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.
npx skills add addxai/ReflectWorld --skill reflectworld-perceptgit clone --depth 1 https://github.com/addxai/ReflectWorldWrote 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.
[](https://agentmods.dev/skills/addxai/reflectworld/reflectworld-percept)<a href="https://agentmods.dev/skills/addxai/reflectworld/reflectworld-percept"><img src="https://agentmods.dev/badge/skills/addxai/reflectworld/reflectworld-percept/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.
<a href="https://agentmods.dev/skills/addxai/reflectworld/reflectworld-percept"><img src="https://agentmods.dev/badge/skills/addxai/reflectworld/reflectworld-percept.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01799 |
| Opus 5 | $0.00000 | $0.00899 |
| Sonnet 5 | $0.00000 | $0.00360 |
| Haiku 4.5 | $0.00000 | $0.00180 |
Grade A, and why
reflectworld-percept 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ReflectWorld Perception
What you are
Perception automatically analyzes video segments from Eye using cloud VLM (Gemini). Working Memory tracks cross-segment event context. Results flow to ReflectWorld (storage) and Act (rules) via PostProcessor — all automatic.
Data flow
Eye → onSegment → Perception.analyze (automatic)
|
PerceptionResult
| |
ReflectWorld Act rules
(PostProcessor handles both)
When to use this tool
| Scenario | Action |
|---|---|
| User describes their scene, focus targets, or security rules | configure with config fields |
| User wants to change VLM model | configure with vlm_model |
| User explicitly asks to analyze a specific segment | analyze with segment fields (normally automatic) |
| User asks for pipeline debug info | get_status with camera_id |
Actions
configure — set analysis context
Call this before starting a watch to tell the VLM what to look for. Changes take effect immediately on the next analyzed segment.
Configurable fields:
| Field | Type | Description |
|---|---|---|
scene_description |
string | Describe the camera scene for better VLM grounding |
focus_targets |
string | Comma-separated items to pay extra attention to |
security_rules |
string | Custom security criteria for risk assessment |
vlm_model |
string | Override VLM model for all perception levels. Empty string resets to default |
Scene-specific configure examples
Kitchen / cooking:
{
"action": "configure",
"config": {
"scene_description": "Overhead kitchen camera viewing stovetop and counter",
"focus_targets": "stove flames, oil splatter, smoke, food color changes, knife handling, pot handles"
}
}
Front door security:
{
"action": "configure",
"config": {
"scene_description": "Front door camera overlooking porch and driveway",
"focus_targets": "people, packages, vehicles, animals, door state (open/closed)",
"security_rules": "Flag unknown persons after 10pm. Alert on package removal."
}
}
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.
- 9d ago First seen · 221 lines · 0 tokens per session scan A 7b7a8cdf1ca3
reflectworld-percept 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 1,799 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.
Other skills, from other repositories
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
video-frames
Extract a single frame from a local video at the first frame, a timestamp, or a zero-based frame index using FFmpeg.
ideation
Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.
ppt-design
A workflow for designing presentation slides as editable HTML pages, with an optional conversion to editable PowerPoint files. It defines slide layouts, an outline, visual rules, and how images are embedded.
create-openbitfun-cinematic-wallpaper-skin
Apply the cinematic animated-wallpaper style recipe to a OpenBitFun Appearance skin. Use after loading the parent create-openbitfun-skin Skill when the user provides animated character artwork and wants a host-managed video background, source-derived glass materials, image-led cards, illustrated dialogs, reproducible…