agentleFS
Sign inStart free
leolou0512leolou0512/claude-skills/skills/watch/SKILL.md

watch

Skill1 starsChanged 26 days agoMITView on GitHub

Silent two-tier watcher for any session. A plain script checks cheaply and wakes the session as soon as something is ready or broken; a 50-minute wake keeps the conversation cache warm. Use whenever a session waits on a job, run, deploy, build, team or external state, or when anyone says patrol, monitor, watcher, "tell me when done", "keep checking", or would otherwise reach for cron, sleep loops or repeated polling.

48 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use decision-map, map and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Mathews-TomSkill

    decision-map

    Use when mapping unresolved architecture, policy, or scope decisions before planning, or working one decision ticket, including a prototype ticket whose throwaway evidence the prototype package builds. Also applies to "map the decisions", "decision map", and "wayfinder". Not for implementation slices of a known feature, milestone plans, general UI generation, standalone prototypes outside a decision map (use prototype), or adopting experimental code into production.

    Also in 3 projects that use this

  • AWSSkill

    map

    Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.

    Also in 3 projects that use this

  • dubwoahSkill

    ask

    Answer questions about the codebase without generating or modifying any code. Use when the user wants to understand how something works, find where something is defined, or explore the project structure. Invoked with /ask.

    Also in 3 projects that use this

  • javatarzSkill

    wiki

    Access and manage the local GitHub Wiki clone. Use this skill when you need to read wiki content (architecture, design docs, guides), update wiki documentation, check wiki status, or push wiki changes. The wiki contains high-level system design and architectural documentation.

    Also in 3 projects that use this

  • renatorozasSkill

    grill

    Adversarial code review. Don't let me ship until the changes pass your scrutiny.

    Also in 3 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 7 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 44 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never poll from the model.

    line 8
  2. Distinctive:

    Check output: act and report, then relaunch if still waiting.

    line 20
  3. Very specific:

    Use a slower --every for checks heavier than a few seconds.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 44 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Watch

Never poll from the model. Every model wake re-reads the whole context.

# Bash with run_in_background: true
bash ~/.claude/skills/watch/watch.sh -- <check command>
  • Tier 1, silent: the check runs every 60 s (--every) as plain shell. It exits, waking the session, as soon as the check prints something new. Quiet costs no tokens.
  • Tier 2, keep warm: at 50 min it exits with WARM. That read resets the 1-hour cache, so the next real wake doesn't pay a rebuild. --warm 0 turns it off: use when nothing may wake this session for over a day.

On wake

  • WARM: relaunch the same command. No text to the user.
  • Check output: act and report, then relaunch if still waiting.
  • watch: check failed: the check broke. Fix it and tell the user; a dead watcher is not calm.

Writing the check

Print only when action is needed; print nothing otherwise. Same output twice is reported once.

wait forcheck
process endbash -c 'kill -0 <pid> 2>/dev/null || echo "<pid> ended"'
result filebash -c '[ -e <path> ] && echo "<path> ready"; true'
log failuregrep -m1 -E "Traceback|FAILED" <log>
several thingsa small script that echoes one line per item

Use a slower --every for checks heavier than a few seconds.

Limits

  • The watcher dies with its session. To outlive the session, run the job detached with on-disk state; the watcher only reports on it.
  • Subagents have a 5-minute cache: they hand back with the job path and let the lead watch, rather than wait.
  • Cost numbers are API-price estimates; subscription weights are unpublished.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free