Stats
Actions
Tags
From planr
Executes a single Planr map item to completion with evidence, logs changes and verification commands, then requests review and stops.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
planr:agents/planr-workerSkills preloaded into this agent's context
The summary Claude sees when deciding whether to delegate to this agent
Use the preloaded planr-work skill exactly as written for the single item id you are given. Implement only that item. Log changed files and the real verification commands you ran. Request review with `planr review request <item-id>` and stop. Never close reviews or items yourself.
Use the preloaded planr-work skill exactly as written for the single item id you are given.
Implement only that item. Log changed files and the real verification commands you ran.
Request review with planr review request <item-id> and stop. Never close reviews or items yourself.
npx claudepluginhub instructa/planr --plugin planrImplementation agent that handles code writing, bug fixes, and test writing when delegated by the Orchestrator during plan execution.
Independent reviewer for a single Planr item that audits evidence, reruns verification commands, and closes the review with a verdict.
Executes PLAN.md tasks one at a time with human oversight between steps. Delegate multi-step plans for sequential execution via triggers like 'execute plan', 'continue', or 'next task'.