Skip to content
SkillScript-led920 tokens in use

Breakout Trade Planner

Reads VCP screener JSON and works out entry, stop, target, share count and portfolio heat for each candidate, with Alpaca-style order templates written to a report.

7,426 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/breakout-trade-planner

Skill label

measured from its files

What installing Breakout Trade Planner costs

76tokens idle
920tokens in use
1,596tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/_market_calendar.py, scripts/order_builder.py, scripts/plan_breakout_trades.py, scripts/risk_calculator.py.

Touches

shelldetectednetworkdetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples9/15
  • Output12/15
  • Size15/15
  • Resources5/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 30
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/_market_calendar.py, line 108
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/plan_breakout_trades.py, line 613

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity36
  • Momentum40

Breakout Trade Planner takes the JSON output of the VCP screener skill and applies a Minervini-style gate to every candidate. Candidates that pass get a trade plan with signal and worst-case entry prices, a stop below the last contraction low, a target in R-multiples and a position size based on worst-case risk.

The script checks account-level limits (single position size, sector exposure and total open risk) and writes a JSON file and a Markdown report. It runs offline on local files and does not place orders. The output is a planning aid and not investment advice.

What You Get

  • A JSON plan and a Markdown report named with the decision timestamp
  • Per candidate: signal entry, worst-case entry, stop, risk per share, target price and share count
  • Two order templates per actionable plan: a stop-limit bracket to pre-place and a limit bracket for use after confirmation
  • A summary of total risk, total position value and counts for each group

Common Use Cases

  • Turning a day’s VCP screener results into sized plans
  • Checking how much total open risk a set of candidates would add to a portfolio
  • Seeing why a candidate was rejected, deferred or constrained
  • Replaying a plan for a past date with the as-of option

What Makes It Unique

Sizing uses the worst-case entry price (pivot plus a chase allowance), so the stated risk per trade is the largest the plan allows. Candidates must pass a fixed gate: a valid VCP, a good, strong or textbook rating band and worst-case risk of no more than 8 percent. Breakout-state candidates also need breakout volume and a price within the chase limit. Plan validity follows the real exchange calendar, so a plan made after the close or on a holiday points to the next trading session.

Under The Hood

The agent runs a local Python script that reads the screener JSON, an optional exposure JSON and the command line settings, then writes a JSON file and a Markdown file into an output folder (reports/ by default), so it creates files on disk. It makes no network calls and needs no API keys; it needs the pandas-market-calendars package for the exchange calendar. The order templates are data in the report and are never sent to a broker.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers