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/trader-memory-corenpx skills add ntaffzii/Skill-Agents --skill trader-memory-coregit 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/trader-memory-core)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/trader-memory-core"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/trader-memory-core.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 | $0.00094 | $0.01051 |
| Opus 5 | $0.00047 | $0.00526 |
| Sonnet 5 | $0.00019 | $0.00210 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
trader-memory-core 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trader Memory Core
Overview
A trade without a record teaches nothing — the entire point of journaling is to make patterns visible across many trades (which setups actually work, whether stops get respected, whether sizing discipline holds) instead of relying on memory of a few vivid wins or losses. This skill defines a simple local journal schema and computes the standard trade-quality statistics from it: win rate, average R-multiple, and expectancy.
Not financial advice. This summarizes past results from data you supply; it does not predict future performance, and past win rate/expectancy are not guarantees.
When to use
- บันทึกไม้เทรดที่ปิดแล้วลง journal
- คำนวณ win rate, R-multiple เฉลี่ย, expectancy จากประวัติการเทรด
- Reviewing whether stops/sizing were followed as planned across recent trades (pairs with a postmortem review of individual losing trades)
When NOT to use
- The trade is still open — this skill's stats are for closed trades only; log the setup/plan when opening, but win/loss stats need an exit price
- The user wants a live P&L dashboard connected to a broker — this is a local structured-file journal, not a broker integration
Core knowledge
R-multiple: the standard way to compare trades of different sizes on equal footing. R = (exit_price - entry_price) / (entry_price - stop_price) for a long trade — a +2R trade made twice its initial planned risk; a -1R trade lost exactly the planned risk (stop was hit cleanly); anything worse than -1R means the stop wasn't respected as planned or slippage occurred.
Win rate: fraction of trades with R > 0. On its own this is a weak metric — a strategy can have a low win rate and still be strongly profitable if average wins are large relative to average losses (or vice versa), which is why expectancy matters more than win rate alone.
Expectancy (in R-multiples): win_rate × avg_win_R + loss_rate × avg_loss_R (avg_loss_R is negative, so this naturally nets losses against wins). A positive expectancy means the strategy makes money on average per trade, over this sample — it is a backward-looking summary of the logged trades, not a forward guarantee.
What ships with it
2 files 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.
- 6d ago First seen · 59 lines · 94 tokens per session scan A 722f932188ad
trader-memory-core is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 1,051 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
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.
solana
Query Solana wallets, tokens, txs, and NFTs in USD.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.
merger-model
Build M&A accretion/dilution workbooks in Excel.