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 agentmods add skills/yennanliu/investskill/research-bundlenpx skills add yennanliu/InvestSkill --skill research-bundlegit clone --depth 1 https://github.com/yennanliu/InvestSkillWrote 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/yennanliu/investskill/research-bundle)<a href="https://agentmods.dev/skills/yennanliu/investskill/research-bundle"><img src="https://agentmods.dev/badge/skills/yennanliu/investskill/research-bundle.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.01140 |
| Opus 5 | $0.00015 | $0.00570 |
| Sonnet 5 | $0.00006 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
research-bundle 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Bundle
This skill has been unified into
full-report. Use/us-stock-analysis:full-reportwith a--depthflag instead:
| Old Usage | New Equivalent |
|---|---|
/research-bundle AAPL --quick |
/us-stock-analysis:full-report AAPL --depth quick |
/research-bundle AAPL |
/us-stock-analysis:full-report AAPL --depth standard |
/research-bundle AAPL (full) |
/us-stock-analysis:full-report AAPL --depth comprehensive |
The full-report skill absorbs everything research-bundle provided: the 5-phase framework, composite scoring weights, investment thesis narrative, conflict resolution rules, entry/exit strategy, and monitoring plan — plus HTML report output and configurable depth.
Composite Scoring Weights (Quick Reference)
Component Weight Sub-Score (0-10)
─────────────────────────────────────────────────────
Business Quality 25% [competitor + fundamental]
Valuation 25% [DCF + relative valuation]
Market Signals 20% [insider + institutional + earnings]
Technical Setup 15% [technical analysis timing]
Risk Profile 15% [short interest + options signals]
─────────────────────────────────────────────────────
COMPOSITE SCORE 100% X.X / 10
8.0–10.0 → Strong Buy | 6.5–7.9 → Buy
5.0–6.4 → Hold/Watch | 3.5–4.9 → Underweight
0.0–3.4 → Sell/Avoid
5-Phase Research Framework (reference)
The original research-bundle framework — now executed automatically by full-report:
Phase 1 — Business Foundation (competitor-analysis, sector-analysis) Assess economic moat width (Wide/Narrow/None), Porter's Five Forces, market share trajectory, and sector rotation positioning. Score: business quality 0–10.
Phase 2 — Valuation (dcf-valuation, stock-valuation) DCF intrinsic value across 3 scenarios + comparable company multiples (EV/EBITDA, P/E, P/S). Probability-weighted composite IV. Upside/downside to fair value.
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.
- 4d ago First seen · 94 lines · 31 tokens per session scan A 7dcf1a1925a6
research-bundle is a skill published in the GitHub repository yennanliu/InvestSkill (198 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 1,140 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
dcf-model
DCF valuation: free cash flow projections, WACC, terminal value, sensitivity analysis.
initiating-coverage
Full equity research initiation: company research, financial model, valuation, charts, 30-50 page report.
comps-analysis
Comparable company analysis: operating metrics, valuation multiples, peer benchmarking.
html-report
Self-contained styled HTML reports written to the task directory: PDF-exportable research documents with inline data, charts, and theme-aware CSS.
competitive-analysis
Competitive landscape analysis: positioning, scorecards, moat assessment, market share trends.