Skip to content
Back to search

Trade-quant

SkillWorks with Claude CodeGitHub

Paper-trading day-trade scout: Claude Code skills that scan, filter, simulate, size and risk-check opening-range breakouts, with a KPI journal

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 21 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Soumava1/Trade-quant with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Soumava1/Trade-quant'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/soumava1--trade-quant/badge.svg)](/listings/soumava1--trade-quant)

HTML

<a href="/listings/soumava1--trade-quant"><img src="/api/listings/soumava1--trade-quant/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

mkdir -p trader
cp config/config.example.json trader/config.json   # then edit your limits
python3 .claude/skills/trader-scanner/scan.py universe   # stock list, refresh weekly

`trader/` holds your config and scan runs. It is gitignored and never committed. The paper journal lives in `journal/trades.jsonl` (set by `journal_dir` in the config) so its history is kept in git. Put your name and email in `sec_user_agent`, or in the `SEC_USER_AGENT` environment variable, to include SEC filings: the SEC asks every tool that reads EDGAR to identify itself.

The example config is set up for a $1,000 paper account:

| Setting | Value | | --- | --- | | Budget | $1,000, with 10% kept in cash | | Max loss | $15 per trade, $30 per day, $80 per month (then the scout stops until next month) | | Trades | 2 a day | | Reward:risk | at least 2:1 | | Prices | $5 to $150 | | Position cap by score | 85+ → 75%, 70+ → 60%, 55+ → 45%, otherwise (paper picks) 25% |

