human-runlisted

# human-run (platform skill — single source) **Who runs the script:** the **human**, via shell command `x`. **Who prepares it:** the **agent**, via this skill’s `ensure-env.sh` + `propose.sh`. **Never** paste a multi-line script into chat as the execution channel. **Never** wrap agent self-exec through this skill — tools already run those. Runtime CLI lives in the same wezdeck tree as this skill: `scripts/runtime/cli/{wd-run,x}` + `agent-run-lib.sh`. Docs: `docs/agent-run.md`. Profile: `agent-profiles` → `reporting.md`. ## Who runs what | Actor | Duty | | --- | --- | | **Human** | In a real terminal: `x` (peek → confirm → run in recorded cwd) | | **Any agent** | **Load skill → ensure-env → propose.sh → tell user only `x`** | | **Agent tools** | Self-runnable work — do **not** call this skill | ## When to load (mandatory) Load whenever **any** of these is true: - You are about to ask the human to run / paste / copy a shell script or multi-line command - The command needs a real TTY, GUI, host secret the agent must not hold, or privileges outside the agent sandbox - The human must read and approve the exact script before it runs **Do not load** when you can run it with tools, or when the snippet is illustrative only (mark 勿粘贴执行). ## Resolve TOOL_HOME ```text 1. directory of this SKILL.md (follow symlinks; ~/.agents/skills/human-run → …) 2. $HUMAN_RUN_HOME if set 3. else fail — re-run link-platform-skills.sh from a wezdeck that has human-run ``` ## Environment