From planr
Execute one Planr map item from pick through evidence-backed completion, including implementation, testing, review, and approval steps.
How this skill is triggered — by the user, by Claude, or both
Slash command
/planr:planr-workThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this for one picked item at a time.
Use this for one picked item at a time.
planr pick --json
planr trace item <item-id>
planr pick heartbeat <item-id>
Read the linked plan/context, implement the smallest correct slice, then record evidence:
planr log add --item <item-id> --summary "what changed" --files path-a,path-b --cmd "exact verification command"
planr review request <item-id>
Only close after review is complete:
planr review close <review-id> --verdict complete
planr close <item-id> --summary "Verified"
For longer work, keep runtime state current:
planr pick progress <item-id> --percent 50 --note "tests running"
planr pick pause <item-id> --note "waiting for human input"
planr pick resume <item-id>
If a human approval gate is required, request it before close and wait for an approved decision:
planr approval request <item-id> --reason "release approval"
planr approval list --open
planr context add ... --item <item-id> for discoveries another client needs.planr pick stale --older-than-seconds 900 before resetting abandoned ownership.planr pick release <item-id> --force only when ownership must be reset.npx claudepluginhub instructa/planr --plugin planrCoordinates coding agents with a live task graph using Planr. Handles project planning, dependency linking, item picking, review gates, and interruption recovery.
Executes a written implementation plan from disk with task tracking and review checkpoints. Use when you have a plan file ready to implement.
Executes written implementation plans with review checkpoints. Loads plans, follows steps exactly, runs verifications, and completes development using sub-skills.