What is kimi-code-video?

A procedure for using local Kimi-Code to analyse video files and return a Chinese summary, timeline, notable moments, and editing ideas. Kimi-Code is a local AI tool for video analysis.

Use it with files such as MP4, MOV, M4V, or WebM to identify scenes, timestamps, visuals, people, actions, subtitles, narration, and interface flows.

It gives a repeatable way to inspect a video and separate observed details from uncertainties.

kimi-code-video — Skill for Claude Code and Codex by cyuanxv

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.

Any agent

npx skills add cyuanxv/agent-cockpit --skill kimi-code-video

Clone the repo

git clone --depth 1 https://github.com/cyuanxv/agent-cockpit

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cyuanxv/agent-cockpit/kimi-code-video.svg)](https://agentmods.dev/skills/cyuanxv/agent-cockpit/kimi-code-video)

Your own site

<a href="https://agentmods.dev/skills/cyuanxv/agent-cockpit/kimi-code-video"><img src="https://agentmods.dev/badge/skills/cyuanxv/agent-cockpit/kimi-code-video.svg" alt="Measured on agentmods" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 485 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.00485
Opus 5	$0.00019	$0.00243
Sonnet 5	$0.00008	$0.00097
Haiku 4.5	$0.00004	$0.00049

Measured 7d ago against content hash bb8e5c43f9c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

kimi-code-video 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/kimi_video_analyze.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/kimi-code-video/SKILL.md · 53 lines

What it actually says

Kimi-Code Video

Use this skill when the user asks Codex to analyze a local video with Kimi-Code, asks for video summaries, scene or shot timelines, key moments, editing suggestions, or explicitly mentions Kimi-Code's video ability.

Inputs

Ask for a local video path if the user did not provide one. Accept common video files such as .mp4, .mov, .m4v, and .webm.

Default analysis goal:

Chinese Markdown output.
One-sentence conclusion.
Content summary.
Scene/timeline breakdown with timestamps when possible.
Key visuals, people, actions, subtitles, narration, and UI flow.
Editing suggestions and follow-up processing ideas.
Uncertainties, separated from observed facts.

Procedure

Verify that the video file exists before running Kimi.
Run kimi --version and kimi doctor if Kimi-Code availability is uncertain.
If kimi -p fails with No model configured, stop and tell the user to run kimi login, then kimi -p "ping" --output-format text.

Prefer the direct path first:

skills/kimi-code-video/scripts/kimi_video_analyze.sh "<video_path>" "<analysis_goal>"

If Kimi does not actually inspect the video and only treats the path as text, retry with extracted frames:
```
skills/kimi-code-video/scripts/kimi_video_analyze.sh --mode frames "<video_path>" "<analysis_goal>"
```
Read the output file path printed by the script. Summarize the result for the user and point to the full output file.

Output Contract

For normal analysis, return the generated Markdown file path plus a concise summary. For structured downstream handoff, follow references/output-format.md.

Safety

Do not delete or overwrite the source video.
Do not upload the video to public locations.
Do not run Kimi with --yolo.
Do not start kimi web with --dangerous-bypass-auth.
Keep generated outputs local.

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

7d ago First seen · 53 lines · 39 tokens per session scan A bb8e5c43f9c0

Subscribe to this mod's changes

kimi-code-video is a skill published in the GitHub repository cyuanxv/agent-cockpit (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 485 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.

Claude Code Creative and media agent agent-workspace ai-agents codex gemini-cli

podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

bytedance/deer-flow · 38 tokens

nano-banana-pro-openrouter

Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.

opensquilla/opensquilla · 49 tokens

spotify-player

Terminal Spotify playback/search via spogo (preferred) or spotifyplayer. Use when the user asks to play music, search for a song, skip a track, pause playback, check what is currently playing, control Spotify, list audio devices, or manage a Spotify queue from the terminal.

elizaOS/eliza · 60 tokens

imagegen

Generate original images, artwork, product visuals, diagrams, or other raster assets with the desktop's configured image provider. Use whenever the user asks to create or generate an image.

NanmiCoder/cc-haha · 38 tokens

voice-clone-lab

A consent-controlled tool for creating a reusable synthetic voice from a local speaker recording.

opensquilla/opensquilla · 52 tokens

srt-from-script

Build an SRT subtitle file from a 3-shot short-drama script (ai-video-script OUTPUT FORMAT). Reads each SHOTN block's DURATIONS + VOICEOVER, emits cumulative-timestamped SRT cues. Pure text-processing, no LLM, no network. Used by meta-short-drama between merge and the final subtitle-burn step.

opensquilla/opensquilla · 78 tokens