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 193 lines
  1. # Trade-quant
  2. A paper-trading day-trade scout built as Claude Code skills. Each run finds
  3. opening-range breakouts in US stocks that are "in play", checks the news,
  4. plans the stop and target, replays the trade 10,000 times on the stock's own
  5. recent bars, sizes it to your limits, and runs a risk check. You get a short
  6. ranked list of trades, or an honest "nothing today". A paper journal then
  7. measures how those picks actually did.
  8. **Paper trading only. Nothing here places an order.** The scout refuses to
  9. run unless `"paper": true` is in your config. Not financial advice: most
  10. people who day trade lose money, and the odds shown are a reality check from
  11. the last 60 days, not a forecast.
  12. ## How it works
  13. ```
  14. scanner -> news -> entry -> stocks-in-play filter -> exit plan -> Time Machine -> budget -> risk
  15. \-> paper journal -> KPIs
  16. ```
  17. | Step | Skill | What it does |
  18. | --- | --- | --- |
  19. | Scan | `trader-scanner` | Finds stocks whose 5- or 15-minute opening range has broken to the upside, across ~5,900 US stocks |
  20. | News | `trader-news` | Yahoo headlines and SEC 8-Ks. Halts, risk headlines and serious 8-Ks veto a trade; legal, regulatory, earnings and deal news are cautions |
  21. | Entry | `trader-entry` | A fresh breakout, or a late entry if the price is still holding within 1% above the range high |
  22. | In play | `trade-scout` | Opening-range relative volume at least normal, daily ATR at least $0.50, at least 1M shares a day, and above VWAP; ranked by relative volume |
  23. | Exit | `trader-exit` | Stop at the range low or 10% of the daily ATR; targets of 2R, 3R and 4R; always flat by 3:55 PM |
  24. | Time Machine | `trader-timemachine` | 10,000 replays of the rest of the day for each stop/target pair, plus every past session the rule fired; keeps the best average R |
  25. | Budget | `trader-budget` | Whole shares inside your max loss, position cap, cash buffer and order limits |
  26. | Risk | `trader-risk` | One batch check: daily loss, trades per day, reward:risk, entry window, duplicates |
  27. | Journal | `trade-scout/journal.py` | Records each pick, settles it on that day's real bars after the close, and reports the KPIs |
  28. Each trade gets a score out of 100, built only from the tools' numbers: Time
  29. Machine edge and average R, the rule's history, relative volume, VWAP and
  30. the market's direction, and freshness. Position size follows the score.
  31. - **HIGH:** passed every gate.
  32. - **PICK:** when nothing is HIGH, the best trade with a positive expected
  33. outcome, lower conviction, so the journal has something to measure most days.
  34. - **WATCH / REJECT:** each comes with the reason.
  35. The stocks-in-play rules follow Zarattini, Barbon & Aziz, ["A Profitable Day
  36. Trading Strategy For The U.S. Equity
  37. Market"](https://ideas.repec.org/p/chf/rpseri/rp2498.html) (Swiss Finance
  38. Institute RP 24-98).
  39. ## Requirements
  40. - Python 3.11+ (the tools use only the standard library)
  41. - Network access to `query1/query2.finance.yahoo.com`, `feeds.finance.yahoo.com`,
  42. `www.nasdaqtrader.com` and `www.sec.gov`
  43. - [Claude Code](https://code.claude.com) to use the skills and the agent (the
  44. scripts also run on their own)
  45. ## Setup
  46. ```bash
  47. mkdir -p trader
  48. cp config/config.example.json trader/config.json # then edit your limits
  49. python3 .claude/skills/trader-scanner/scan.py universe # stock list, refresh weekly
  50. ```
  51. `trader/` holds your config and scan runs. It is gitignored and never
  52. committed. The paper journal lives in `journal/trades.jsonl` (set by
  53. `journal_dir` in the config) so its history is kept in git. Put your name and email in `sec_user_agent`, or in the
  54. `SEC_USER_AGENT` environment variable, to include SEC filings: the SEC asks
  55. every tool that reads EDGAR to identify itself.
  56. The example config is set up for a $1,000 paper account:
  57. | Setting | Value |
  58. | --- | --- |
  59. | Budget | $1,000, with 10% kept in cash |
  60. | Max loss | $15 per trade, $30 per day, $80 per month (then the scout stops until next month) |
  61. | Trades | 2 a day |
  62. | Reward:risk | at least 2:1 |
  63. | Prices | $5 to $150 |
  64. | Position cap by score | 85+ → 75%, 70+ → 60%, 55+ → 45%, otherwise (paper picks) 25% |
  65. ## Use
  66. In Claude Code:
  67. - `/trade-scout`, or ask "find me high conviction trades", runs the full
  68. pipeline and summarises it.
  69. - The `trade-scout` agent does the same and reads the news behind each HIGH
  70. trade before reporting.
  71. From the shell:
  72. ```bash
  73. python3 .claude/skills/trade-scout/scout.py # full scan
  74. python3 .claude/skills/trade-scout/scout.py --symbols NVDA,AMD # your list only
  75. python3 .claude/skills/trade-scout/journal.py settle # after the close
  76. python3 .claude/skills/trade-scout/journal.py report # the KPIs
  77. ```
  78. **When to run:** after the opening range forms, 9:40 AM New York time for the
  79. 5-minute range and 9:50 AM for the 15-minute one. Most breakouts happen before
  80. about 10:45, and late entries can still be found until 3:30 PM. A full scan
  81. takes 5 to 10 minutes.
  82. **Scheduled runs:** Claude runs the scout on trading days at 9:47, 9:58,
  83. 10:12, 10:27 and 10:44 AM and 12:33 PM New York time, and settles the journal
  84. at 4:07 PM. It posts each summary and commits the journal to `main`. Entries
  85. before 9:45 are blocked by the config, so 9:47 is the first useful scan.
  86. **To take a trade on paper:** run `/trader-risk` on it (which records the
  87. PASS), then `/trader-broker`. It needs your explicit yes and a connected
  88. Alpaca paper account (below).
  89. ## Alpaca paper account (optional)
  90. The repo's `.mcp.json` adds Alpaca's official MCP server (`alpaca-mcp-server`,
  91. pinned to 2.4.0), locked to paper trading. It holds no keys: it reads them
  92. from your environment. On your own computer:
  93. 1. In Alpaca's dashboard, create **paper** trading API keys.
  94. 2. Install [`uv`](https://docs.astral.sh/uv/), which provides `uvx`.
  95. 3. Set the keys as environment variables in your shell profile, never in the
  96. repo or a chat:
  97. ```bash
  98. export ALPACA_API_KEY="your paper key" # macOS/Linux: ~/.zshrc or ~/.bashrc
  99. export ALPACA_SECRET_KEY="your paper secret"
  100. ```
  101. On Windows: `setx ALPACA_API_KEY "..."` and `setx ALPACA_SECRET_KEY "..."`,
  102. then open a new terminal.
  103. 4. Open the repo in Claude Code, approve the `alpaca` server when asked, and
  104. check `/mcp` shows it connected.
  105. 5. Ask "show my Alpaca account info" and confirm in the dashboard that it is
  106. the paper account.
  107. `.claude/settings.json` sets the permissions for this repo:
  108. - **Ask every time:** placing, changing, cancelling or closing an order.
  109. - **Blocked:** options, crypto, and "close or cancel everything".
  110. - **Allowed without asking:** read-only lookups (account, positions, orders,
  111. quotes).
  112. Never move an order tool to `allow`. Cloud sessions cannot reach Alpaca, so
  113. the scheduled scans never place orders. Place them from your own computer
  114. after your yes.
  115. ## KPIs
  116. `journal.py report` shows HIGH and PICK separately:
  117. - win rate
  118. - average R (the expected gain per trade, in multiples of the risk)
  119. - average win and average loss
  120. - profit factor (gross wins / gross losses)
  121. - P&L and return on the budget
  122. - max drawdown, in dollars and in R
  123. - longest losing streak
  124. - trades per day
  125. - how trades ended: target, stop or at the close
  126. Judge the results over 30 to 50 or more trades. An average R above +0.2 with a
  127. drawdown you can live with is the bar before risking real money, and real
  128. fills (slippage at the open) will be worse than the replays.
  129. ## Repository layout
  130. ```
  131. .claude/skills/trader-* the 11 Day Trader skills (vendored, MIT, see LICENSE-day-trader-skill)
  132. .claude/skills/trade-scout/ scout.py (pipeline), features.py (stocks in play), journal.py (KPIs), SKILL.md
  133. .claude/agents/trade-scout.md
  134. .claude/settings.json permissions for the Alpaca order tools (ask / blocked / allowed)
  135. .mcp.json Alpaca's MCP server, paper only, keys from your environment
  136. config/config.example.json starting limits for trader/config.json
  137. journal/trades.jsonl the paper journal (picks and their settled outcomes)
  138. tests/ offline tests on saved market data (TSLA, 2026-10-19)
  139. ```
  140. ## Development
  141. ```bash
  142. uv sync
  143. uv run pytest
  144. uv run ruff check .
  145. ```
  146. The tests run offline on fixtures from the upstream pack. Live runs need the
  147. network hosts above.
  148. ## Credits
  149. The `trader-*` skills come from
  150. [Jakeschincariol/day-trader-skill](https://github.com/Jakeschincariol/day-trader-skill)
  151. (MIT, see `.claude/skills/LICENSE-day-trader-skill`).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.