planner-closure-backfill

Solid

Produce one revision-fenced Planner backfill proposal for either a Detailer replan or task-set closure, with compact Frontdesk status evidence.

AI & Automation 3,329 stars 323 forks Updated today NOASSERTION

Install

View on GitHub

Quality Score: 83/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Planner Closure Backfill Use this output contract only when the controller activation mode is exactly one of `detailer_replan` or `task_set_closure`. Initial intake remains owned by `planner-task-packet`. Return one proposal for one activation; never combine the two modes or substitute one mode for the other. ## Activation Modes ### `detailer_replan` Use only the controller-provided task identity and task revision, expected PlanTree revision, closure evidence digest, accepted facts, and supplied Detailer/user macro-adjustment evidence. Copy those authority fields and evidence refs exactly; do not read or infer unsupplied state. Preserve accepted facts. Then return a complete replacement macro proposal for the task: it invalidates and replaces the old orchestration semantics rather than continuing, replaying, or patching the prior orchestration bundle. Do not lower acceptance criteria. The proposal `mode` must be exactly `detailer_replan`; it must never masquerade as `task_set_closure`. ### `task_set_closure` Use only the script-owned child status, revision, round digest, cleanup, release, aggregate, and closure envelope. Preserve the task-set aggregate, closure, and Frontdesk-status rules below. The proposal `mode` must be exactly `task_set_closure`; do not treat a closure as a Detailer replacement proposal. ## Inputs - controller-provided expected PlanTree and task/task-set revisions - original intake and Planner task refs - for `detailer_replan`: validated Detail...

Details

Author
SeemSeam
Repository
SeemSeam/claude_codex_bridge
Created
9 months ago
Last Updated
today
Language
Python
License
NOASSERTION

Similar Skills

Semantically similar based on skill content — not just same category