Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/archetypeai/agent-skillsnpx agentmods add skills/archetypeai/agent-skills/atai-operational-state-monitoring-agentWrote 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-operational-state-monitoring-agent)<a href="https://agentmods.dev/skills/archetypeai/agent-skills/atai-operational-state-monitoring-agent"><img src="https://agentmods.dev/badge/skills/archetypeai/agent-skills/atai-operational-state-monitoring-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-operational-state-monitoring-agent"><img src="https://agentmods.dev/badge/skills/archetypeai/agent-skills/atai-operational-state-monitoring-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 | $0.00308 | $0.09155 |
| Opus 5.5 | $0.00123 | $0.03662 |
| Sonnet 5.5 | $0.00062 | $0.01831 |
| Haiku 4.5 | $0.00031 | $0.00915 |
Grade A, and why
atai-operational-state-monitoring-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 7d 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 — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSM Agent — Managed State Classification via the Agents API
The OSM agent labels every window of a multichannel sensor recording with an operational state (drilling activities, machine modes, process phases) server-side. The platform runs the whole graph:
source → interpolate → window → windowInterpolate → samplingRate → limitValues → encoder → classifier → sink
The encoder is Newton Omega; the classifier is a kNN over Omega embeddings. You never host either.
Choose a path
| Path 1 — run a maintained bundle | Path 2 — build an agent on your data | |
|---|---|---|
| you have | a prepared CSV (the Volve sample, or data like it) | labelled recordings of your machine |
| you get | per-window predictions from Archetype AI's six-state Volve classifier | your own blueprint and bundle, fitted and chosen on your data, with a test score and a delivery score |
| APIs | files, bundles, instances | files, Optimizations, promote, Evals, bundles, instances |
| scripts | references/run_osm_agent.py, on the official archetypeai client |
references/osm_lifecycle/, a small stdlib HTTP helper (the client doesn't cover Optimizations / Evals / promote yet) |
| time | ~1–2 min on a clear queue | minutes to hours, with the dataset's size and the platform's load |
| status | verified on production | verified on production, staging (2026-10-01) and dev (2026-09-30), identical results |
Path 2's last step is Path 1, run on your own bundle instead of the maintained one, so the output schema, polling, pitfalls and cleanup below apply to both.
Tailored work (a classifier Archetype AI fits and packages for your data, or help with a hard dataset): [email protected].
When to Apply
- Classify operational states over a CSV with no client-side ML — Path 1 for the maintained Volve bundle, Path 2 for your own states
- Build, test and deploy an OSM agent for your machine from labelled recordings — Path 2
- Demo or evaluate the managed OSM path as a deployed, repeatable batch job
- Score managed predictions against held-out ground truth
What ships with it
18 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 504 B
- references/osm_lifecycle/atai_http.py 11 KB runs code
- references/osm_lifecycle/background.py 2.6 KB runs code
- references/osm_lifecycle/common.py 1.6 KB runs code
- references/osm_lifecycle/deliver.py 11 KB runs code
- references/osm_lifecycle/optimize.py 8.2 KB runs code
- references/osm_lifecycle/promote_and_test.py 7.3 KB runs code
- references/osm_lifecycle/requirements.txt 150 B
- references/osm_lifecycle/score.py 5.0 KB runs code
- references/osm-output.csv 221 KB
- references/platform-notes.md 9.5 KB
- references/requirements.txt 414 B
- references/run_osm_agent.py 17 KB runs code
- references/sample_data/README.md 1.6 KB
- references/sample_data/volve_states_opt_slice_04_labels.csv 445 KB
- references/sample_data/volve_states_opt_slice_04.csv 404 KB
- tests/test_lifecycle.py 15 KB runs code
- tests/test_references.py 17 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.
- 7d ago Changed · +1 lines cf9397dd4772
- 13d ago Changed · +6 lines b551d758c1b3
- 18d ago Changed · +2 lines deefc095a5f5
- 19d ago Changed · +15 lines 555c548a2c22
- 24d ago Changed bc3e55b7d7b5
- 25d ago Changed · +249 lines · +91 tokens per session 14a15af8d904
- 1mo ago First seen · 259 lines · 217 tokens per session scan A 86c6465c67b4
atai-operational-state-monitoring-agent is a skill published in the GitHub repository archetypeai/agent-skills (7 stars, last pushed today), licensed Apache-2.0. It adds 308 tokens to every session and 9,155 once invoked, about $0.0012 per session on Opus 5.5. 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
environment
Interpret environmental sensor readings and sustained changes for room comfort and air quality. Use for [environment:initial] greeting context, [environment:update] events, questions about room temperature, humidity, measured CO2 or air quality, checking changes after ventilation or air cleaning, and room-feeling…
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?". Also holds your OWN sleep history — "how many times have you slept?", "when do you usually go to sleep?".
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).