pi

A guide for using Watch Skill with Pi, a coding agent that loads command-line tools through skills.

In plain words
What is it for?
It is for configuring Watch Skill as a Pi skill, running its health check, and optionally connecting it through a third-party MCP adapter.
Why use it?
It documents how to install Watch Skill, make it available to Pi, and check that the setup 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/pi
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 465 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 $0.00465
Opus 5 $0.00000 $0.00233
Sonnet 5 $0.00000 $0.00093
Haiku 4.5 $0.00000 $0.00047

Measured 2d ago against content hash 9be1de51c7eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pi 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/pi.md · 58 lines

What it actually says

Watch Skill in Pi

Status: doc-verified ☑ — matches the pi-coding-agent docs; not executed here.

Pi deliberately ships no MCP client ("MCP servers are overkill for most use cases" — their words, and for a CLI-first tool they have a point). Pi's native extension surface is skills: CLI tools with instructions. Watch Skill is a CLI, so this is the honest path — no adapter code.

Install

# `watch-skill` on PATH — Pi skills shell out to it
uv tool install "watch-skill[standard]"   # or: pipx install "watch-skill[standard]"
watch-skill doctor

Configure

Add the skills library as a Pi skills directory — the SKILL.md files document the CLI exactly the way Pi skills expect:

pi --skills-dir C:\path\to\watch-skill\adapters\claude-skill\skills

(or add the directory to your Pi settings' skills paths; Pi also loads skills from packages, so a pi package wrapping the same directory works for sharing.)

Prefer MCP anyway? The third-party pi-mcp-adapter extension adds MCP client support to Pi; feed it the standard entry:

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

Smoke test (3 steps)

  1. pi "Watch https://www.youtube.com/watch?v=aqz-KE-bpKQ - what happens at 0:10?"
  2. Pi should run watch-skill watch ... per the skill instructions and answer with timestamps.
  3. Follow up with a question about the same video — the skill directs it through watch-skill ask, not a re-watch.

Notes

  • watch-skill ask prints text-first evidence, so Pi's no-vision setups still get grounded answers; frame paths are in the output when looking is warranted.
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 · 58 lines · 0 tokens per session scan A 9be1de51c7eb

Subscribe to this mod's changes

pi 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 465 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.