videomemory AGENTS.md

videomemory AGENTS.md is an instructions file for Codex, OpenCode from Clamepending/videomemory. It costs 2,260 tokens per session, scanned A, original, MIT.

Project instructions for VideoMemory, a video-monitoring service that analyzes camera feeds with AI and exposes the results through an HTTP API.

In plain words
What is it for?
Running VideoMemory, checking its health, configuring API keys, using its API, and connecting it to agent workflows or Claude Code channels.
Why use it?
They explain how to run the service and connect an external coding agent to it, including how visual events can trigger follow-up actions.

Instructions file for CodexOpenCode

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 instructions/clamepending/videomemory/agents-md
Clone the repo
git clone --depth 1 https://github.com/Clamepending/videomemory

Made for: Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/clamepending/videomemory/agents-md.svg)](https://agentmods.dev/instructions/clamepending/videomemory/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/clamepending/videomemory/agents-md"><img src="https://agentmods.dev/badge/instructions/clamepending/videomemory/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,260 This file is loaded in full into every session.
When invoked 2,260 The same file — it is already loaded in full.
Security scan A 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 $0.02260 $0.02260
Opus 5 $0.01130 $0.01130
Sonnet 5 $0.00452 $0.00452
Haiku 4.5 $0.00226 $0.00226

Measured 5d ago against content hash e79a7f5641ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

videomemory AGENTS.md scanned grade A 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X PUT http://localhost:5050/api/settings/GOOGLE_API_KEY \
AGENTS.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VideoMemory - Agent Integration Guide

VideoMemory is a video monitoring system. You create tasks for camera input devices, and the system analyses the video feed using vision-language models to fulfil those tasks (counting events, detecting conditions, triggering actions, etc.).

This document describes how to run the VideoMemory core service and interact with it via HTTP from an external agent.

For agent integrations, keep VideoMemory as the long-running visual monitor. For "when X happens, do Y", put the visual trigger in the VideoMemory task and store the follow-up action in the webhook-capable agent runtime.

For true push-style Claude Code wakeups, use docs/claude-code-channel.md and claude-videomemory-channel/. Claude Code channels can receive external events into a running Claude session.

Quick Start

If the server is not already running, start it:

uv run flask_app/app.py

The server is available at http://localhost:5050 (or at the host's IP on port 5050 if deployed on a remote machine like a Raspberry Pi). API keys are configured via the Settings tab in the web UI, or via PUT /api/settings/{key} (see Configuration section below).

For local integration testing, choose one stack:

  • Core only: docker compose -f docker-compose.core.yml up --build
  • Core + OpenClaw: docker compose -f docker-compose.real-openclaw.yml up --build

OpenAPI Spec

A machine-readable OpenAPI 3.1 spec is served at:

GET http://localhost:5050/openapi.json

Use this to auto-discover all available endpoints and their schemas.

Health Check

GET /api/health

Returns {"status": "ok", ...} when the server is running.

Health is not the same as monitor readiness. A monitor also needs a reachable model runtime or configured model API key, plus camera permission for local USB or built-in cameras. Coding agents should run:

node scripts/agent/ensure-server.mjs --json

On macOS, the terminal or host app that launches Python may need Camera permission in System Settings before OpenCV can read built-in/USB cameras.

Read the full file on GitHub · 312 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. 5d ago First seen · 312 lines · 2,260 tokens per session scan A e79a7f5641ba

Subscribe to this mod's changes

videomemory AGENTS.md is an instructions file published in the GitHub repository Clamepending/videomemory (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,260 tokens to every session, about $0.0113 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens