amp

An Amp agent setup for watch-skill, a tool that lets an agent inspect videos and answer questions about what happens in them. It documents installation, configuration, and a short test using a YouTube video.

In plain words
What is it for?
Use it to install watch-skill in Amp, configure its MCP server, run a smoke test, and ask questions about video scenes.
Why use it?
It provides the commands and configuration needed to connect video watching to Amp and verify that the connection works.

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/amp
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 512 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 $0.00512
Opus 5 $0.00000 $0.00256
Sonnet 5 $0.00000 $0.00102
Haiku 4.5 $0.00000 $0.00051

Measured 2d ago against content hash 13c5050c4050, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

amp 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 2d 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/amp.md · 68 lines

What it actually says

Watch Skill in Amp

Status: doc-verified ☑ — config matches Sourcegraph's own Amp MCP setup guide; 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"] below.

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

Configure

The CLI does it in one line:

amp mcp add watch-skill -- uvx --from "watch-skill[standard]" watch-skill serve

Or edit settings directly. Amp namespaces its servers under amp.mcpServers rather than the bare mcpServers most clients use, so a block copied from Cursor or Cline needs that key changed:

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

Smoke test (3 steps)

  1. Ask Amp: "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 and answer from the index without re-processing.

Notes

  • Amp also accepts remote servers as a url, which is what watch-skill serve --http exposes (port 8747, /mcp). Keep it on loopback or put a bearer token in front of it — see Configuration.
  • The same settings key works in the CLI and the editor extensions; there is one server list, not two.
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. 2d ago First seen · 68 lines · 0 tokens per session scan A 13c5050c4050

Subscribe to this mod's changes

amp is an agent published in the GitHub repository oxbshw/watch-skill (320 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 512 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.