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 chordee/houdini-tools --skill houdini-litegit clone --depth 1 https://github.com/chordee/houdini-toolsWrote 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/chordee/houdini-tools/houdini-lite)<a href="https://agentmods.dev/skills/chordee/houdini-tools/houdini-lite"><img src="https://agentmods.dev/badge/skills/chordee/houdini-tools/houdini-lite/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/chordee/houdini-tools/houdini-lite"><img src="https://agentmods.dev/badge/skills/chordee/houdini-tools/houdini-lite.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 | $0.00094 | $0.02174 |
| Opus 5 | $0.00047 | $0.01087 |
| Sonnet 5 | $0.00019 | $0.00435 |
| Haiku 4.5 | $0.00009 | $0.00217 |
Grade A, and why
houdini-lite 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Houdini Lite Expert
MCP tools for inspecting .bgeo.sc geometry caches and USD scene files, plus a few write tools for stitching USD Value Clips and rewriting USD anchors. All tools avoid loading full geometry into memory. Parameter schemas come from each tool's MCP registration — this skill covers tool selection, behavioral rules, and workflows.
Tool Picker
bgeo (reads only the first compressed Blosc chunk — fast on multi-GB files)
- counts only →
bgeo_read_header - attributes, geometry type, detail values, software info →
bgeo_inspect - discover sequences / frame range / total size in a directory →
bgeo_list_sequence
VDB (header-only parse via Python stdlib — no pyopenvdb / no Houdini)
- grid names, types, friendly labels, file-level metadata →
vdb_inspect - discover sequences / frame range / total size in a directory →
vdb_list_sequence - stitch per-frame .vdb sequence into a USD Volume (time-sampled filePath) →
vdb_stitch_volume_usd
USD read (never loads geometry; payloads deferred by default)
- single-layer hierarchy (no composition, fastest) →
usd_read_hierarchy - fully composed hierarchy (resolves refs + sublayers) →
usd_read_hierarchy_composed - direct sublayers/refs/payloads only →
usd_read_composition_arcs - camera lens & projection attributes →
usd_read_cameras - attribute names/types on a prim →
usd_read_prim_attributes - value of one named attribute →
usd_read_attribute_value - all standard layer metadata (time codes, fps, units, axis, customLayerData, expressionVariables) →
usd_read_layer_metadata - every file the scene points at — textures, light HDRIs, VDB caches — and whether each is on disk →
usd_read_asset_paths - every layer the scene needs, followed transitively (packaging, transfer, broken-path audit) →
usd_read_layer_dependencies - RenderSettings / RenderProduct prims and what a render driven by each would actually use →
usd_read_render_settings
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 · 95 lines · 94 tokens per session scan A ad294a46ff2c
houdini-lite is a skill published in the GitHub repository chordee/houdini-tools (5 stars, last pushed 11d ago), licensed MIT. It adds 94 tokens to every session and 2,174 once invoked, about $0.0005 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 skills, from other repositories
slides
Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding…
lov-media-publisher
A video publishing workflow for the WeChat Channels and Bilibili creator dashboards. It checks media and post fields, handles platform-specific limits and layouts, and reads the submitted details back from the platform.
lov-article-creator
A skill that turns source material or a draft into a complete, branded WeChat public-account article package.
lov-illustrate
A document-illustration workflow that examines a Markdown document, chooses suitable real images, charts, or generated visuals, and inserts them into an enhanced version. Markdown is a plain-text format that uses simple symbols for headings, links, and other document structure.
lov-any2deck
Generate professional slide deck images from content (Markdown, text, URLs). Creates outlines with style instructions, then generates individual slide images. Supports 16 visual styles, CJK/Latin mixed text, branding overlays, and PPTX/PDF export. Use when the user asks to "create slides", "make a presentation"…
lov-gen-logo
A logo and application-icon design workflow that creates distinct, versioned drafts and keeps brand marks separate from app icons. It also prepares selected assets for their intended uses, such as websites or device screens.