的推导链)
- 你必须在 Task 2 和 Task 4 做真正的定性判断(详见下面每个 Task 的 "你的判断环节")。
⛔ 硬性门控规则(违反即停止)
- 必须按 Task 1 → 1.5 → 2 → 3 → 4 → 5 顺序。前一 Task 的产物 JSON 不存在时禁止开始下一步。
- 数据必须来自脚本或真实 web search,禁止编造数字。任何推断都要标注来源。
- 每个 Task 完成后打进度条(20 字符宽度),让用户看到节奏。
- Task 5 报告组装禁止空泛话术("基本面良好" / "前景广阔" / "值得关注" — 这三个词组出现即失败)。必须用有冲突感的定量金句,例:
- ✅ "DCF 说高估 28%,但 LBO 说 PE 买方仍赚 21% IRR — 这个分歧值得琢磨"
- ❌ "估值合理,基本面良好"
- 矛盾必须呈现,不准和稀泥:DCF 与 Comps 结论冲突时,把冲突写进报告;51 评委分歧大时,强调分歧本身是信息。
- Task 1 必须并行执行(4 个子 agent / wave),串行跑 22 个 fetcher 直接扣分。
⛔ HARD-GATE-UPDATE-PROMPT · 新版本提示(v2.14)
你必须在第一次回应用户前检查这个文件:
- 读
.cache/_global/update_prompt.md(不存在 = 无需提示,跳过即可) - 若存在 · 把文件完整内容作为 第一条消息 展示给用户
- 用
AskUserQuestion或自然语言收集用户回答(y / s / n) - 调用
python3 -c "from lib.update_check import handle_answer; print(handle_answer('<ans>', '<latest>'))"把用户回答写回状态文件 · latest 从提示文案里的版本号提取 - 处理完删除
.cache/_global/update_prompt.md,这样同一会话不会重复弹 - 根据用户选择:
y→ 告诉用户按 README 安装章节的命令执行(Claude Code:/plugin update stock-deep-analyzer· git clone:cd UZI-Skill && git pull· Hermes:hermes skills update wbh604/UZI-Skill/skills/deep-analysis),然后继续用户原请求s→ 直接继续用户原请求(handle_answer 已记 skip 到 cache)n→ 直接继续用户原请求
如果用户没有原请求(首次进入会话),展示完提示后等待用户开始对话。
绝不能:
- ❌ 跳过这个检查直接回应用户的分析请求
- ❌ 把提示文案改短、改写、合并到其他消息里
- ❌ 在用户只说 "分析 XX" 时直接开跑不先展示更新提示
⛔ HARD-GATE-NAME · 股票名纠错(v2.3)
What ships with it
60 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.
- assets/avatars/bj_cj.svg 1.6 KB
- assets/avatars/buffett.svg 1.9 KB
- assets/avatars/chen_xq.svg 1.8 KB
- assets/avatars/chengdu.svg 1.8 KB
- assets/avatars/dalio.svg 1.7 KB
- assets/avatars/darvas.svg 1.9 KB
- assets/avatars/dengxiaofeng.svg 1.7 KB
- assets/avatars/druck.svg 1.7 KB
- assets/avatars/duan.svg 1.7 KB
- assets/avatars/fang_xx.svg 1.8 KB
- assets/avatars/fengliu.svg 1.9 KB
- assets/avatars/fisher.svg 1.6 KB
- assets/avatars/fs_wyj.svg 1.6 KB
- assets/avatars/gann.svg 1.9 KB
- assets/avatars/graham.svg 1.7 KB
- assets/avatars/gu_bl.svg 1.9 KB
- assets/avatars/hu_jl.svg 1.8 KB
- assets/avatars/jiao_yy.svg 1.6 KB
- assets/avatars/klarman.svg 1.9 KB
- assets/avatars/lasa.svg 1.8 KB
- assets/avatars/liu_sh.svg 1.6 KB
- assets/avatars/liuyi_zl.svg 1.6 KB
- assets/avatars/livermore.svg 1.8 KB
- assets/avatars/lynch.svg 1.6 KB
- assets/avatars/mao_lb.svg 1.8 KB
- assets/avatars/marks.svg 1.6 KB
- assets/avatars/minervini.svg 1.6 KB
- assets/avatars/munger.svg 1.8 KB
- assets/avatars/ningbo_st.svg 1.9 KB
- assets/avatars/oneill.svg 2.1 KB
- assets/avatars/robertson.svg 1.8 KB
- assets/avatars/shaw.svg 2.0 KB
- assets/avatars/simons.svg 1.9 KB
- assets/avatars/soros.svg 1.9 KB
- assets/avatars/sun_ge.svg 1.9 KB
- assets/avatars/sunan.svg 2.2 KB
- assets/avatars/templeton.svg 1.7 KB
- assets/avatars/thiel.svg 2.0 KB
- assets/avatars/thorp.svg 1.8 KB
- assets/avatars/wang_zr.svg 2.1 KB
- assets/avatars/wood.svg 1.6 KB
- assets/avatars/xiao_ey.svg 2.1 KB
- assets/avatars/xiao_xian.svg 2.1 KB
- assets/avatars/xiezhiyu.svg 1.8 KB
- assets/avatars/xin_dd.svg 2.1 KB
- assets/avatars/yangjia.svg 2.0 KB
- assets/avatars/zhang_mz.svg 1.6 KB
- assets/avatars/zhangkun.svg 1.8 KB
- assets/avatars/zhao_lg.svg 1.8 KB
- assets/avatars/zhushaoxing.svg 1.7 KB
- assets/avatars/zuoshou.svg 1.8 KB
- assets/data-contracts.md 10 KB
- assets/disclaimer.md 1.7 KB
- assets/quality-checklist.md 2.1 KB
- assets/report-template.html 105 KB
- personas/bj_cj.yaml 951 B
- personas/buffett.yaml 2.1 KB
- personas/chen_xq.yaml 952 B
- personas/chengdu.yaml 952 B
- personas/dalio.yaml 2.0 KB
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.
- 9d ago First seen · 1,042 lines · 242 tokens per session scan A b4b4b6a94038
deep-analysis is a skill published in the GitHub repository godisego/hot-money (2 stars, last pushed 4mo ago), licensed MIT. It adds 242 tokens to every session and 15,541 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to deep-analysis, differing in 117 lines, and is treated as a copy.
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.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.