video-navigation

video-navigation is a skill for Claude Code, Codex from getsquish/squish. It costs 112 tokens per session (2,124 once invoked), scanned C, original, Apache-2.0.

A method for examining videos through timestamped visual contact sheets and audio-activity maps.

In plain words
What is it for?
Use it to find scene changes, visible events, or unusual audio, then inspect the relevant time range and report exact timecodes.
Why use it?
It makes a video searchable when the agent cannot directly ingest the entire clip, reducing the need to guess where an event occurs.

Skill for Claude CodeCodex

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 skills/getsquish/squish/video-navigation
Any agent
npx skills add getsquish/squish --skill video-navigation
Clone the repo
git clone --depth 1 https://github.com/getsquish/squish

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.

agentmods badge for video-navigation

README.md
[![agentmods](https://agentmods.dev/badge/skills/getsquish/squish/video-navigation.svg)](https://agentmods.dev/skills/getsquish/squish/video-navigation)
Your own site
<a href="https://agentmods.dev/skills/getsquish/squish/video-navigation"><img src="https://agentmods.dev/badge/skills/getsquish/squish/video-navigation.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00112 $0.02124
Opus 5 $0.00056 $0.01062
Sonnet 5 $0.00022 $0.00425
Haiku 4.5 $0.00011 $0.00212

Measured 3d ago against content hash 6a6499041b40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

video-navigation scanned grade C with 1 finding 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 3d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

and do not refuse — compress the clip into **timestamped contact sheets** (one image per
skills/video-navigation/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video navigation: treat video as an address space

You have vision but cannot ingest video. When a task involves a video's content, do not guess and do not refuse — compress the clip into timestamped contact sheets (one image per window of the clip, frames sampled evenly, each cell stamped with its timecode) and, when the tool provides it, an audio-activity band on the same absolute timeline. The map is your index into the video; zooming is how you navigate it.

The reasoning primitive: video → visual + audio activity map → inspect → zoom where it matters → answer with timecodes.

Non-goals. This is a video navigation and retrieval skill, not a video editing workflow. Navigation over editing; retrieval over transformation. Audio activity is an energy envelope, not transcription, sound classification, or emotion inference; a sheet is a sequence map, not motion replacement. Your deliverable is answers with timestamps — absolute seconds that hand off cleanly to any editing or clipping tool, which is where this skill stops.

When to use

  • "What happens in this video / screen recording?"
  • The question spans time: before/after, a scene change, progress, "find the moment when…".
  • The answer needs precise citations ("at 0:07 the press comes down").
  • The clip is too long or too large to ingest any other way.

When not to use: the user needs one specific frame only (extract that frame instead); the question cannot be answered from either frames or activity timing. Pairing note: if the question is about what was said, pair with an ASR/transcript tool. Audio activity can locate when something happened, but cannot recover words or identify the source of a sound.

What you need: a squisher

Any tool implementing this contract (see Wiring below for today's implementations):

(video, density?, start?, end?) → sheet image(s) + per-cell timecodes + optional audio activity

  • density — grid size per sheet (3x36x6): more frames per call.
  • start/end — window the run to a time range: more precision per frame.
  • Output: sheet images in time order, plus the timecode of every cell.
  • Local Squish 0.3+ also returns audio.samples[] (time = absolute seconds, level = 0..1) and burns the same activity envelope above the grid. normalization: clip_peak means zoom calls stay comparable to the whole clip.

Read the full file on GitHub · 147 lines

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. 3d ago First seen · 147 lines · 112 tokens per session scan C 6a6499041b40

Subscribe to this mod's changes

video-navigation is a skill published in the GitHub repository getsquish/squish (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 112 tokens to every session and 2,124 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.