kimi-code

A setup guide for connecting the watch-skill tool to Kimi Code CLI. Kimi Code CLI is a command-line coding assistant, while watch-skill watches a YouTube video and provides a command-line service for it.

In plain words
What is it for?
Use it to install watch-skill with uvx or pipx, add it to Kimi Code at user or project level, and test it with a YouTube video. The input says the guide was checked against official documentation but not executed.
Why use it?
It explains how to install, configure, and smoke-test the connection instead of leaving the setup to guesswork. A smoke test is a small check that a 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/kimi-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 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 yesterday against content hash dcb73b44f627, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kimi-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/kimi-code.md · 65 lines

What it actually says

Watch Skill in Kimi Code CLI

Status: doc-verified ☑ — config matches Moonshot's official Kimi Code CLI 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

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

Configure

User level: ~/.kimi-code/mcp.json (shared across projects). Project level: .kimi-code/mcp.json in the repo (wins on name conflicts). The format is the common mcpServers shape:

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

Or skip the JSON and use the CLI/TUI: kimi mcp add from the shell, or /mcp-config inside a session.

Smoke test (3 steps)

  1. kimi, 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

  • Entries with command are stdio servers; entries with url are HTTP. For a remote setup, watch-skill serve --http and a url entry pointing at http://<host>:8747/mcp also works.
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 · 65 lines · 0 tokens per session scan A dcb73b44f627

Subscribe to this mod's changes

kimi-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 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.