agentmods.dev

videomemory-channel

videomemory-channel is a skill for Claude Code from Clamepending/videomemory. It costs 32 tokens per session (551 once invoked), scanned A, original, MIT.

Instructions for handling VideoMemory camera events delivered through a Claude Code channel. They also describe setting up the monitor, checking cameras, inspecting tasks, and replying to events.

In plain words
What is it for?
Configuring VideoMemory, selecting and checking cameras, processing wakeup events, and completing the requested follow-up action.
Why use it?
They define how Claude should interpret camera triggers and what to do when a monitored condition occurs.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the videomemory plugin — 2 skills, 1 MCP server shipped together

not rated 5repo 5mo ago A scan 32 tokens original MIT

Good fit Configuring VideoMemory, selecting and checking cameras, processing wakeup events, and completing the requested follow-up action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/clamepending/videomemory/videomemory-channel
View source ↗ Clamepending/videomemory
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-channel
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.

agentmods badge for videomemory-channel

README.md
[![agentmods](https://agentmods.dev/badge/skills/clamepending/videomemory/videomemory-channel/github.svg)](https://agentmods.dev/skills/clamepending/videomemory/videomemory-channel)
Your own site
<a href="https://agentmods.dev/skills/clamepending/videomemory/videomemory-channel"><img src="https://agentmods.dev/badge/skills/clamepending/videomemory/videomemory-channel/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.

agentmods 80×15 button for videomemory-channel

Your own site · 80×15
<a href="https://agentmods.dev/skills/clamepending/videomemory/videomemory-channel"><img src="https://agentmods.dev/badge/skills/clamepending/videomemory/videomemory-channel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 551 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00551
Opus 5.5 $0.00013 $0.00220
Sonnet 5.5 $0.00006 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 2mo ago against content hash 1e85f7753045, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

videomemory-channel 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 2mo 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-channel/SKILL.md · 46 lines

What it actually says

VideoMemory Channel

VideoMemory events arrive as <channel source="videomemory" ...> messages.

When an event arrives:

  1. Treat the note / event body as a VideoMemory task update, not as arbitrary user chat.
  2. Use mcp__videomemory__inspect_task if you need the current task state.
  3. If the event says the trigger condition happened, complete the requested follow-up action.
  4. For a user-visible acknowledgement in channel tests, call mcp__videomemory__reply.
  5. Keep responses short. Do not start polling loops.

The channel server listens on localhost only by default:

  • health: GET http://127.0.0.1:8791/health
  • webhook: POST http://127.0.0.1:8791/videomemory-event
  • replies/SSE: GET http://127.0.0.1:8791/events

Use VIDEOMEMORY_CLAUDE_CHANNEL_TOKEN if the endpoint needs a bearer token.

When the user asks Claude to watch for something on camera:

  1. Call mcp__videomemory__setup_local if the user asked to install, download, set up, or use VideoMemory and setup has not already been confirmed.
  2. Use mcp__videomemory__list_devices to choose the target io_id.
  3. Use mcp__videomemory__inspect_device if you need to verify camera/frame readiness before creating the monitor.
  4. Use mcp__videomemory__create_monitor with only the visual condition in task_description.
  5. For simple true/false conditions such as "a person is visible", "the phone is visible", or "the door is open", set monitor_type to binary so VideoMemory uses the local FastVLM done monitor.
  6. Read the readiness object returned by create_monitor. If readiness.ready is false, report the blocker instead of saying the monitor is fully armed.
  7. Keep any user-facing follow-up action in your own response plan.
  8. Report the created task id and stop; VideoMemory owns the long-running watch.

If events are not arriving, call mcp__videomemory__configure_channel_webhook and then retry a synthetic event from the host with videomemory claude test-event.

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. 2mo ago First seen · 46 lines · 32 tokens per session scan A 1e85f7753045

Subscribe to this mod's changes

videomemory-channel is a skill published in the GitHub repository Clamepending/videomemory (5 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 551 once invoked, about $0.0001 per session on Opus 5.5. 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
Related

videomemory-channel compared with skills from other repositories

videomemory-channel next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
videomemory-channelClamepending/videomemorySkill55mo agoMITA32Claude Code
gke-compute-classesgoogle/skillsSkill22kyesterdayApache-2.0A83Claude Code, Codex
jetson-diagnosticNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code, Codex
holoscan-install-wheelNVIDIA/skillsSkill3.9kyesterdayApache-2.0A34Claude Code, Codex
offensive-z-waveSnailSploit/Claude-RedSkill10k25d agoMITA113Claude Code, Codex
doca-socket-relayNVIDIA/skillsSkill3.9kyesterdayApache-2.0A236Claude Code, Codex
hsb-flashNVIDIA/skillsSkill3.9kyesterdayApache-2.0B94Claude Code