trade-journal-analyzer

trade-journal-analyzer is a skill for Claude Code from winstonkoh87/Athena-Public. It costs 29 tokens per session (852 once invoked), scanned A, original, MIT.

A trade-journal analysis tool that reads historical entries, finds statistical patterns, and classifies losing periods called drawdowns.

In plain words
What is it for?
Use it to calculate win rates, compare planned and achieved risk-to-reward ratios, examine losing streaks and recovery time, detect changing performance, and review emotional trading.
Why use it?
It turns subjective trading notes into measurable evidence about which setups, instruments, times, and behaviours are helping or hurting results.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it to calculate win rates, compare planned and achieved risk-to-reward ratios, examine losing streaks and recovery time, detect changing performance, and review emotional trading.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/winstonkoh87/athena-public/trade-journal-analyzer
Install

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.

Any agent
npx skills add winstonkoh87/Athena-Public --skill trade-journal-analyzer
Clone the repo
git clone --depth 1 https://github.com/winstonkoh87/Athena-Public

Made for: Claude Code.

Wrote 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.

agentmods badge for trade-journal-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/winstonkoh87/athena-public/trade-journal-analyzer/github.svg)](https://agentmods.dev/skills/winstonkoh87/athena-public/trade-journal-analyzer)
Your own site
<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/trade-journal-analyzer"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/trade-journal-analyzer/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.

agentmods 80×15 button for trade-journal-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/trade-journal-analyzer"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/trade-journal-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 852 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00852
Opus 5 $0.00015 $0.00426
Sonnet 5 $0.00006 $0.00170
Haiku 4.5 $0.00003 $0.00085

Measured 13d ago against content hash 033f48143a4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

trade-journal-analyzer 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 13d 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.

examples/skills/workflow/trade-journal-analyzer/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trade Journal Analyzer (Expanded)

Absorbs: drawdown-classifier

Reads historical trade entries, extracts actionable statistical patterns, AND classifies drawdowns. Converts a "diary" into a "data warehouse."

Triggers

"analyze my trades", "journal patterns", "what's my actual WR", "edge audit", "losing streak", "drawdown", "is my system broken", "should I stop trading", "3 losses in a row"

Core Analytics

  1. Ingest: Read entries from .context/trading_journal/.
  2. Parse: Extract setup type, instrument, direction, entry, SL, TP, result, notes.
  3. Analyze:
    • Win Rate by Setup Type: Which setups are actually profitable?
    • Win Rate by Instrument: Where is the edge strongest?
    • Win Rate by Time of Day: Asian vs London vs NY session performance.
    • Average R:R Achieved: Planned RR vs actual RR (execution gap).
    • Drawdown Sequences: Longest losing streaks, recovery time.
    • Edge Decay: Is WR trending up or down over last 20 trades?
  4. Flag:
    • Setups with WR < breakeven threshold → flag for review or removal.
    • Instruments with consistent negative EV → stop trading them.
    • Emotional notes correlation → do emotional trades have lower WR?

Drawdown Classification

Not all drawdowns are equal. The wrong response is more dangerous than the drawdown itself.

Class 1: Noise (Random Variance)

  • Losing streak within expected statistical bounds for the system's WR.
  • Test: At 60% WR, a 5-loss streak has P = 0.4^5 = 1.02%. Over 200 trades, ~2 expected.
  • Response: Do nothing. Continue executing. Do NOT adjust.

Class 2: Structural (Setup Flaw)

  • Losses concentrated in a specific setup, instrument, or time period.
  • Test: Is the WR decline isolated to one setup type?
  • Response: Quarantine the specific setup. Continue trading others.

Class 3: Thesis-Breaker (Edge Invalidation)

  • Systematic WR decline across ALL setups.
  • Test: Is the WR decline persistent (>30 trades)? Has market microstructure changed?
  • Response: Full stop. Trigger circuit-breaker. Paper trade. Re-validate edge.

Read the full file on GitHub · 88 lines

Changes

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.

  1. 13d ago First seen · 88 lines · 29 tokens per session scan A 033f48143a4d

Subscribe to this mod's changes

trade-journal-analyzer is a skill published in the GitHub repository winstonkoh87/Athena-Public (587 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 852 once invoked, about $0.0001 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.