Menü
Arm the OS scheduler to relaunch claude at a given time with a given handover. Dedup-guarded. Use when the user asks to arm a resume / schedule a relaunch or run /handover-arm-resume.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | handover-arm-resume |
| description | Arm the OS scheduler to relaunch claude at a given time with a given handover. Dedup-guarded. Use when the user asks to arm a resume / schedule a relaunch or run /handover-arm-resume. |
When the user asks to arm a scheduled resume, run:
bash scripts/handover/arm-resume.sh --time <HH:MM|smart|auto> --handover <path> [--force] [--dedup-any] [--dry-run]
--time smart (prefer) reads the usage cache and picks the throughput-maximizing
slot; auto waits for the next cap reset; HH:MM is explicit local time.
Dedup is PER-HANDOVER, not prefix-wide: it refuses (rc=3) only when a resume job
for THIS SAME handover is already scheduled (--force replaces the matched
job). Arming a DIFFERENT handover while another is queued SUCCEEDS —
independent tickets are meant to run concurrently, so never serialise them
or --force over one to queue the other. "Same handover" means the same
derived task name, which since HIMMEL-1304 is built from the CANONICAL
path plus a hash of it: every spelling of one file (relative, absolute,
.., symlink, and on Windows C:/ vs /c/ vs case) collapses to ONE
identity, and two distinct paths no longer collide just because punctuation
was stripped. A --force replace is also transactional — the old slot is
deleted only after the new job is registered and verified, so a later
refusal or failure can no longer leave you with no arm at all.
--dedup-any opts into the broad "any existing slot blocks" mode the
unattended auto-arm watchdogs use. This shells the SANCTIONED arm path —
never hand-roll schtasks/at
(blocked by block-rogue-claude-schedule). See
.claude/commands/handover-arm-resume.md for the time sentinels + exit codes.
Panel-only CR gate for Codex — runs the shell critic panel and CodeRabbit CLI pass over the branch diff, records ledger evidence, and clears the CR marker through the sanctioned chokepoint only when both the panel and CodeRabbit findings are clean (no Critical/Important blockers). Use when the user asks to run /pr-check or clear the CR gate under Codex.
Use when the user says "new epic", "new task", "new standalone", "end session", "update status", "handover", "handover-resume
Arm/inspect/remove the recurring luna clip-pipeline cadence (daily harvest+triage, daily synthesize+archive, daily health) via schtasks/cron, each leg pinned to a cheap --model. Dedup-guarded. Use when the user asks to arm/check/disarm the clip-pipeline cadence or runs /pipeline-cadence.
Use when the per-project auto-memory store (`~/.claude/projects/<project-slug>/memory/`: the always-loaded `MEMORY.md` index + one topic file per fact) is approaching or over its load budget (~24.4KB) — the harness emits a size-limit warning at session load when over budget (e.g. "MEMORY.md is NN KB (limit 24.4KB)"), content past the limit is silently dropped = partial recall. Losslessly compounds the DURABLE gotchas out of the auto-memory into qmd-searchable luna / himmel reference notes (read-many → propagation review → write-once → qmd gate → slim index → delete sources), so the always-loaded index stays lean and adopter-generic learnings land in himmel docs (memory + vault never propagate to other users). Lean-invoke, operator-run on demand — NOT an always-on hook (HIMMEL-569).
Use when turning an idea into an implementation plan — runs brainstorm → spec → plan as ONE pipeline with an ADVERSARIAL CRITIC LOOP between each stage. Trigger on "build/implement/design X", "/minerva", or any feature/capability work that should pass through a spec + plan before code. Composes superpowers brainstorming + writing-plans (no fork); adds a spec-critic and a plan-critic.
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".