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 instructions/sandraschi/streamfog-mcp/agents-mdgit 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/instructions/sandraschi/streamfog-mcp/agents-md)<a href="https://agentmods.dev/instructions/sandraschi/streamfog-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/streamfog-mcp/agents-md.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 | $0.00889 | $0.00889 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
streamfog-mcp AGENTS.md 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 3d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions — streamfog-mcp
Identity
Streamfog MCP is an AI-driven AR lens orchestrator for live OBS streams. It controls Streamfog face filters, AR effects, and Vtuber avatars via the local Streamer.bot WebSocket bridge. Streamfog has no public API - every command is a fire-and-forget Streamer.bot DoAction dispatch.
Commands
uv sync— install Python depsjust lint— Ruff checkjust fix— Ruff auto-fixjust fmt— Ruff formatjust test— pytest (coverage-gated)just serve/just dev— run backend on port 10994 (dual mode: REST + MCP/mcp)just e2e— Playwright fleet auditjust build-native— full Tauri native installer buildjust build-native-debug— Tauri debug build (skip PyInstaller)just cua-nsis-test— NSIS smoke test (install -> nav walk -> uninstall)just cua-webapp-test— pre-Tauri browser walkjust mcpb-pack— rebuild .mcpb bundle (fresh stage)start.ps1— launch backend + webapp + open browsercd webapp && bun run dev— frontend onlycd webapp && bun run build— production frontend build
Ports (fleet-registered)
- 10994 — Backend (FastAPI REST + FastMCP streamable HTTP
/mcp) - 10995 — Frontend (Vite + React 19)
Architecture
LLM Agent -> FastMCP (tools) -> Streamer.bot WebSocket -> Streamfog Desktop -> OBS
|
FastAPI (REST) -> React Dashboard (:10995)
MCP endpoint: http://127.0.0.1:10994/mcp (streamable HTTP) or stdio
Key files
src/streamfog_mcp/_mcp.py— FastMCP singleton + shared bridge + resourcessrc/streamfog_mcp/server.py— FastAPI gateway (REST routes + /mcp mount, composed lifespan)src/streamfog_mcp/tools/core_tools.py— 5 MCP toolssrc/streamfog_mcp/services/streamerbot.py— Streamer.bot WebSocket clientsrc/streamfog_mcp/logging_ring.py— in-memory log ring buffer (/api/logs)src/streamfog_mcp/errors.py—_error_response()with logger.exceptionsrc/streamfog_mcp/skills/streamfog/SKILL.md— skill (chat preprompt, /api/skills)scripts/mcpb-pack.ps1— fresh-stage MCPB pack (src// not flattened)native/— Tauri 2.0 desktop wrapper (PyInstaller sidecar, embedded resource)
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.
- 3d ago First seen · 66 lines · 889 tokens per session scan A 55f7cc21a884
streamfog-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/streamfog-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 889 tokens to every session, about $0.0044 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 instructions, from other repositories
blender-mcp AGENTS.md
AGENTS.md instructions for sandraschi/blender-mcp, covering blender-mcp agent context and quick ref.
blender-mcp CLAUDE.md
Claude Code instructions for sandraschi/blender-mcp, covering blender-mcp — ai-powered blender automation, commands, architecture and code style & standards.
blender-mcp copilot-instructions.md
Copilot instructions for sandraschi/blender-mcp: You have access to a Blender 3D automation server. You can control Blender scenes, objects, materials, rendering, and physics through MCP tools.
plexmcp AGENTS.md
AGENTS.md instructions for sandraschi/plexmcp, covering plexmcp — agent context, project overview, key commands, lint and test.
discord-mcp AGENTS.md
Instructions for sandraschi/discord-mcp, covering discord-mcp — agent guide, standards, key files and quick ref.
tailscale-mcp CLAUDE.md
Claude Code instructions for sandraschi/tailscale-mcp, covering tailscale-mcp — claude code guide, standards and key files.