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 taxueseek/fund-investment-guide --skill invest-discussgit clone --depth 1 https://github.com/taxueseek/fund-investment-guideWrote 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/taxueseek/fund-investment-guide/invest-discuss)<a href="https://agentmods.dev/skills/taxueseek/fund-investment-guide/invest-discuss"><img src="https://agentmods.dev/badge/skills/taxueseek/fund-investment-guide/invest-discuss/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/taxueseek/fund-investment-guide/invest-discuss"><img src="https://agentmods.dev/badge/skills/taxueseek/fund-investment-guide/invest-discuss.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 | $0.00067 | $0.00921 |
| Opus 5.5 | $0.00027 | $0.00368 |
| Sonnet 5.5 | $0.00013 | $0.00184 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
invest-discuss 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.
What it actually says
大师会诊
单一视角必然盲视。让四种投资思维同时审视你的标的。
四种视角
| 视角 | 核心问题 | 否决红线 |
|---|---|---|
| 生意视角 | 懂这门生意吗？有护城河吗？管理层靠谱吗？ | 看不懂 / 没护城河 / 管理层有问题 |
| 趋势视角 | 现在什么趋势？价格反映了多少乐观？有催化剂吗？ | 逆势而为 / 价格已透支 / 没催化剂 |
| 配置视角 | 占多少仓位？和现有持仓相关性？能承受多大回撤？ | 仓位过重 / 相关性太高 / 无法承受回撤 |
| 反向视角 | 最可能亏钱的三个场景？共识太强了吗？周期高位吗？ | 说不清亏钱场景 / 共识极端 / 周期高位 |
Phase 0：档位路由（关键词直通，零 token）
收到用户请求后，先用以下关键词表直接定位档位，不需要 LLM 判断。
| 关键词（任中一个即命中） | 直达档位 |
|---|---|
| 重仓、仔细看看、质询、准备买入、多看看 | 深度质问（重仓前自检） |
| 过会、评审、投委会、正式决策、上会 | 投委会评审（机构级决策） |
| （其他所有情况） | 快速扫描（默认，日常筛选） |
默认走快速扫描。只有明确命中上面两行时才升级档位。
三档执行规格
快速扫描（默认）：四种视角并行给立场（各200字内）+ 判官总结（评级A-D + 核心分歧 + 否决检查 + 建议仓位） 深度质问：四种视角轮流质问你——每视角3个问题，用户现场回答 → 判官给准备度评级（充分/一般/不足）+ 关键盲区 + 行动建议 投委会评审：用户提交投资备忘录（标的/仓位/逻辑/风险/退出条件）→ 四视角质询 → 视角间交锋 → 正式表决（赞成/反对/附条件通过）+ 执行条款
质量标准
每种视角必须给出：明确立场（支持/反对/观望/附条件）+ 关键理由（一句话）+ 否决检查（是否触发红线）
判官职责：识别核心分歧、信号解码（沉默/转移/保留背后的盲区）、综合评级 A（强烈推荐）→ D（反对）
绝对不要
- 不要让四种视角给出模棱两可的判断——每个视角必须站队
- 不要在快速扫描时展开长篇大论——200字内
- 不要在用户未回答质询问题时替用户假设答案
- 不要跳过否决红线检查
下游路由
| 结论 | 下一步 |
|---|---|
| 需深度个股分析（含美股） | invest-stock |
| 需基金分析 | invest-fund |
| 需配置方案 | invest-allocation |
| 需单个资产类判断 | invest-asset |
大师会诊 · 单一视角必然盲视
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 Changed · -1 lines 1f3f4341b018
- 1mo ago First seen · 76 lines · 67 tokens per session scan A 75293f2116db
invest-discuss is a skill published in the GitHub repository taxueseek/fund-investment-guide (21 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 921 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
paymob-integration
Integrate and operate Paymob payments in Egypt, UAE, KSA, and Oman — checkout, Intention API, HMAC webhooks, SDKs, plugins, refunds, reconciliation, go-live, diagnostics, and support tickets.
tushare
A Python interface to Tushare, a financial-data service providing market, company, fund, futures, and other finance-related data. It shows how to authenticate and query the service into pandas tables.
credit-analysis
A framework for analysing bonds and other fixed-income investments, including issuer credit quality, interest-rate sensitivity, credit spreads, and default risk. A credit rating estimates how likely an issuer or specific bond is to repay its debt.
investment-report-reader
Read and extract content from PDF investment reports — sell-side notes (GS/MS/JPM/UBS/Citi/BofA), 10-Ks, annual reports, fund factsheets, manager commentaries, and macro outlooks. Specialises in CHARTS, TABLES, and IMAGES that text-only extraction silently misses (most research charts are vector and invisible to…
vibe-trading
Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 79 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest →…
earnings-analysis
Institutional-quality earnings analysis for public equities. Parses 10-Qs, earnings releases, and call transcripts into a 4-layer framework (Parse → Compare → Diagnose → Decide), runs a mechanical scoring engine that produces a composite verdict across beat quality, operational health, and management signals, and…