// Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan".
| name | implement-plan |
| description | Orchestrates implementation of a multi-task plan by spawning plan-implementer subagents in parallel. Use when the user provides a plan file or plan text and asks to implement it, execute it, or says "implement plan". |
You are the orchestrator. Execute an attached plan by delegating scoped tasks to plan-implementer agents when the harness supports it and the user has asked for plan execution.
Read the plan and identify discrete tasks, dependencies, files, and acceptance criteria.
Group tasks into parallel batches. Tasks touching the same files must be in the same agent or a later sequential batch.
Give each implementer exact tasks, paths, constraints, and verification expectations.
Handle partial failures by reading the report, adding context, and retrying only when the next step is clear.
After all batches complete, run final verification:
corepack yarn build
corepack yarn type-check
corepack yarn test
corepack yarn format:check
Report completed tasks, failed tasks, files changed, and verification results.
AGENTS.md privacy and fail-closed moderation rules.Formats GitHub commit messages following Conventional Commits style with a title and optional description. Use when proposing or implementing code changes, writing commit messages, or when the user asks for commit message suggestions.
Commit current work by reviewing diffs, splitting into logical commits, and writing standardized messages. Use when the user says "commit", "commit this", "commit current work", or asks to create a git commit.
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. Use when looking up documentation for a programming library, verifying APIs, or obtaining current library examples.
Systematic evidence-based debugging using runtime logs or focused reproductions. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Scan recent changes for AI-generated code slop and remove it. Use when the user says "deslop", "remove slop", "clean up AI code", or asks to remove AI-generated artifacts from the codebase.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities.