Menü
Use when moving to a new chat/thread/tool/model or context is near limit. Not for same-thread small questions.
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 | handoff |
| description | Use when moving to a new chat/thread/tool/model or context is near limit. Not for same-thread small questions. |
Script root: ACC_PLUGIN_ROOT from SessionStart (hooks inject). PLUGIN_ROOT is hooks-only.
Reply rule:
codex resume / codex resume --last or codex exec resumethread/resume (same), thread/start (new), thread/fork only if user asks forkpython3 "<ACC_PLUGIN_ROOT>/scripts/build_handoff.py" --project-root .
--model <name> --reasoning <low|medium|high>.codex/anyone-can-code/artifacts/PORTABLE_HANDOFF.mdthread/start with the printed prompt whole. Do not trim.Small change → native model menu under chat (or CLI /model).
Big mid-work switch → new chat + this handoff (model+reasoning in prompt). User decides. No invent model API.
When this skill's job is finished:
Use when a plan or concrete tasks exist and user said build/go/implement. Not to invent scope or claim done without verify.
Use when goal/spec is clear and you need ordered tasks before writing code. Not while still clarifying.
Use when about to claim done/works/fixed, or user asks test/check/prove. Run evidence; not for pure planning chat.
Use when another installed plugin/skill may do the job better, or to route specialists. ACC stays workflow owner.
Use when user wants an explicit recorded decision or blocker saved to artifacts. Not silent monitoring.
Use when request is too vague to plan or build. Not when goal and constraints are already clear.