A local camera-monitoring tool for watching for a visual condition, such as whether a dog is visible. It connects a camera stream to a follow-up response from the coding assistant.

Use it to set up a camera, select a device, and create a monitor for a stated visual condition. It is described for local camera monitoring through a FaceTime camera bridge.

It removes the need for the assistant to repeatedly inspect the camera manually. The description does not say how often it checks or what actions it takes after detecting a condition.

videomemory — Skill for Claude Code by Clamepending

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 Clamepending/videomemory --skill videomemory

Clone the repo

git clone --depth 1 https://github.com/Clamepending/videomemory

Made for: Claude Code.

Or install videomemory, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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/clamepending/videomemory/videomemory/github.svg)](https://agentmods.dev/skills/clamepending/videomemory/videomemory)

Your own site

<a href="https://agentmods.dev/skills/clamepending/videomemory/videomemory"><img src="https://agentmods.dev/badge/skills/clamepending/videomemory/videomemory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/clamepending/videomemory/videomemory"><img src="https://agentmods.dev/badge/skills/clamepending/videomemory/videomemory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 494 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	$0.00031	$0.00494
Opus 5	$0.00015	$0.00247
Sonnet 5	$0.00006	$0.00099
Haiku 4.5	$0.00003	$0.00049

Measured 10d ago against content hash 32c73a24b6c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

videomemory 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 10d 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.

claude-videomemory-channel/skills/videomemory/SKILL.md · 42 lines

What it actually says

VideoMemory

VideoMemory is a local camera monitor for Claude Code. Treat it as the user's local perception service: VideoMemory owns the video stream and long-running watch loop; Claude owns the user request and the follow-up response.

When the user says something like "download VideoMemory and watch my dog from my FaceTime camera":

Call mcp__videomemory__setup_local first.
- Use the default camera_id: "facetime" unless the user names another camera.
- This starts/checks the local VideoMemory service, wires the webhook back to this Claude channel, and opens the browser FaceTime camera bridge.
If setup returns readiness.ready: false, report the exact readiness warnings and tell the user to grant browser camera permission in the opened camera tab. Do not claim the monitor is armed yet.
Use mcp__videomemory__list_devices only if the user names a different camera or setup did not identify the expected device.
Create the monitor with mcp__videomemory__create_monitor.
- Put only the visual condition in task_description, for example the user's pet dog is visible.
- Use io_id: "browser_facetime" for the browser FaceTime bridge unless the user chose a different device.
- Use monitor_type: "binary" for simple true/false criteria such as "dog is visible", "person is at the door", or "phone is held up".
- Use monitor_type: "general" only when the user wants richer notes or open-ended scene analysis.
Read the create-monitor response. If readiness.ready is false, surface the blocker. If ready, tell the user the monitor is armed and VideoMemory will wake Claude when the condition is met.
Do not poll. VideoMemory will push a channel event when the monitor fires.

For incoming VideoMemory channel events, use the event note/task fields to decide the response. If a test asks for a visible reply, call mcp__videomemory__reply.

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.

10d ago First seen · 42 lines · 31 tokens per session scan A 32c73a24b6c2

Subscribe to this mod's changes

videomemory is a skill published in the GitHub repository Clamepending/videomemory (5 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 494 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.

Hardware and IoT

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

hsb-flash

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…

NVIDIA/skills · 94 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens