roo-code

A setup guide for using Watch Skill inside Roo Code, a coding assistant. It explains how to install the tool, configure it for one project or all projects, and test video questions.

In plain words
What is it for?
Use it to add Watch Skill to Roo Code's MCP settings, configure project or global access, and check that Roo can watch a video and answer follow-up questions.
Why use it?
It makes the connection between Roo Code and Watch Skill repeatable for individuals or teams. Project settings can be committed so collaborators use the same configuration.

Agent

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/roo-code
Clone the repo
git clone --depth 1 https://github.com/oxbshw/watch-skill
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 526 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 $0.00526
Opus 5 $0.00000 $0.00263
Sonnet 5 $0.00000 $0.00105
Haiku 4.5 $0.00000 $0.00053

Measured yesterday against content hash d596b4e62955, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

roo-code 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 yesterday.

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/roo-code.md · 64 lines

What it actually says

Watch Skill in Roo Code

Status: doc-verified ☑ — config matches the official Roo Code MCP docs; not executed here.

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

Configure

Roo Code reads two levels. Project scope is .roo/mcp.json in the repository root; global scope is mcp_settings.json, reachable from the MCP panel. When a server name appears in both, the project file wins.

{
  "mcpServers": {
    "watch-skill": {
      "command": "uvx",
      "args": ["--from", "watch-skill[standard]", "watch-skill", "serve"]
    }
  }
}

Commit .roo/mcp.json to give a whole team the same video tools.

Smoke test (3 steps)

  1. Ask Roo: "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

  • Roo substitutes ${env:VAR} when it loads the config, so a provider key can be referenced instead of pasted: "env": {"WATCHSKILL_ANTHROPIC_API_KEY": "${env:ANTHROPIC_API_KEY}"}.
  • Add watch_video and ask_video to alwaysAllow once you trust them; the loop tools are worth leaving on manual approval, since loop_video_gen and loop_game run commands you supply (see SECURITY.md).
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. yesterday First seen · 64 lines · 0 tokens per session scan A d596b4e62955

Subscribe to this mod's changes

roo-code is an agent published in the GitHub repository oxbshw/watch-skill (320 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 526 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.