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/position-laddernpx skills add yennanliu/InvestSkill --skill position-laddergit 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/position-ladder)<a href="https://agentmods.dev/skills/yennanliu/investskill/position-ladder"><img src="https://agentmods.dev/badge/skills/yennanliu/investskill/position-ladder.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 5.1 | $0.00044 | $0.06423 |
| Opus 5 | $0.00022 | $0.03211 |
| Sonnet 5 | $0.00009 | $0.01285 |
| Haiku 4.5 | $0.00004 | $0.00642 |
Grade A, and why
position-ladder 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 7d 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Position Ladder — Staged Entry & Cost-Basis Management
⚠️ Data Verification — Do This Before Any Analysis
Before running any analysis, always retrieve the latest market data for the ticker:
- Fetch current price — use web search or ask the user for the live price, 52-week range, and market cap. Never assume a price from training data.
- Confirm key figures — recent earnings, revenue, key ratios (P/E, P/S, etc.) as applicable to this skill.
- State your data source — note where the numbers came from (e.g., "Google Finance, June 19 2026") at the top of the output.
- Flag stale data explicitly — if live data is unavailable, display this warning before proceeding:
⚠️ Live data unavailable. The following analysis uses training-data estimates which may be significantly out of date. Verify all prices and metrics before making any decisions.
Never silently substitute training-data estimates for current prices. When in doubt, ask the user to paste the latest quote.
⚠️ Read This First — This Is Scenario Modeling, Not a Recommendation
This framework is more prescriptive than the rest of the InvestSkill catalog: it outputs specific price levels and share counts. Every number it produces is a conditional plan under stated assumptions, not an instruction to trade.
Three honest claims must appear in every output:
- Lowering average cost is not the same as making money. Average cost is an accounting anchor and a psychological one — it is not a return metric. Trimming a high-cost lot mechanically lowers the number without creating a dollar of wealth. Always report total return and realized P&L alongside average cost, and show the buy-and-hold comparison.
- This is volatility harvesting. The strategy monetizes oscillation around a level. It outperforms in a range-bound / mean-reverting tape and underperforms in a strong trend — in either direction. A stock that only goes up leaves the ladder underfilled; a stock that only goes down fills it and keeps falling.
- Position control is the actual edge. The hard ceiling on share count — "stop adding at N shares, no matter what" — is what converts averaging down from an unbounded liability into a bounded, pre-sized bet. Without the cap, this is not a strategy; it is a mechanism for concentrating capital into losers.
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.
- 7d ago First seen · 411 lines · 44 tokens per session scan A 8e7fe40de3d3
position-ladder is a skill published in the GitHub repository yennanliu/InvestSkill (200 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 6,423 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
dcf-model
DCF valuation: free cash flow projections, WACC, terminal value, sensitivity analysis.
comps-analysis
Comparable company analysis: operating metrics, valuation multiples, peer benchmarking.
initiating-coverage
Full equity research initiation: company research, financial model, valuation, charts, 30-50 page report.
ui-design
Design-quality reference for financial-research visual output: typography, color, composition, and avoiding generic AI aesthetics.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.
user-profile
Manage user profile including watchlists, portfolio, and preferences.