tx-cycle

name	tx-cycle
description	Run a tx cycle scan — sub-agent swarm for automated codebase issue discovery. Use when the user mentions "cycle", "scan", or "find issues".
disable-model-invocation	true

tx cycle — Sub-Agent Swarm Issue Discovery

Before running tx cycle, ask the user these questions to build the right command:

Required

1. Task prompt (--task-prompt): What area of the codebase should agents review?
   • Examples: "Review core services", "Audit API endpoints", "Check error handling"

Optional (with defaults)

2. Scan prompt (--scan-prompt): What should agents look for?

   • Default: "Find bugs, anti-patterns, missing error handling, weak EARS requirement coverage, integration-test gaps in critical flows, OTEL non-blocking risks, and performance/infra issues."

3. Number of agents (--agents N): How many parallel scan agents per round?

   • Default: 3

4. Fix mode (--fix): Should a fix agent run between scan rounds?

   • Default: off (scan-only)

5. Dry run (--dry-run): Report findings without writing to the database?

Building the Command

Once you have the user's answers, construct and run:

tx cycle \
  --task-prompt  \
  --scan-prompt  \
  --agents 3