The your AI Code plugin for an end-to-end AI development workflow — ticket management, multi-agent code review, security audit, and automated PR creation — built on a Harness for long-running AI agents with strict context management and cross-session learning.
Skills 13 in the Claude listing
audit Comprehensive multi-agent code audit that delegates to the code-reviewer and security-scanner sub-agents. autopilot Consume a pre-built ticket list (split-plan.md under .simple-workflow/backlog/product_backlog/{parent-slug}/) and drive the per-ticket /scout -> /impl -> /ship pipeline in topological order with polic brief Conducts a structured Socratic interview that gathers requirements, then writes a brief and an autopilot policy file for a new feature or task. catchup Recovers branch state and recommends the next development action after a context reset. Create ticket Do not auto-invoke. impl Do not auto-invoke. investigate Investigates codebase topics by spawning the researcher subagent and writing structured findings to disk. plan2doc Creates an implementation plan by spawning the planner subagent with a size-routed model (sonnet for Size S, opus for M/L/XL) and writing the plan to disk. refactor Plans and executes a refactoring with safety checks by delegating to the planner and code-reviewer agents, then iterating implementation + review up to three rounds. scout Investigates the codebase and produces an implementation plan by delegating to `/investigate` (researcher subagent) and `/plan2doc` (planner subagent), then emits a `## [SW-CHECKPOINT]` block at end-o ship Ships completed work by committing staged changes, moving any bound ticket to `.simple-workflow/backlog/done/`, delegating knowledge-base extraction to `/tune` via the Skill tool, pushing the branch, test Creates and runs tests for a specified file or feature by spawning the test-writer subagent in a forked context, then returns a structured summary with test file paths and pass/fail counts. tune Analyzes evaluation logs (eval-round, quality-round, security-scan, audit-round, autopilot-log) by spawning the tune-analyzer subagent and maintains the project knowledge base under `.simple-workflow/