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 agentmods add commands/hufirst/onsense/onsensegit clone --depth 1 https://github.com/hufirst/onsenseWrote 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/commands/hufirst/onsense/onsense)<a href="https://agentmods.dev/commands/hufirst/onsense/onsense"><img src="https://agentmods.dev/badge/commands/hufirst/onsense/onsense.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00426 |
| Opus 5 | $0.00015 | $0.00213 |
| Sonnet 5 | $0.00006 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
onsense 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 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.
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.
What it actually says
Branch on $ARGUMENTS (empty → see). Keep responses short.
- see / look / camera / (empty) →
get_live_frame→ describe what you see concisely (transcribe any text verbatim). If dark/blurry, add a one-liner: "hold the phone steady on the target". - sensors / status →
read_sensors→ summarize as battery, illuminance, and posture (lying/upright/tilted). - photos →
recent_photos→ a simple table of number (1, 2, 3 — assigned by you, so the user has something to point at), filename, date. Keep the number→id mapping for the follow-up. - photo N → the user's N is that display number, NOT the MediaStore id. Map it back to the real id (run
recent_photosfirst if you don't have the list), thenget_photo(id).get_photosaves the file and returns its path. Look at the image, then alwaysrename_photo(path, "<what it shows>")— e.g. "whiteboard sprint plan". You have already seen it, so this costs nothing; skipping it leaves the user with an unreadablephoto_1000024531.jpg. Report the final saved path in one short line. - all →
read_sensors+get_live_frametogether.
On failure ("phone unreachable"): a one-line note to check that the phone app is sharing and on the same Wi-Fi.
$ARGUMENTS
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.
- 5d ago First seen · 23 lines · 30 tokens per session scan A 958c9fa1042e
onsense is a command published in the GitHub repository hufirst/onsense (2 stars, last pushed 25d ago), licensed MIT. It adds 30 tokens to every session and 426 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.
Other commands, from other repositories
eval-axon
You are evaluating axon — a zero-cloud MCP server that gives AI coding agents real-time hardware awareness. You ARE the agent. axon is YOUR tool.
stress-test
Run a quick CPU stress test and verify axon detection.
comparative-test
Run blind vs axon-informed agent comparison.
snapshot
Take a quick hardware snapshot and interpret it.
commit-all
Group all changes semantically and commit each group separately.
tapeout
Produce a complete, fab-ready export bundle for a routed board — or refuse loudly. Superset of /kct:manufacturing-readiness: runs the three sign-off pre-gates, then adds a BOM part-number-resolution gate, a per-rule warning-review gate (assembly-affecting warnings block unless explicitly acknowledged), schematic +…