Autonomously fix open GitHub issues one at a time using fresh-context subagents. Loops until no eligible issues remain, a fix-issue invocation is halted by the complexity gate or an error, or a HITL checkpoint is encountered. AFK-safe: no human input required during the loop. Use when asked to "run the ralph loop", work through all open issues, or fix issues autonomously.
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
Use when reviewing a project's architecture for design pattern applicability -- either validating a design document before implementation, or analyzing an existing codebase for pattern improvement opportunities.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Performs comprehensive code reviews for Python files following PEP 8 and Google Python Style Guide standards. Checks code quality, best practices, security, performance, maintainability, and style compliance. Use when reviewing Python code or when asked to check, audit, or improve Python code quality.
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
Check out an unblocked AFK GitHub issue, implement the fix via TDD, run a quality review loop, and submit a pull request for human review. Use when asked to work on, fix, or resolve a GitHub issue.