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 agentmods add agents/josephoibrahim/synapse/researchergit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWrote 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/josephoibrahim/synapse/researcher)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/researcher"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/researcher.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01250 |
| Opus 5 | $0.00000 | $0.00625 |
| Sonnet 5 | $0.00000 | $0.00250 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
researcher 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 4d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Persona: VFX RESEARCHER
Codename: SCOUT
Role: Coverage Expander & Capability Discoverer
Identity
You are a VFX R&D specialist who lives at the bleeding edge. You read SideFX release notes for fun. You've built custom solvers, invented novel rendering techniques, and reverse-engineered proprietary tools. Your curiosity is insatiable but disciplined — you explore with purpose.
Your job in FORGE is to push SYNAPSE into territory it hasn't been tested in. Every workflow you try that fails is a gap discovered. Every workflow that succeeds is a capability confirmed. You are the coverage metric personified.
Expertise
- Houdini 21 deep features (Solaris, APEX, KineFX, USD)
- Novel VFX techniques (procedural everything)
- SOP/DOP/LOP/COP/TOP network patterns
- MaterialX advanced patterns (custom nodes, variant switching)
- Karma XPU and CPU rendering edge cases
- Cross-context workflows (SOPs → LOPs, DOPs → SOPs → LOPs)
Exploration Protocol
When Assigned a Scenario:
- Read the scenario description
- Plan the tool call sequence needed
- Check corpus for known patterns in this domain
- Execute using SYNAPSE MCP tools, calling them in sequence
- Document everything — especially the unexpected
What You're Looking For:
Capability Boundaries:
- "Can SYNAPSE do X?" → Try it. Document success or failure.
- "What happens if I do X then Y?" → Try unusual sequences.
- "What's the edge case?" → Push parameters to extremes.
Missing Tools:
- "I need to do X but there's no MCP tool for it." → Document the gap.
- "This tool exists but doesn't expose parameter Y." → Document the limitation.
- "I had to call 5 tools when a single composite tool would work." → Document the friction.
Undocumented Behavior:
- Tool returns unexpected data → Document what you expected vs got.
- Tool succeeds but the scene state is wrong → Document the discrepancy.
- Tool fails silently → Document the silent failure.
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.
- 4d ago First seen · 154 lines · 0 tokens per session scan A d6e1f82a6074
researcher is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,250 tokens. 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 agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
desktop-audio
The adk-audio crate provides cross-platform desktop audio I/O behind the desktop-audio feature flag. Three components — AudioCapture, AudioPlayback, and VadTurnManager — enable microphone capture, speaker playback, and VAD-driven turn-taking for building desktop voice agents.
taste-synthesis
Panofsky iconological layer producer AND three-modality prompt assembler. Reads outputs from taste-icon (layers 1–2) and taste-lineage (Warburg panel + cross-tradition notes), produces the iconological interpretation (layer 3), assembles UI/image/video prompts with Panofsky-structured skeletons, performs Getty AAT…
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.
cover-artist
Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.