reflectworld-mem

reflectworld-mem is a skill for Claude Code, Codex from addxai/ReflectWorld. It costs 0 tokens per session (1,332 once invoked), scanned A, original, Apache-2.0.

A search and note system for video captured by ReflectWorld cameras. It can search recorded events, recurring behavior, and saved agent rules using ordinary language.

In plain words
What is it for?
Use it to search camera history, investigate what happened, identify recurring visits, add observation notes, or manage persistent viewing rules.
Why use it?
It avoids manually reviewing recordings when you need to find a person, event, or pattern.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to search camera history, investigate what happened, identify recurring visits, add observation notes, or manage persistent viewing rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/addxai/reflectworld/reflectworld-mem
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 addxai/ReflectWorld --skill reflectworld-mem
Clone the repo
git clone --depth 1 https://github.com/addxai/ReflectWorld

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 reflectworld-mem

README.md
[![agentmods](https://agentmods.dev/badge/skills/addxai/reflectworld/reflectworld-mem.svg)](https://agentmods.dev/skills/addxai/reflectworld/reflectworld-mem)
Your own site
<a href="https://agentmods.dev/skills/addxai/reflectworld/reflectworld-mem"><img src="https://agentmods.dev/badge/skills/addxai/reflectworld/reflectworld-mem.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,332 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Memory Poisoning · line 12
    Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.
    Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
How audits are shown
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 $0.00000 $0.01332
Opus 5 $0.00000 $0.00666
Sonnet 5 $0.00000 $0.00266
Haiku 4.5 $0.00000 $0.00133

Measured 8d ago against content hash ec672e21e155, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reflectworld-mem 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 8d 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.

packages/mem/skills/reflectworld-mem/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

reflectworld_memory

Search and manage ReflectWorld video memories from ReflectWorld cameras.

When to use

Use reflectworld_memory when the user asks about:

  • What happened in front of a camera ("who came to the door today?")
  • Identifying recurring patterns ("does this person visit often?")
  • Retrieving event history for a camera or entity
  • Adding structured notes about observations
  • Setting persistent rules/preferences that the VLM should follow

Actions

search

Semantic search across video memories. Searches episodic (raw events), semantic (behavioral patterns), and procedural (agent rules) collections.

{
  "action": "search",
  "query": "person carrying package at front door",
  "camera_id": "cam-front-door",
  "mode": "event",
  "memory_type": "episodic",
  "limit": 10,
  "threshold": 0.7
}

Parameters:

Parameter Type Required Description
query string yes Natural language search query
camera_id string no Filter to specific camera
mode "snapshot" | "event" | "stream" no Filter by capture mode
memory_type "episodic" | "semantic" | "procedural" | "all" no Collection to search (default: "all")
limit integer no Max results (default: 20, max: 200)
threshold number 0-1 no Minimum similarity score

add_note

Store a manual observation or user-defined rule. Use memory_type="procedural" for notification rules/preferences — these are automatically injected into the VLM prompt on every analysis cycle.

{
  "action": "add_note",
  "note": "Alert user when animals or pets appear in the camera feed.",
  "camera_id": "global",
  "memory_type": "procedural"
}

Parameters:

Parameter Type Required Description
note string yes Note content to store
camera_id string no Associated camera. Use "global" for rules applying to all cameras
memory_type "episodic" | "procedural" no Collection to store in. Use "procedural" for user rules/preferences (default: episodic)
user_id string no Associated user
agent_id string no Agent making the note
mode "snapshot" | "event" | "stream" no Context mode

Read the full file on GitHub · 143 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. 8d ago First seen · 143 lines · 0 tokens per session scan A ec672e21e155

Subscribe to this mod's changes

reflectworld-mem is a skill published in the GitHub repository addxai/ReflectWorld (98 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,332 tokens. 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.