菜单
Analyze codebase using GitNexus knowledge graph + codebase-retrieval. Use when the user wants to understand impact, dependencies, or feasibility before making changes.
Implement tasks from OpenSpec change or conversation plan. Use when the user wants to start implementing, continue implementation, or work through tasks.
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Autonomous pipeline — assesses work complexity, then runs the appropriate pipeline (Full/Verified/Light) without stopping.
Reproduce bugs, explore apps, or run QA test flows via dev-browser. Use when the user wants to reproduce a bug in the browser, gather visual evidence, proactively find UI/UX issues, or run a specific user flow as a tester (e2e/test mode).
Execute maintenance work directly. Brief mini-plan, then carry out the change.
Plan and implement CI/CD pipeline changes. Explore scope, deployment strategy, and automation, then implement with optional spec creation.
| name | analyze |
| description | Analyze codebase using GitNexus knowledge graph + codebase-retrieval. Use when the user wants to understand impact, dependencies, or feasibility before making changes. |
Before launching the subagent, gather context from the current conversation:
Brief the user, then launch Agent tool with subagent_type: "osf-analyze".
Pass context using this format:
Analysis request: [what the user wants to understand]
Focus areas: [specific files, symbols, or features mentioned]
Context: [any relevant decisions or background from conversation]