goose

goose is an agent for coding agents from oxbshw/watch-skill. It costs 0 tokens per session (514 once invoked), scanned A, original, MIT.

A setup guide for connecting the Watch Skill video-analysis tools to OpenClaw, an agent system that discovers instruction files called skills. It covers installation, skill discovery, configuration, and a basic test.

In plain words
What is it for?
Use it to let OpenClaw watch online videos, answer time-specific questions, and use Watch Skill workflows such as extracting structure or recovering from errors.
Why use it?
It explains how to make the tools available through OpenClaw's skill directories without requiring a separate tool configuration.

Agent

Part of the watch-skill plugin — 10 skills, 1 command, 27 agents, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/oxbshw/watch-skill/goose
Clone the repo
git clone --depth 1 https://github.com/oxbshw/watch-skill

Or install watch-skill, the plugin that ships this one along with the rest of its 10 skills, 1 command, 27 agents, 1 MCP server.

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 goose

README.md
[![agentmods](https://agentmods.dev/badge/agents/oxbshw/watch-skill/goose.svg)](https://agentmods.dev/agents/oxbshw/watch-skill/goose)
Your own site
<a href="https://agentmods.dev/agents/oxbshw/watch-skill/goose"><img src="https://agentmods.dev/badge/agents/oxbshw/watch-skill/goose.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00000 $0.00514
Opus 5 $0.00000 $0.00257
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00051

Measured 3d ago against content hash bd7ed915a74f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goose scanned grade A with 0 findings 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 3d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/agents/goose.md · 68 lines

What it actually says

Watch Skill in Goose

Status: doc-verified ☑ — config matches Block's official Goose docs; not executed here.

Goose calls MCP servers "extensions"; a command-line extension is exactly our stdio server.

Install

uvx --from "watch-skill[standard]" watch-skill doctor

uvx fetches the package on first use and needs no checkout. Prefer a permanent install? pipx install "watch-skill[standard]", then use "command": "watch-skill", "args": ["serve"] in the config below.

git clone https://github.com/oxbshw/watch-skill && cd watch-skill
uv sync --extra all
uv run watch-skill doctor

Then run watch-skill setup, which writes the config pointing at your checkout rather than the published package.

Configure

Either run goose configureAdd ExtensionCommand-line Extension and enter the command below, or add the block to ~/.config/goose/config.yaml yourself:

extensions:
  watch-skill:
    name: Watch Skill
    type: stdio
    enabled: true
    cmd: uvx
    args: ["--from", "watch-skill[standard]", "watch-skill", "serve"]
    timeout: 300

timeout: 300 matters: a first watch_video on a long clip is a real pipeline (download, frames, OCR, transcription), not a quick lookup.

Smoke test (3 steps)

  1. goose session, then: "Watch https://www.youtube.com/watch?v=aqz-KE-bpKQ and tell me what happens at 0:10."
  2. Approve the watch_video call.
  3. Follow up: "what color is the bird?" — should call ask_video, no re-processing.

Notes

  • Goose is model-agnostic; Watch Skill's report is plain text + image blocks, so any model Goose drives can read at least the text. Frame paths are in the text for models without vision.
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. 3d ago First seen · 68 lines · 0 tokens per session scan A bd7ed915a74f

Subscribe to this mod's changes

goose is an agent published in the GitHub repository oxbshw/watch-skill (320 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 514 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.