Pre-Trade Discipline Gate reads a local JSON or YAML checklist of candidate entries and decides whether each planned manual order should proceed. It checks that the entry is in a written plan, the stop is predefined, the size is within plan and actual risk does not exceed planned risk. It also reads optional exposure, circuit-breaker and trader-memory artifacts.
It never places or cancels orders and never calls a broker or fetches market data. It writes a decision report and an optional journal row, and can carry a ledger of approved operating rules that each need a recorded acknowledgement.
What You Get
- A pre_trade_discipline_decision JSON report with GO, REVIEW_REQUIRED, NO_GO or NO_ACTIONABLE_ORDERS
- A matching Markdown report unless JSON only is requested
- A JSONL journal row recording the checklist answers used for the decision
- A link from the report back to the related thesis in trader-memory-core
- An approved-rules ledger with activate, list, extend, retire, restore and supersede commands
Common Use Cases
- Checking a planned entry against its written plan just before opening the broker
- Blocking new entries during a post-loss cooldown window
- Making checklist adherence visible in later monthly reviews
- Running an exit-code gate in a shell pipeline with the fail-on-non-go option
What Makes It Unique
It is built for discipline and fails closed. Bad risk numbers, missing artifacts or an unreadable rules ledger all lead to REVIEW_REQUIRED, which sends the trader back to review before any order. The approved-rules feature lists each applicable rule and requires an acknowledgement, and it states that the acknowledgement is recorded and not verified. A two-week rule experiment script reviews one rule over 14 New York calendar days using the trader’s own observations.
Under The Hood
Claude runs Python scripts from the shell. The scripts read the answers file, optional JSON decision files from sibling skills and thesis state folders, then write the decision reports, journal rows and the approved-rules ledger as local files, with the ledger written atomically. They call no broker API and no web service. Reports can be linked into thesis files through the trader-memory-core link function, which leaves review dates alone. Everything uses the Python standard library and stays on your machine.