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 erphq/skills --skill equity-research-frameworkgit clone --depth 1 https://github.com/erphq/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/erphq/skills/equity-research-framework)<a href="https://agentmods.dev/skills/erphq/skills/equity-research-framework"><img src="https://agentmods.dev/badge/skills/erphq/skills/equity-research-framework/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/erphq/skills/equity-research-framework"><img src="https://agentmods.dev/badge/skills/erphq/skills/equity-research-framework.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 | $0.00059 | $0.02082 |
| Opus 5.5 | $0.00024 | $0.00833 |
| Sonnet 5.5 | $0.00012 | $0.00416 |
| Haiku 4.5 | $0.00006 | $0.00208 |
Grade A, and why
equity-research-framework 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Equity Research Framework
What This Skill Does
This is the scaffolding for building a research view on any public company. Given a company + some initial interest, it walks through the steps to land on a thesis that's defensible, evidence-based, and clearly opinionated. Without a framework, research becomes "I read the 10-K and I like them" — which doesn't convince anyone and won't hold up when the stock moves against you.
The framework has five pillars: Business (what they actually do and how they make money), Industry (structural dynamics, competition, secular tailwinds/headwinds), Financials (profitability, growth, capital efficiency), Valuation (what you're being asked to pay relative to what you're getting), and Risks (what breaks the thesis). A finished thesis covers all five.
The Framework
1. Business
- What do they sell, and to whom? Be specific. "They sell software" is useless; "They sell cloud-native HR systems to mid-market enterprises (500–5,000 employees) in North America, primarily" is useful.
- Revenue model: Subscription? Transaction? Services? Hardware + service? Mix? For each line, what's the unit (per-seat, per-transaction, per-consumption)?
- Customer concentration: Top 10 customers as % of revenue. >20% = concentration risk. <10% = diversified.
- Geography: US / international mix. FX exposure.
- Go-to-market: Direct sales, channel, self-serve, mix. Changes in GTM often predict margin trajectories.
- Product strategy: Single-product company, platform strategy, suite strategy. Platform plays have higher NRR ceiling; single-product exposed.
- Moat: What keeps competitors out? (Network effects, switching costs, proprietary data, regulatory, brand, scale economics). Rate moat 1–5.
2. Industry
- Market size: TAM + growth rate. Source the number (analyst reports, company disclosures) rather than accept management claims.
- Structure: Monopoly / oligopoly / fragmented. Who are the #1, #2, #3 players + share?
- Secular tailwinds/headwinds: Is the pie growing? Is the share distribution changing? New entrants? Technology shifts? Regulatory shifts?
- Customer-side dynamics: Are buyers consolidating or fragmenting? Increasing budget or shrinking?
- Value-chain position: Where in the stack does this company sit? Upstream of commoditization? Or being commoditized from below?
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 · 123 lines · 59 tokens per session scan A ecde17ec246b
equity-research-framework is a skill published in the GitHub repository erphq/skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 2,082 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
vobiz-partner-api
Vobiz Partner / reseller API - create customer sub-accounts, transfer balance, run KYC sessions (PAN+Aadhaar OTP, no documents), and query per-customer CDRs/transactions/numbers.
finanz-versicherung
Strukturiert bereitgestellte Finanz- und Versicherungsunterlagen als neutrale Übersicht und Checkliste.
metatradermcp
Use when working with MQL4, MQL5, MetaTrader 4/5, Expert Advisors (EAs), custom indicators, or scripts. Covers OrderSend, iMACD, iRSI, CopyBuffer, trade operations, indicator buffers, and MQL4-to-MQL5 migration. Triggers on any .mq4/.mq5/.mqh file or MetaEditor compilation.
edgartools-sec-data
How to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K/10-Q data, or company financials.
creating-financial-models
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions.
analyzing-financial-statements
This skill calculates key financial ratios and metrics from financial statement data for investment analysis.