What is video-ingest?

A guide for reading and comparing WebM, MP4, and GIF recordings. It helps an agent examine video frames over time, including test recordings and bug reports.

Use it to investigate end-to-end test videos, reproduce interface bugs, review multi-step workflows, and diagnose visual differences.

It makes it easier to find when a screen problem happens and compare a working recording with a failing one.

How putervision/state-memory-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to putervision/state-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/putervision/state-memory-mcp/main/.agents/skills/video-ingest/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/putervision/state-memory-mcp

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/putervision/state-memory-mcp/video-ingest.svg)](https://agentmods.dev/skills/putervision/state-memory-mcp/video-ingest)

Your own site

<a href="https://agentmods.dev/skills/putervision/state-memory-mcp/video-ingest"><img src="https://agentmods.dev/badge/skills/putervision/state-memory-mcp/video-ingest.svg" alt="Measured on agentmods" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 877 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	$0.00038	$0.00877
Opus 5	$0.00019	$0.00439
Sonnet 5	$0.00008	$0.00175
Haiku 4.5	$0.00004	$0.00088

Measured 7d ago against content hash a4ba4c1c9275, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

video-ingest 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.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

video-ingest — 100% identical, 13 lines differ
video-ingest — 100% identical, 0 lines differ

.agents/skills/video-ingest/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Frame Digesting & Temporal Memory Skill (video-ingest)

This skill provides step-by-step guidance, best practices, and operational patterns for digesting WebM, MP4, and GIF video recordings using @putervision/vision-memory-mcp.

1. When to Use Video Ingestion

Use video ingestion whenever you encounter:

E2E Playwright / Cypress / Selenium Test Artifacts: Recorded .webm screenchunks or .mp4 test run videos.
Bug Reproduction Videos: User-uploaded screen recordings demonstrating UI glitches or crashes.
UI Walkthrough Recordings: Demonstrations of complex multi-step user workflows.
Visual Regression Diagnostics: Comparing a passing baseline video run against a failing test run.

2. Ingestion Strategies & Parameter Tuning

Scenario	Recommended Parameters	Why
Action Event Timestamps (Highest Precision)	`action_timestamps: [1.2, 3.5, 7.0]`	Samples keyframes at exact interaction timestamps (clicks, types, navigation events) from test runners or state-memory logs.
Dynamic UI / Animations	`scene_threshold: 0.3`, `fps: 1`	Combines scene-change detection (`gt(scene,0.3)`) with 1 fps background sampling to capture major screen transitions without frame bloat.
High-Speed Test Runs	`fps: 2` or `fps: 5`	Increases frame rate sampling for rapidly switching UI test steps.
Long Screen Recordings	`fps: 0.5`, `scene_threshold: 0.4`	Lowers sampling rate to conserve storage while extracting unique keyframe states.

3. Mandatory Dual-MCP Evidence Workflow

When diagnosing bugs or linking test runs to task nodes:

Ingest Video: Call manage_video (action: "ingest") with file path and action timestamps.
Extract Evidence Payload: Read the returned evidence_payload containing source_video_id, frame_range, and timestamps_ms.
Build Evidence Pack: Call create_evidence_pack linking keyframe_state_ids with state-memory-mcp task or blocker node IDs.
Compare Trajectories (On Failure): Call compare_states(video_a_id: "...", video_b_id: "...") to pinpoint exact frame divergence points.

Read the full file on GitHub · 69 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.

7d ago First seen · 69 lines · 38 tokens per session scan A a4ba4c1c9275

Subscribe to this mod's changes

video-ingest is a skill published in the GitHub repository putervision/state-memory-mcp (79 stars, last pushed 18d ago), licensed MIT. It adds 38 tokens to every session and 877 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 2026-08-30.

Creative and media Research developer-tools mcp mcp-server model-context-protocol sqlite state-graph

openclaw-content-autopilot

AI content generation and auto-publishing MCP server with 5 tools for social platforms. Use when: (1) 'write a tweet about X' or 'draft LinkedIn post', (2) 'publish this to MoltBook' or 'post to social', (3) 'schedule content for tomorrow 9am', (4) 'how did my last post perform' or 'engagement stats', (5) 'what should…

yedanyagamiai-cmd/openclaw-mcp-servers · 130 tokens

threebrowser-studio-mcp

Author, inspect, render, validate, animate, and save Three.js WebGPU projects in the native ThreeBrowser Studio through its real threestudio MCP tools. Use whenever Codex is asked to build or edit a ThreeBrowser Studio scene, material, Blender-style shader or texture graph, animation, lighting setup, camera, or…

SamG-Coder/ThreeBrowserStudio · 122 tokens

talkthrough

Analyze narrated screen recordings and audio files — timestamped transcript, scene keyframes, OCR text, and wall-clock anchoring via the local talkthrough MCP server. Use when the user shares a recording or asks to triage feedback, extract meeting actions, or correlate a recording with logs.

korovin-aa97/talkthrough-mcp · 60 tokens

state-memory-mcp: Skill for Claude Code