Big-AGI is an open-source workspace for using multiple AI models through chat and other AI functions. It is intended for engineers, founders, researchers, and other users who want to work with AI personas, model comparisons, image generation, voice, documents, and code-related features. The catalogue entries provide commands, instructions, and a skill for working with Big-AGI.
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 commands/enricoros/big-agi/sync-openrouter-apigit clone --depth 1 https://github.com/enricoros/big-AGIWrote 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/commands/enricoros/big-agi/sync-openrouter-api)<a href="https://agentmods.dev/commands/enricoros/big-agi/sync-openrouter-api"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/sync-openrouter-api.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 | $0.00009 | $0.00784 |
| Opus 5 | $0.00005 | $0.00392 |
| Sonnet 5 | $0.00002 | $0.00157 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
sync-openrouter-api scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Live endpoint (extra signal):** The models list is public - `curl https://openrouter.ai/api/v1/models` - ground-truth for per-model capabilities/metadata. If `.env.api-keys` has `OPENROUTER_API_KEY`, also fire a real s What it actually says
Review the OpenRouter implementation:
- Models list:
src/modules/llms/server/openai/openrouter.wiretypes.ts(list API response schema) - Chat wire types:
src/modules/aix/server/dispatch/wiretypes/openai.wiretypes.ts(OpenAI-compatible) - Request adapter:
src/modules/aix/server/dispatch/chatGenerate/adapters/openai.chatCompletions.ts('openrouter' dialect) - Response parser:
src/modules/aix/server/dispatch/chatGenerate/parsers/openai.parser.ts(shared OpenAI parser) - Vendor config:
src/modules/llms/vendors/openrouter/openrouter.vendor.ts
GOAL: Ensure complete support for OpenRouter's API including advanced features like reasoning/thinking tokens, tool use, search integration, and multi-modal capabilities. OpenRouter is OpenAI-compatible but has important extensions and differences.
Use Task tool with subagent_type=Explore and thoroughness="very thorough" to discover:
- Map API structure - all endpoints, parameters, capabilities from https://openrouter.ai/docs
- Advanced features - How to use: reasoning/thinking tokens (o1, DeepSeek R1), tool use/function calling, search integration, multi-modal (vision/audio)
- Changelog location - How does OpenRouter communicate API updates and breaking changes?
- Model metadata - What capabilities are exposed in the models list API? How to detect feature support?
- OpenAI deviations - Extensions, special headers (HTTP-Referer, X-Title), response fields, streaming differences
Then check the latest API information. Try these sources (be creative if blocked):
Primary Sources:
- API Reference: https://openrouter.ai/docs/api-reference
- Chat Completions: https://openrouter.ai/docs/api-reference#chat-completions
- Models List: https://openrouter.ai/docs/api-reference#models-list
- Parameters Guide: https://openrouter.ai/docs/parameters
- Announcements: https://openrouter.ai/announcements (feature launches, API updates, new models)
- Models Directory: https://openrouter.ai/models (check metadata for capabilities)
Alternative Sources:
- GitHub: https://github.com/OpenRouterTeam (SDKs, examples, issues for recent changes)
- Web Search: "openrouter api changelog" or "openrouter reasoning tokens" or "openrouter tool use"
If blocked: Ask user to provide documentation.
Live endpoint (extra signal): The models list is public - curl https://openrouter.ai/api/v1/models - ground-truth for per-model capabilities/metadata. If .env.api-keys has OPENROUTER_API_KEY, also fire a real streaming POST https://openrouter.ai/api/v1/chat/completions ("stream":true) to inspect reasoning/tool/usage fields and OpenRouter-specific extensions. Never commit or echo the key.
$ARGUMENTS Focus on discrepancies and gaps:
- Request/Response structure: New fields, changed requirements, streaming event types
- Feature support: Thinking tokens format, tool calling protocol, search parameters
- Model capabilities: How to detect and enable advanced features per model
- OpenRouter extensions: Headers, routing, fallbacks, rate limiting (free vs paid)
- Breaking changes: Protocol updates, deprecated fields, new required parameters
Report differences in wire types, adapter logic, parser handling, or dialect-specific quirks. Prioritize new capabilities that improve user experience (reasoning visibility, better tool use, etc.).
When making changes, add comments with date: // [OpenRouter, 2026-MM-DD]: explanation
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 · 52 lines · 9 tokens per session scan A 65ab67f2962e
sync-openrouter-api is a command published in the GitHub repository enricoros/big-AGI (7,109 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 784 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
bifrostpublicstaticblogn8n-helicone-node
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓.
prompt
Command "prompt" from treylom/prompt-engineering-skills, covering /prompt - ai 프롬프트 생성기, ⛔ critical rules (최상단 배치), 🏛️ 대원칙 불변 조항 (재경님 2026-07-29 — 전 목적·전 모델·향후 어떤 이식/개편에도 불변), 절대 금지 사항 (constraints) and 실행 트리거 (only these).
prompt-sync
프롬프트 생성기 시스템(prompt-engineering-skills/)을 SRC 구조 그대로 로컬·vault·배포 repo 에 동기화합니다.
prompt-update
프롬프트 엔지니어링 통합 업데이트 (tofu-at 생성 — /prompt-update).
auto-prompt
AI 프롬프트 자동 생성 - K-AI 스테이션 양식 호환 (한 행에 한 모델).
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.