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 skills/usalu/semio/commitnpx skills add usalu/semio --skill commitgit clone --depth 1 https://github.com/usalu/semioWhat 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 | $0.00064 | $0.01880 |
| Opus 5 | $0.00032 | $0.00940 |
| Sonnet 5 | $0.00013 | $0.00376 |
| Haiku 4.5 | $0.00006 | $0.00188 |
Grade A, and why
commit 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 yesterday.
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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- yesterday First seen · 142 lines · 64 tokens per session scan A 6018a602f474
commit is a skill published in the GitHub repository usalu/semio (21 stars, last pushed 4d ago), licensed AGPL-3.0. It adds 64 tokens to every session and 1,880 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
parametric-modeling
Parametric design methodology, data structures, constraint systems, Grasshopper and Dynamo patterns, parameter space exploration, and associative geometry for AEC computational design.
parametric-modeling
Parametric design methodology, data structures, constraint systems, Grasshopper and Dynamo patterns, parameter space exploration, and associative geometry for AEC computational design.
sceneview
Build 3D and AR apps with the SceneView SDK in Jetpack Compose, SwiftUI (iOS/macOS/visionOS via SceneViewSwift), Web (Filament.js), Flutter and React Native. Use whenever the user asks for "3D in Compose", "AR with ARCore in Compose", a model viewer, or any cross-platform 3D/AR app where the dependency is…
aholo-site
Work on Aholo Viewer Astro website and Playground surfaces under website/. Use for routes, layouts, components, page chrome, i18n UI copy, scoped CSS, client render runtime, Playground runner, preview canvas, inspector, presets, route-local Monaco, and URL parameters. Use aholo-examples for example content pairs.
aholo-renderer
Work on the @manycore/aholo-viewer package. Use only when the user explicitly asks for renderer source, package build, public exports, JSDoc/API docs, generated declaration flow, renderer dist, packing, or release validation.
pc-ci-dependency-bot
Sweep the open dependency-bot pull requests once - rebase the stale ones, re-trigger infrastructure failures, and merge the green patch and minor updates. Use when the user wants to baby sit, unblock, or push through pending dependabot pull requests, and on each firing of a /loop that watches them.