watch-and-act

watch-and-act is a skill for Claude Code from ulpi-io/autonomous-engineering. It costs 149 tokens per session (3,201 once invoked), scanned A, original, no licence file.

A monitoring skill that waits for an outside event, such as a CI result, deployment, queue update, or endpoint change, by checking at scheduled intervals.

In plain words
What is it for?
Use it to wait for external signals, detect when they change, and take the requested action before a set deadline.
Why use it?
It lets an agent continue watching for a result that the work environment cannot send as a notification.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the autonomous-engineering plugin — 18 skills shipped together

Good fit Use it to wait for external signals, detect when they change, and take the requested action before a set deadline.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ulpi-io/autonomous-engineering/watch-and-act
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ulpi-io/autonomous-engineering --skill watch-and-act
Clone the repo
git clone --depth 1 https://github.com/ulpi-io/autonomous-engineering

Made for: Claude Code.

Or install autonomous-engineering, the plugin that ships this one along with the rest of its 18 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for watch-and-act

README.md
[![agentmods](https://agentmods.dev/badge/skills/ulpi-io/autonomous-engineering/watch-and-act.svg)](https://agentmods.dev/skills/ulpi-io/autonomous-engineering/watch-and-act)
Your own site
<a href="https://agentmods.dev/skills/ulpi-io/autonomous-engineering/watch-and-act"><img src="https://agentmods.dev/badge/skills/ulpi-io/autonomous-engineering/watch-and-act.svg" alt="Measured on agentmods" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00149 $0.03201
Opus 5 $0.00075 $0.01600
Sonnet 5 $0.00030 $0.00640
Haiku 4.5 $0.00015 $0.00320

Measured 8d ago against content hash dd73fad3f060, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

watch-and-act scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/watch-state.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Check** the signal with a real command (`gh run list`/`gh pr checks`, a curl health check, a queue
watch-and-act/SKILL.md · 203 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 203 lines · 149 tokens per session scan A dd73fad3f060

Subscribe to this mod's changes

watch-and-act is a skill published in the GitHub repository ulpi-io/autonomous-engineering (2 stars, last pushed 21d ago), with no licence file. It adds 149 tokens to every session and 3,201 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.