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 brave-searchgit 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/brave-search)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/brave-search"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/brave-search/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/brave-search"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/brave-search.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 | $0.00055 | $0.02387 |
| Opus 5.5 | $0.00022 | $0.00955 |
| Sonnet 5.5 | $0.00011 | $0.00477 |
| Haiku 4.5 | $0.00006 | $0.00239 |
Grade A, and why
brave-search 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brave Search Skill - VFX Research Intelligence
Version: 2.2.2 | Updated: 2026-10-10
Three Tools, Three Jobs
| Tool | When to use | What you get |
|---|---|---|
mcp__brave-search__brave_web_search |
Quick lookups, filtered results, URL lists, pagination | URLs + snippets |
brave_llm_context.py (via Bash) |
Deep research, grounding, actual page content | Extracted text, tables, code blocks |
brave_image_search.py (via Bash) |
Finding reference photos / stills | Full-size image URL + WxH + caption per hit |
Decision rule: If you need to read the content of pages (not just find them), use LLM Context. If you need URL lists, type-filtering, or pagination, use web_search. If you need the images themselves, use image search (Tool 3) - not a page search followed by scraping.
Tool 1 - MCP Web Search
mcp__brave-search__brave_web_search(query, count, result_filter, freshness, extra_snippets)
Parameters
| Param | Values | Default | Notes |
|---|---|---|---|
query |
string | - | Required. Max 400 chars / 50 words |
count |
1-20 | 10 | 20 for comprehensive research |
result_filter |
web news videos discussions images |
web | For reference photos with full-size URLs use Tool 3 |
freshness |
pd pw pm py or date range |
- | pm = past 31 days |
extra_snippets |
boolean | false | Up to 5 extra excerpts per result |
spellcheck |
boolean | true | Set false for exact error messages |
offset |
0-9 | 0 | Pagination |
VFX Query Formula
[Software] [Version] [Task] [Context]
"Houdini 20.5 VEX wrangle point cloud tutorial"
"Unreal Engine 5.5 PCG graph landscape scatter"
"Blender 4.5 geometry nodes array instances procedural"
Goggles - Domain Filtering
Pin results to authoritative VFX sources. Pass as goggles parameter string:
# SideFX only
$site=sidefx.com,boost=10\n$discard
# Foundry docs only
$site=learn.foundry.com,boost=10\n$discard
# Multiple trusted VFX domains
$site=sidefx.com,boost=10\n$site=odforce.net,boost=8\n$site=cgwiki.com,boost=6\n$discard
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 255 lines · 55 tokens per session scan A cc63e728e722
brave-search is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 55 tokens to every session and 2,387 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
comfyui-civitai
A ComfyUI integration for searching, inspecting, and downloading models from CivitAI, a website that hosts community-created AI models and model versions.
fs-notebook-tabs
A computer-science capstone: an on-device ML keyboard that predicts next words privately — problem, method, evaluation, and defense answers. Built as a decision-grade coursework defense deck for professor, defense committee.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
scenario-model-comparison
Use when comparing Scenario models on the same brief through MCP: a bake-off with shared prompts and inputs, cost, generation time and quality measured side by side, choosing a default model, testing a new release against the incumbent, or finding which model handles a style, edit, or reference image best. Keywords…
get-more-from-ai
Level up how you actually use AI — from basic one-shot questions to the techniques that get dramatically better results — matched to what you already do. Use when asked how do I get better at using AI, how do power users use AI, I feel like I'm using AI at 10%, or teach me to use AI better. Produces an honest read of…
spot-ai-mistakes
Learn to recognize where and how AI tends to go wrong — the specific failure patterns — so you catch its mistakes on sight instead of getting burned by confident errors. Use when asked how do I know when AI is wrong, what are AI's common mistakes, how do I catch AI errors, or where does AI mess up. Produces the…