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/ntaffzii/skill-agents/position-sizernpx 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.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 | $0.00103 | $0.01056 |
| Opus 5 | $0.00051 | $0.00528 |
| Sonnet 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 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 — 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.
- 4d 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 2d ago), licensed MIT. It adds 103 tokens to every session and 1,056 once invoked, about $0.0005 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
pseo-scale
Architect programmatic SEO systems for 10K-100K+ pages with database-backed data layers, data sufficiency gating, incremental validation, crawl budget management, content enrichment pipelines, and edge delivery. Use when scaling beyond 10K pages, when builds are OOMing, when Google is not indexing all pages, or when…
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
excel-author
Build auditable financial workbooks headless via openpyxl.
pptx-author
Build PowerPoint decks headless with python-pptx.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.