stack/skills/ms-watch/SKILL.md

name, description, disable-model-invocation

name	description	disable-model-invocation
ms-watch	Use for all instances where a watch, wait, or agentic status check is needed. This skill avoid the need for wait cycles and other methods used to wait for an action outcome.	false

ms-watch — self-armed condition watches

One CLI call arms an isolated systemd --user transient timer per watch. Each tick is a fresh, cgroup-isolated process; no loop, no script, no orphan. You never sleep, never write a watch script, never background anything.

Tool

MOSAIC_AGENT_SEND="/absolute/checkout/tools/tmux/agent-send.sh" \
/absolute/checkout/tools/agent-watch/agent-watch.sh start \
  --name <lowercase-id> --session <your-tmux-session> \
  [--socket <tmux-socket>]            # REQUIRED for mosaic-fleet seats using tmux
  --when '<shell command>'            # exit 0 = met; quote it
  --message "text delivered to you" \
  [--class actionable|reaction|human|digest|terminal-log] \
  [--interval 30] [--timeout 3600] [--repeat] [--quiet-timeout]

agent-watch.sh list                   # your host's watches
agent-watch.sh log <name>             # what it did and why
agent-watch.sh stop <name>            # retire + clean state

Use the actual checkout path in place of /absolute/checkout. The CLI otherwise uses a sender under $HOME/.config/mosaic, which may not be this repository's reviewed transport. No timers or meta-watch are installed merely by loading this skill. Live watch operations require assignment authority. list and status can write stale-notice claims and send messages; they are not read-only probes. The CLI's status [--json] returns 0 for clean, 3 for stale/dead meta-watch, and 6 for an unreachable systemd user bus. Do not infer health from a failed query.

Rules

1. Name it for the thing watched (ci-pr1350-green, peer-orch-01-reply), not for yourself — names appear in [watch:<name>] message prefixes and in systemctl list-timers 'agent-watch-*'.
2. Interval floor is 10s. A watcher is a fallback cadence. If you find yourself wanting 1s polls, the real fix is an event, not a faster watch.
3. Timeout is real (default 1h): on expiry you get one terminal-log note (unless --quiet-timeout) and the watch retires. A watch is never forever; re-arm deliberately if the condition is still pending.
4. Conditions are cron-style: clean-ish environment, cwd=$HOME. Use absolute paths. Do NOT rely on ambient credentials — resolve tokens through the git credential helper or absolute service-credential paths.
5. Transport is not application acceptance. The current watcher treats sender exit 0 and 2 as terminal for retry purposes. Exit 0 means transport dispatched, application acceptance unknown; exit 2 does not prove submission or receipt. Its legacy delivered log wording is not an acknowledgement. Other sender failures retry twice, then retire; do not add blind resends.
6. A broken condition (exit ≠ 0/1) retires the watch with a terminal-log note. Check log <name> before re-arming — re-arming a broken condition without fixing it just burns another timeout.
7. --repeat re-arms after every delivery. Default is one-shot on purpose: each watch should correspond to one pending fact.
8. Retire your watches when the mission closes (stop). list shows stale-state entries whose timer is gone; stop removes those too.
9. Fleet seats MUST pass --socket mosaic-fleet. Socket selection is explicit option, then MOSAIC_TMUX_SOCKET, then unique discovery; ambiguity refuses.

When NOT to watch

• Waiting on another SEAT: send them a message (agent-send / comms) instead — a watch polling their output is a loop wearing a hat.
• Waiting on yourself: just do the next thing.
• Something that already has a wake path (fleet watcher injects comms automatically): those arrive without any watch.

Failure model (what you'll see)

Symptom	Meaning
started watcher ... then nothing, timer inactive	condition broke (exit ≠ 0/1) or timeout hit — log <name> says which
[watch:x] ... timeout after Ns	retired; re-arm only if still relevant
delivered (rc=2) in log	legacy retry classification, not proof of receipt; reconcile through authorized records, not private-pane inspection
delivery failed rc=1 after 3 attempts	your session was gone; restart it, then re-arm