How do I install the Operate skill?

Run npx skillmds@latest add zapgun-ai/operate in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Operate skill do?

clawback operate (operator watch) It is listed under Coding & Dev Tools on SkillMD.

Is Operate safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Operate?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Operate free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Operate?

zapgun-ai (@zapgun-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Operate by zapgun-ai — Agent Skill

Name: Operate
Author: zapgun-ai

File contents

clawback operate (operator watch)

Run .skills/operate/scripts/operator_watch.sh from the project root. It watches a proxy you already started with the monitor skill (run_monitor.sh --detach) and emits one line per actionable event on stdout, staying quiet during healthy idle.

.skills/operate/scripts/operator_watch.sh                              # defaults below
.skills/operate/scripts/operator_watch.sh data/clawback.run.log data/clawback.run.pid

Defaults match run_monitor.sh:

LOG_FILE = data/clawback.run.log
PID_FILE = data/clawback.run.pid
poll cadence: OPERATOR_WATCH_POLL_SEC (default 5s)

What it emits

log lines matching [error] / [warn] / → 4xx|5xx / failed / self-loop / EADDRINUSE / ECONN* / unhandled / Error:
two INFO signals an operator wants: clawback listening (a (re)bind) and runtime mode toggled (e.g. the baseline→armed flip after a fresh proxy's 5-turn capture window, or any admin toggle)
a synthetic [error] PROXY DOWN … line the moment the proxy pid stops responding — then it exits non-zero so the watch ends deliberately instead of hanging silent

Why not just `run_monitor.sh --attach`?

--attach only tails the log. macOS/BSD tail has no --pid, so a crash makes the log go quiet and an attached follower can't tell "dead" from "idle". Only run_monitor.sh's foreground follow mode has a liveness watcher — but that mode starts its own proxy and would collide on the port with one already detached. This script adds liveness to the already-detached case without touching the port.

Agent usage (the operator loop)

.skills/scripts/run_monitor.sh --detach — start the proxy.
Point the Monitor tool at .skills/operate/scripts/operator_watch.sh with persistent: true. Each emitted line becomes a notification.
On a PROXY DOWN (or a crash signature), read the tail of data/clawback.run.log to find the cause — that's the "pattern in the logs that needs fixing" — then bring it back with the restart skill and re-arm the Monitor.

Stop the proxy with the shutdown skill; the watch exits on its own when the proxy is gone.

---name: operatedescription: clawback operate (operator watch)---# clawback operate (operator watch)Run `.skills/operate/scripts/operator_watch.sh` from the project root. It watches a proxy youalready started with the [monitor](../monitor/SKILL.md) skill(`run_monitor.sh --detach`) and emits **one line per actionable event** onstdout, staying quiet during healthy idle.```bash.skills/operate/scripts/operator_watch.sh # defaults below.skills/operate/scripts/operator_watch.sh data/clawback.run.log data/clawback.run.pid```Defaults match `run_monitor.sh`:- `LOG_FILE` = `data/clawback.run.log`- `PID_FILE` = `data/clawback.run.pid`- poll cadence: `OPERATOR_WATCH_POLL_SEC` (default 5s)## What it emits- log lines matching `[error]` / `[warn]` / `→ 4xx|5xx` / `failed` / `self-loop` / `EADDRINUSE` / `ECONN*` / `unhandled` / `Error:`- two INFO signals an operator wants: `clawback listening` (a (re)bind) and `runtime mode toggled` (e.g. the baseline→armed flip after a fresh proxy's 5-turn capture window, or any admin toggle)- a synthetic `[error] PROXY DOWN …` line the moment the proxy pid stops responding — then it **exits non-zero** so the watch ends deliberately instead of hanging silent## Why not just `run_monitor.sh --attach`?`--attach` only tails the log. macOS/BSD `tail` has no `--pid`, so a crashmakes the log go quiet and an attached follower can't tell "dead" from"idle". Only `run_monitor.sh`'s foreground `follow` mode has a livenesswatcher — but that mode starts its **own** proxy and would collide on theport with one already detached. This script adds liveness to thealready-detached case without touching the port.## Agent usage (the operator loop)1. `.skills/scripts/run_monitor.sh --detach` — start the proxy.2. Point the **Monitor** tool at `.skills/operate/scripts/operator_watch.sh` with `persistent: true`. Each emitted line becomes a notification.3. On a `PROXY DOWN` (or a crash signature), read the tail of `data/clawback.run.log` to find the cause — that's the "pattern in the logs that needs fixing" — then bring it back with the [restart](../restart/SKILL.md) skill and re-arm the Monitor.Stop the proxy with the [shutdown](../shutdown/SKILL.md) skill; the watchexits on its own when the proxy is gone.

Frequently asked questions

Operate