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 ntaffzii/Skill-Agents --skill position-sizergit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/ntaffzii/skill-agents/position-sizer)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/position-sizer"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/position-sizer/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/ntaffzii/skill-agents/position-sizer"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/position-sizer.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 | $0.00103 | $0.01056 |
| Opus 5.5 | $0.00041 | $0.00422 |
| Sonnet 5.5 | $0.00021 | $0.00211 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
position-sizer 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Position Sizer
Overview
"How many shares should I buy?" only has a defensible answer once you know how much you're willing to lose if the stop is hit. This skill does the arithmetic — fixed-fractional risk sizing, ATR-based stop distance, and Kelly criterion — on numbers the user supplies. It does not fetch prices or recommend a trade.
Not financial advice. This calculates how many shares fit a chosen risk budget; it does not evaluate whether the trade itself is a good idea.
When to use
- คำนวณจำนวนหุ้นที่ควรซื้อ ตามความเสี่ยงที่รับได้ต่อไม้
- Sizing a position given account equity, entry price, and a stop-loss level
- Converting ATR (Average True Range) into a volatility-scaled stop and matching position size
- Estimating a Kelly-criterion fraction from historical win-rate/win-loss stats (as an upper bound, not a recommendation — see Known limitations)
When NOT to use
- No stop-loss level or risk percentage has been specified — ask for these first; sizing "how many shares fit my account" without a risk budget is really just "how much can I afford," a different question
- The user wants a signal on whether to take the trade at all — this skill only sizes a trade already decided on
Core knowledge
Fixed-fractional sizing: risk a fixed percentage of account equity per trade.
dollar_risk_per_share = |entry_price - stop_price|
total_risk_amount = account_equity × risk_pct
shares = floor(total_risk_amount / dollar_risk_per_share)
Shares are always rounded down so actual dollar risk never exceeds the budget. Common risk_pct defaults discussed in trading literature range roughly 0.5%-2% per trade — this skill doesn't assert a "correct" number; ask the user or use their stated tolerance.
ATR-based stop: instead of a fixed percentage stop, scale the stop distance to the security's own recent volatility: stop_price = entry_price - (ATR × multiplier), commonly multiplier 1.5-3×. Then size with the same fixed-fractional formula using this derived stop distance.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 66 lines · 103 tokens per session scan A 93c7064e4fee
position-sizer is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed 15d ago), licensed MIT. It adds 103 tokens to every session and 1,056 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
expense-review-policy
Review invoices and contracts against accounts-payable policy before human approval.
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
hyperliquid
Hyperliquid market data, account history, trade review.
excel-author
Build auditable financial workbooks headless via openpyxl.
solana
Query Solana wallets, tokens, txs, and NFTs in USD.