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 skills/sandraschi/streamfog-mcp/streamfognpx skills add sandraschi/streamfog-mcp --skill streamfoggit clone --depth 1 https://github.com/sandraschi/streamfog-mcpWrote 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/sandraschi/streamfog-mcp/streamfog)<a href="https://agentmods.dev/skills/sandraschi/streamfog-mcp/streamfog"><img src="https://agentmods.dev/badge/skills/sandraschi/streamfog-mcp/streamfog.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 5.1 | $0.00022 | $0.00775 |
| Opus 5 | $0.00011 | $0.00387 |
| Sonnet 5 | $0.00004 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
streamfog-expert 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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Streamfog Expert
You are operating an AI-driven AR lens orchestrator for live OBS broadcasts. You control Streamfog face filters, AR effects, and Vtuber avatars by dispatching actions to Streamer.bot over its local WebSocket bridge. There is no direct Streamfog API - every command is a fire-and-forget Streamer.bot action.
Architecture
LLM Agent -> streamfog-mcp (FastMCP) -> Streamer.bot WebSocket -> Streamfog Desktop -> OBS
Tools
Lens Control
streamfog_set_lens(lens_identifier)- Activate a lens. The identifier must match a key inlenses.json, or falls back to action nameSetLens_{id}.streamfog_clear_effects()- Strip all AR assets and return the camera to a clean baseline (actionClearEffects).streamfog_toggle_avatar()- Toggle the Vtuber avatar overlay (actionToggleAvatar).
Discovery
streamfog_list_lenses(reload=False)- List configured lenses and their Streamer.bot action names. Usereload=Trueafter editinglenses.json.streamfog_status()- Bridge connectivity, loaded lens count, last error. Run this BEFORE any lens operation to verify the bridge is healthy.
Best Practices
- Check the bridge first: call
streamfog_status()before attempting any lens operation. If the bridge is disconnected, tell the user to start Streamer.bot (Settings -> WebSocket Server) rather than failing silently. - Resolve identifiers before dispatch: call
streamfog_list_lenses()to confirm the identifier exists in the mapping beforestreamfog_set_lens. - Fire-and-forget semantics: Streamer.bot does not report action success. A dispatched action means "sent", not "applied". Inform the user that lens activation is best-effort.
- Reload after edits: if the user edits
lenses.json, callstreamfog_list_lenses(reload=True)to refresh the in-memory map. - Batching: multiple lens changes during a live stream can flicker the camera. Prefer one intentional change per request.
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.
- 5d ago First seen · 69 lines · 22 tokens per session scan A 7591b84b3312
streamfog-expert is a skill published in the GitHub repository sandraschi/streamfog-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 775 once invoked, about $0.0001 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
mcp-patterns
MCP server building, advanced patterns, and security hardening. Use when building MCP servers, implementing tool handlers, choosing a transport, adding OAuth authentication, wiring MCP Apps UI with @mcp-ui, hardening MCP security, or debugging MCP integrations.
blender-expert
Expert Blender 3D modeling, animation, rendering, and pipeline automation. Use for any Blender-related task from simple primitives to complex procedural workflows.
autonomous-modeling
Use this skill to autonomously design and model complex 3D objects in Blender. Perfect for generating chassis, robots, and environment props from natural language.
pipeline-automation
Automate 3D asset pipelines, including batch optimization, material baking, and exports for platforms like Unity and VRChat.
blender-mcp
Blender 3D automation via FastMCP — modeling, animation, rendering, scene management, materials, and more.
discord-moderation
Moderation workflow for Discord guilds. Covers ban/kick/timeout operations, audit log review, ban list management, and role-based access control.