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 archetypeai/agent-skills --skill atai-rare-event-detection-agentgit clone --depth 1 https://github.com/archetypeai/agent-skillsWrote 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/archetypeai/agent-skills/atai-rare-event-detection-agent)<a href="https://agentmods.dev/skills/archetypeai/agent-skills/atai-rare-event-detection-agent"><img src="https://agentmods.dev/badge/skills/archetypeai/agent-skills/atai-rare-event-detection-agent/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/archetypeai/agent-skills/atai-rare-event-detection-agent"><img src="https://agentmods.dev/badge/skills/archetypeai/agent-skills/atai-rare-event-detection-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00216 | $0.05203 |
| Opus 5 | $0.00108 | $0.02601 |
| Sonnet 5 | $0.00043 | $0.01041 |
| Haiku 4.5 | $0.00022 | $0.00520 |
Grade A, and why
atai-rare-event-detection-agent 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 11d 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 POST -H "Authorization: Bearer $ATAI_API_KEY" \ How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RED Agent — Managed Rare Event Detection via the Agents API
The RED agent detects named, rare events from a handful of labelled examples. It is the few-shot middle path between two siblings: OSM needs a full labelled library across every regime you care about, anomaly detection needs only normal data but flags everything unusual. RED takes a small named catalog — "pump breakdown", "severe slugging" — with a few labelled examples each plus normal data, and detects those specific signatures recurring.
Algorithmically it is two modules: the Omega encoder turns windowed multivariate sensor data into embeddings, and a nearest-prototype classifier assigns each window to the closest class prototype. One prototype per class — the arithmetic mean of that class's shot embeddings — which is what makes it tolerate the severe imbalance between abundant normal data and one or two fault incidents.
The platform runs the whole graph server-side:
source → interpolate → window → windowInterpolate → samplingRate
→ limitValues → encoder (omega:1.5) → classifier → sink
You don't have to fit or host anything: the platform ships canonical "RED
Quick Start" bundles with a pump-breakdown classifier and its windowing
(window_size=64, step_size=1) already pinned. One run = one agent instance =
one input file. You upload the CSV, resolve the pre-packaged bundle by
name, run it, poll until terminal, and download one output CSV of per-window
predictions. (Detecting your own fault catalog means a classifier fitted
for your data — Archetype AI does that with you; see "Bring your own
classifier" below.)
When to Apply
- Run managed rare-event detection without fitting anything — the pre-packaged Quick Start bundle pins a classifier and its windowing; upload a prepared CSV and run
- Detect a named fault of your own recurring, given only one or two labelled incidents of it plus normal-operation data (bring your own classifier, below)
- Deploy a detector as a repeatable batch job with no client-side ML — the platform embeds and classifies every window
- Score a few-shot detector honestly, where standard accuracy is meaningless because the positive class is under 1% of windows
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/.env.example 626 B
- references/red-output.csv 372 KB
- references/requirements.txt 91 B
- references/run_red_agent.py 18 KB runs code
- references/sample_data/pump_eval_inc04_labels.csv 159 KB
- references/sample_data/pump_eval_inc04.csv 905 KB
- references/sample_data/README.md 3.9 KB
- tests/test_references.py 9.7 KB runs code
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.
- 11d ago First seen · 405 lines · 216 tokens per session scan A 3539bb530aaa
atai-rare-event-detection-agent is a skill published in the GitHub repository archetypeai/agent-skills (5 stars, last pushed 21d ago), licensed Apache-2.0. It adds 216 tokens to every session and 5,203 once invoked, about $0.0011 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.
Other skills, from other repositories
sensing-track
Query flow event logs to answer questions about past sensing events — "Have you seen anybody between 10pm and midnight?", "Is there any motion in the last hour?", "What happened while I was away?".
sensing
React to passive device events tagged [sensing:...] — presence, sound, light, fire hazard — with inline emotion markers and optional short speech. Does NOT handle motion.activity (→ wellbeing) or emotion.detected / speechemotion.detected (→ user-emotion-detection).
emotion
Express emotion through coordinated servo + LED + display eyes on EVERY conversational response. This is the PRIMARY response skill that makes the device feel alive. Do NOT use for ambiance lighting (use Scene) or custom LED colors (use LED Control).
guard
Guard mode for security monitoring. Two uses — (1) Toggle on/off when a friend says "guard mode", "watch the house", "I'm going out", or similar. (2) Handle any sensing event that carries a [guard-active] tag (e.g. [sensing:presence.enter][guard-active], [sensing:motion][guard-active]) with dramatic shock/curious…
led-control
Control the device's RGB light when the user asks for a SPECIFIC color (e.g. "yellow", "red", "yellow", "red", "turn on color X", "enable X light"), an LED effect, or turning LEDs off. Do NOT use for ambiance/activity lighting (use Scene) or emotion expression (use Emotion).
face-enroll
Manage the device's face recognition roster — enroll new faces (3 paths: user-supplied photo, agent-captured snapshot on user request, or HAL's familiar-stranger prompt) and maintain the enrolled set (status / remove / reset). All enrolled persons are friends; strangers stay unnamed until promoted via one of the…