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-docs-localgit 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-docs-local)<a href="https://agentmods.dev/skills/chordee/houdini-tools/houdini-docs-local"><img src="https://agentmods.dev/badge/skills/chordee/houdini-tools/houdini-docs-local/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-docs-local"><img src="https://agentmods.dev/badge/skills/chordee/houdini-tools/houdini-docs-local.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 | $0.00074 | $0.01027 |
| Opus 5 | $0.00037 | $0.00513 |
| Sonnet 5 | $0.00015 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
houdini-docs-local 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Houdini documentation, locally
Every Houdini install carries the whole documentation set as wiki-markup source. Reaching for
sidefx.com is the default habit and it is wrong twice over here: it fails behind a studio
firewall, and it answers for the current release rather than the version in front of you.
The mapping
A docs URL maps to a local archive by its first path segment:
https://www.sidefx.com/docs/houdini/<first>/<rest>.html
↓
$HFS/houdini/help/<first>.zip → <rest>.txt
# H is the Houdini install root — the directory holding bin/ and houdini/,
# not the path to hython. Use the houdini-locator skill to find it.
# The :? makes an unset HFS fail here rather than further down: with H empty,
# the single-file read raises a traceback but the search below just returns
# nothing, which reads exactly like "the docs do not mention this".
H="${HFS:?set HFS to the Houdini install root, e.g. /opt/hfs22.0.368}"
# hom/hou/Node.html → hom.zip : hou/Node.txt
python -c "import zipfile;print(zipfile.ZipFile(r'$H/houdini/help/hom.zip').read('hou/Node.txt').decode('utf-8','replace'))"
Verified against help, nodes, hom, vex, expressions, commands and ref. The .txt
is the source the HTML is generated from, so it carries the same content — including signatures,
parameter tables and examples.
Which archive
Counts below are from Houdini 22.0.368 — 47 archives, 10450 documents. Another build will differ; run the search commands rather than trusting these numbers:
| Archive | Documents | Contents |
|---|---|---|
nodes |
5033 | Every node's reference page, under sop/, lop/, dop/, vop/, … |
vex |
1178 | VEX language and functions |
hom |
966 | Python scripting — hou/Node.txt, hou/Geometry.txt, … |
expressions |
478 | Expression functions |
commands |
442 | HScript commands |
tops |
223 | PDG/TOPs |
ref |
202 | Reference, including plugins.txt and the env-var list |
solaris |
73 | Solaris and Karma |
help |
6 | How the help system itself works, including its markup |
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 · 93 lines · 74 tokens per session scan A 60085a54c4ae
houdini-docs-local is a skill published in the GitHub repository chordee/houdini-tools (5 stars, last pushed 11d ago), licensed MIT. It adds 74 tokens to every session and 1,027 once invoked, about $0.0004 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
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.
lov-thesis-polish
An academic editing tool for improving an MBA thesis or dissertation in Markdown, a plain-text format for structured documents. It addresses language, argument structure, logic, research contributions, and formatting.
learning-assistant
An interactive study assistant that turns a learning goal into a structured plan and guides the learner through it. It uses a local knowledge graph, a connected record of topics and learning state, as its long-term memory.
reading-notes
Process a book or article into structured progressive summary notes saved to the resources folder. Use when the user has finished reading something and wants to capture structured notes — 'I just finished reading X', 'take notes on this book'. Do NOT use for: fetching and summarizing a URL now (use summarize)…
project-learner
An interactive project-teaching assistant that explains a codebase, files, or underlying technologies and records the lessons in Markdown logs. It can continue from earlier learning records.