planner

name	planner
description	Anton planner skill — author, update, and close multi-session initiatives (migrations, rollouts, long-running refactors) in `context/plans/`. Use when starting a multi-session initiative, tracking next steps on in-flight work, migrating a memory entry to a durable plan, closing a completed initiative, or reviewing what's open. Plans live at `context/plans/NNNN-kebab-slug.md` and are mutable — they capture execution state (what's next, what's blocked, log of decisions made during work) while ADRs capture immutable decisions (why). The active-plan index is built by scanning plan files directly and injected into every Codex session by `.Codex/hooks/inject_plans_index.py`. Keywords — plan, planner, initiative, track work, multi-session, next steps, checklist, migration plan, rollout plan, roadmap, in-flight, blocker, close plan, review-by, exit plan, timebox, memory-to-plan handoff.
allowed-tools	Read, Write, Edit, Glob, Grep, Bash

Planner

Anton-local skill for the in-repo plan lifecycle. Owns four workflows: new, list, update, close. Plans live at context/plans/NNNN-kebab-slug.md and are mutable — the body is edited as work progresses, tasks get checked off, the log grows.

Why this skill exists

Anton already has two complementary persistence layers:

• ADRs (context/adrs/) — immutable decisions. Answer why.
• Auto-memory — ephemeral cross-session hints. Answer what did I just learn.
• Git log — immutable commits. Answer what changed.

But there's a missing layer: the multi-session initiative — "adopt Longhorn", "migrate Tailscale", "roll out OpenTelemetry". These span many commits and several sessions. Memory is too ephemeral (decays as new entries push it out); git log is too coarse (no sense of what's ); ADRs are too rigid (decisions, not execution state).