coding agent Skill Pack 💻 Plan first OpenClaw skill pack. Skill Layout This repo now ships two sibling skills: skills/plan issue/SKILL.md skills/coding agent/SKILL.md SKILL.md at repo root is a compatibility entry for single skill setups. Behavior Model 1. Use plan issue for planning/scoping tasks. 2. Wait for explicit APPROVE . 3. Use coding agent to execute the approved plan with ACP first routing, then CLI fallback. Guardrail: no bypass flags ( yolo , dangerously skip permissions ) unless explicitly requested. Review Routing + Run Status Contract Plan artifact review: use ./scripts/plan review or ./scripts/plan review live . PR/code review: use codex review base ... directly or ./scripts/safe review.sh . Never provide a manual review summary before running the matching wrapper/command. ./scripts/safe review.sh now emits the full RUN EVENT lifecycle for single review runs and classifies timeout/signal exits as interrupted . Long run wrapper status events (hard fail policy): RUN EVENT start RUN EVENT heartbeat every 20s after 30s elapsed RUN EVENT interrupted on signal/timeout/interruption RUN EVENT failed on non interruption errors RUN EVENT done on success Usage In OpenClaw: [安装/使用命令见下方] CLI wrappers: [安装/使用命令见下方] Wrapper Architecture The wrapper surface is split intentionally: [安装/使用命令见下方] This keeps transport behavior in shell while moving duplicated policy into one tested core. Command Map (Telegram/OpenClaw) These aliases are routing hints at the channel layer. Behavior is enforced by skills. /coding → compatibility entry skill ( SKILL.md ), routes plan first + execution flow /plan → skills/plan issue/SKILL.md (plan only, no writes) /plan review [ plan ] → batch plan review (single pass full report). In unattended flow it may still end in a blocked state when interactive decision resolution is required; treat that as a hard stop, not an implicit handoff to implementation. /plan review live [ plan ] → Lobster workflow checkpoints by default (in repo workflows/