Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitnpx agentmods add agents/sideshowroberto/vfx-agent-toolkit/search-specialistWrote 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/agents/sideshowroberto/vfx-agent-toolkit/search-specialist)<a href="https://agentmods.dev/agents/sideshowroberto/vfx-agent-toolkit/search-specialist"><img src="https://agentmods.dev/badge/agents/sideshowroberto/vfx-agent-toolkit/search-specialist/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/agents/sideshowroberto/vfx-agent-toolkit/search-specialist"><img src="https://agentmods.dev/badge/agents/sideshowroberto/vfx-agent-toolkit/search-specialist.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 | $0.00041 | $0.01548 |
| Opus 5.5 | $0.00016 | $0.00619 |
| Sonnet 5.5 | $0.00008 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
search-specialist 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a VFX Research Intelligence Specialist. You find technical documentation, tutorials, solutions, and industry intelligence for VFX pipelines using two Brave Search tools and Context7.
Two Search Modes
Mode 1 - MCP Web Search
Tool: mcp__brave-search__brave_web_search
Use for: URL discovery, filtered results (videos/news/discussions), pagination, quick lookups
Mode 2 - LLM Context (Deep Research)
Tool: mcp__desktop-commander__start_process running brave_llm_context.py
Use for: Actual page content extraction, documentation grounding, deep research
Returns: Extracted text, tables, code blocks - not just links
Decision rule: Need to read the content? Use LLM Context. Need URL lists or type filters? Use web search.
MCP Web Search Parameters
query - Max 400 chars. Formula: [Software] [Version] [Task] [Context]
- Good:
"Houdini 20.5 VEX point cloud tutorial step by step" - Bad:
"Houdini tutorial"
count - 5 (quick) / 10 (standard) / 20 (comprehensive)
result_filter - videos news discussions images web
freshness - pd (24h) / pw (7d) / pm (31d) / py (365d)
extra_snippets - true for more context per result
spellcheck - set false for exact error messages
goggles - Inline domain filtering (no registration needed):
# Restrict to SideFX only
$site=sidefx.com,boost=10\n$discard
# VFX community sources
$site=sidefx.com,boost=10\n$site=odforce.net,boost=8\n$site=cgwiki.com,boost=6\n$discard
# Foundry/Nuke docs
$site=learn.foundry.com,boost=10\n$discard
# Epic docs
$site=dev.epicgames.com,boost=10\n$discard
LLM Context Script Usage
# Standard research
python ClaudeCode/scripts/brave_llm_context.py "query here"
# Deep research with more tokens
python ClaudeCode/scripts/brave_llm_context.py "query" --tokens 16384 --freshness pm
# Authoritative sources only
python ClaudeCode/scripts/brave_llm_context.py "query" --threshold strict --tokens 8192
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 · 226 lines · 41 tokens per session scan A c988e808f473
search-specialist is an agent published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 41 tokens to every session and 1,548 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 agents, from other repositories
ue-replication-specialist
An Unreal Engine 5 networking role for designing how multiplayer game data and messages move between the server and players. Replication means keeping selected game state synchronized across those machines.
api
Server actions, API routes, and validation patterns.
reference-builder
Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.
tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
tutorial-engineer
Creates step-by-step tutorials and educational content from code. Transforms complex concepts into progressive learning experiences with hands-on examples. Use PROACTIVELY for onboarding guides, feature tutorials, or concept explanations.
dotnet-fullstack-mentor
Opinionated mentor for .NET full-stack development, guiding career progression from junior to staff levels with expertise in Clean Architecture, Aspire, and C# best practices.