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 HHFinAi/claude-equity-research-skills --skill supply-chain-pass-throughgit clone --depth 1 https://github.com/HHFinAi/claude-equity-research-skillsWrote 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/hhfinai/claude-equity-research-skills/supply-chain-pass-through)<a href="https://agentmods.dev/skills/hhfinai/claude-equity-research-skills/supply-chain-pass-through"><img src="https://agentmods.dev/badge/skills/hhfinai/claude-equity-research-skills/supply-chain-pass-through/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/hhfinai/claude-equity-research-skills/supply-chain-pass-through"><img src="https://agentmods.dev/badge/skills/hhfinai/claude-equity-research-skills/supply-chain-pass-through.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 | $0.00199 | $0.05300 |
| Opus 5 | $0.00100 | $0.02650 |
| Sonnet 5 | $0.00040 | $0.01060 |
| Haiku 4.5 | $0.00020 | $0.00530 |
Grade A, and why
supply-chain-pass-through 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supply Chain Pass-Through (v2)
Purpose
Given a secular trend, produce a mechanically-derived chain of listed beneficiaries and substantiate each link with concrete earnings evidence. The output is a thesis-grade thematic map that a PM can defend in an IC — not a vague "themes we like" list.
The skill's value is as much in what it refuses to include as in what it recommends. Naive baskets are always bigger than correct ones; the pass-through analysis is an anti-bullshit filter on thematic investing.
Core principles
1. Two meanings of pass-through
- Trend pass-through: how the driver mechanically reaches each layer of the chain.
- Value pass-through: whether a company captures the benefit or merely transits it to customers or input suppliers.
Nodes with high trend pass-through and low value capture are the canonical trap. Flag every node on both axes.
2. Single-mechanism gate (new in v2)
A trend must have a single causal mechanism to be analysed as one theme. Bundles of several mechanisms that share a marketing label (e.g. "edge AI", "quantum computing", "metaverse") must be decomposed into sub-themes before any chain is built. This is Phase 0 below.
3. Default skepticism at the L1 platform/originator layer (new in v2)
Across every test of this skill, the "pick and shovel" layer has beaten the "platform/originator" layer on value capture. Shovels beat platforms. Originators face customer power (governments, payers, hyperscalers), supplier power (CDMOs, foundries, specialty inputs), and IP/patent cliffs that pickers and shovellers don't. Start Phase 4 evidence review at the L2/L3 layer; work back to L1 only after the shovels are mapped.
4. End users are cost bearers, not beneficiaries (new in v2)
If a node's cost of goods rises with the trend, it is a cost bearer, not a beneficiary, regardless of whether its revenue grows. EV OEMs in a rare-earth thesis, auto OEMs in a chip shortage thesis, PC OEMs in a memory upcycle thesis — these are all cost bearers. Flag and exclude from the basket. Growth ≠ benefit.
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 · 285 lines · 199 tokens per session scan A 473d54ff2bf5
supply-chain-pass-through is a skill published in the GitHub repository HHFinAi/claude-equity-research-skills (8 stars, last pushed 5mo ago), licensed MIT. It adds 199 tokens to every session and 5,300 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
NSELens
Use this skill whenever the user asks for Indian stock picks, top N stocks to buy, rebound candidates, GTT setups, swing trade ideas, or buy recommendations for the Indian stock market. Triggers on phrases like "top 3 stocks", "top 5 Indian stocks", "top 10 stocks to buy", "best stocks for tomorrow", "NSE rebound…
invest-analyst
A framework for producing professional investment research, including company reports, industry studies, event analysis, analyst-expectation reviews, comparisons, and market summaries. It connects several investment research workflows into one process.
invest-fund
A Chinese-language guide for analysing investment funds, with different workflows for comparing funds, reviewing ETFs, examining new funds, and studying industry funds.
invest-stock
A stock-analysis workflow for companies listed in China, Hong Kong, or the United States. It chooses an analysis style based on the market and whether the user requests a deeper valuation review.
invest-cli
An investment-analysis command-line tool that fetches data for Chinese stocks and funds, US stocks, and stock screening, then applies matching analysis frameworks. A command-line tool is a program operated from a terminal.
invest-allocation
An investment-allocation guide for dividing money among stocks, bonds, commodities such as gold, and cash based on goals, risk tolerance, time horizon, and access needs.