Borrowing it
Nothing to install: this file belongs to stabgan/openrouter-mcp-multimodal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stabgan/openrouter-mcp-multimodal/main/AGENTS.mdgit clone --depth 1 https://github.com/stabgan/openrouter-mcp-multimodalWrote 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/stabgan/openrouter-mcp-multimodal/agents-md)<a href="https://agentmods.dev/instructions/stabgan/openrouter-mcp-multimodal/agents-md"><img src="https://agentmods.dev/badge/instructions/stabgan/openrouter-mcp-multimodal/agents-md/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/instructions/stabgan/openrouter-mcp-multimodal/agents-md"><img src="https://agentmods.dev/badge/instructions/stabgan/openrouter-mcp-multimodal/agents-md.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 | $0.02584 | $0.02584 |
| Opus 5.5 | $0.01034 | $0.01034 |
| Sonnet 5.5 | $0.00517 | $0.00517 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade A, and why
openrouter-mcp-multimodal 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 14d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
Guidance for AI coding agents (Cursor, Claude Code, Copilot, Kiro, etc.) working in openrouter-mcp-multimodal.
Before you ship
- Run
npm run cibefore claiming work is done — this runs lint, format check, version sync, build, and all tests. - Do not commit secrets (
.env, API keys). - Keep imports at the top of files — no inline imports unless documented for circular deps.
- Use exhaustive
switchwithneverin the default case for TypeScript unions.
Architecture at a glance
src/index.ts ← MCP server entry, stdio transport, .env loading
src/version.ts ← SERVER_VERSION + MCP_PROTOCOL_VERSION (must match package.json)
src/tool-handlers.ts ← Tool router: ListTools + CallTool dispatch
src/tool-definitions.ts ← Tool JSON schemas (inputSchema, outputSchema, annotations, icons)
src/tool-descriptions.ts ← TOOL_NAMES array + structured descriptions (use when / bad examples / fails when)
src/tool-icons.ts ← SVG data URI icons for each tool (MCP 2025-11-25)
src/tool-handlers/ ← Handler files (some serve multiple tools, e.g. async-chat.ts → 2 tools, generate-video.ts → 3)
src/openrouter-api.ts ← Direct HTTP client for /videos, /images, /audio/speech, /audio/transcriptions, /rerank, /embeddings, /api/alpha/decisions
src/openrouter-openai-client.ts ← OpenAI SDK configured for OpenRouter base URL
src/errors.ts ← ErrorCode taxonomy (INVALID_INPUT, UNSAFE_PATH, UPSTREAM_*, etc.)
src/logger.ts ← Stderr JSON line logger with secret redaction (stdout reserved for MCP)
src/model-cache.ts ← Shared model catalog cache with TTL, routing suffix handling, and search
src/tts-defaults.ts ← TTS default constants (model, voice, response format)
Tools (21 total)
| Category | Tools |
|---|---|
| Chat | chat_completion, start_chat_completion, get_chat_completion_status |
| Vision | analyze_image, generate_image, generate_image_dedicated |
| Audio | analyze_audio, generate_audio, text_to_speech, speech_to_text |
| Video | analyze_video, generate_video, generate_video_from_image, get_video_status |
| Catalog | search_models, get_model_info, validate_model, rerank_documents, health_check |
| Embedding | embed_text |
| Decisions | decide |
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.
- 14d ago Changed · +21 lines · +421 tokens per session e05f3e30f983
- 15d ago Changed · +2 lines · +136 tokens per session c5292fcf45a5
- 19d ago Changed 460b6d70db5b
- 20d ago Changed · +70 lines · +1,234 tokens per session e5947c852177
- 1mo ago Changed · +1 lines · +10 tokens per session e12758e7396f
- 1mo ago First seen · 79 lines · 783 tokens per session scan A eb630f65fcab
openrouter-mcp-multimodal AGENTS.md is an instructions file published in the GitHub repository stabgan/openrouter-mcp-multimodal (101 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,584 tokens to every session, about $0.0103 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.