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 sideshowroberto/vfx-agent-toolkit --skill vfx-researchgit clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitWrote 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/sideshowroberto/vfx-agent-toolkit/vfx-research)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/vfx-research"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/vfx-research/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/sideshowroberto/vfx-agent-toolkit/vfx-research"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/vfx-research.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 | $0.00051 | $0.00954 |
| Opus 5.5 | $0.00020 | $0.00382 |
| Sonnet 5.5 | $0.00010 | $0.00191 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
vfx-research 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 today.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VFX research
Harness-neutral companion to the brave-search skill, which documents the
Claude Code MCP tools in detail. Use the connected tools' current schemas; tool
names quoted in other skills are not an API contract for this harness.
Pick the source for the question
- Brave Search: discover application documentation, release notes, exact error matches, and integration sources. Include the application, installed version, task, and relevant renderer or operating system in the query.
- Context7: retrieve library documentation and code examples. Resolve the
library with
resolve-library-idusinglibraryNameand a specificquery, then callquery-docswith the returnedlibraryIdand the actual question. Skip resolution when the user supplies the exact library ID or it was already resolved for the current task. - For DCC APIs missing from Context7, read the vendor's versioned documentation directly. Relevant starting domains include docs.blender.org, learn.foundry.com, sidefx.com/docs, dev.epicgames.com, and docs.comfy.org.
Match documentation to the installed version. If the requested version is not indexed, disclose that mismatch and check the vendor's docs or local API before using an example. Do not silently substitute the newest release.
Search and verify
Inspect the available Brave tool schema before choosing filters. Start with a focused web query and a small result set. Use exact quoted error text where helpful. Apply freshness filters to release/news questions, not automatically to stable APIs or older software versions. Use dedicated video or image tools when exposed rather than assuming the web tool accepts every result type.
Search snippets identify sources; open relevant pages before treating their contents as verified. Ground technical conclusions in vendor docs, upstream source, or maintainer examples. Treat community reports as leads to reproduce. If Context7 returns an excerpt without sufficient provenance or version detail, follow its source link before relying on it for a version-sensitive claim.
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.
- today First seen · 77 lines · 51 tokens per session scan A 3195e2f43a91
vfx-research is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 51 tokens to every session and 954 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-02.
Other skills, from other repositories
scenario-zbrush-expert
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted…
usd-tools
Infrastructure skill — low-level OpenUSD scene inspection and validation: read layer stacks, traverse prims, validate USD schemas. Use when working directly with raw USD files (usda, usdc, usdz) or verifying USD compliance. Not for Maya-specific USD export — use maya-pipelineexportusd for that. Not for full DCC…
spatial-interchange
Plan deterministic coordinate-axis and unit conversions between DCCs, engines, and interchange formats from explicit right/up/forward axes and meters-per-unit values.
game-level-layout
Game level layout review helpers for editor contexts.
unity-tooling
Build editor tooling: EditorWindows, PropertyDrawers, AssetPostprocessors and ScriptedImporters. Use when writing custom Unity editor windows, inspectors, or gizmos.
ue5-blueprint-workflow
UE5.6/UE5.7 Blueprint graph workflow for feature implementation, input events, node wiring, and graph validation. Use when requests involve adding Blueprint logic, keyboard input behavior, function chains, event graph edits, or pin-level connection guidance.