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-gemini-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-gemini-api)<a href="https://agentmods.dev/commands/enricoros/big-agi/sync-gemini-api"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/sync-gemini-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 | $0.00559 |
| Opus 5 | $0.00005 | $0.00280 |
| Sonnet 5 | $0.00002 | $0.00112 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
sync-gemini-api 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.
What it actually says
Please take a look at my API code for Google Gemini: message wire types src/modules/aix/server/dispatch/wiretypes/gemini.wiretypes.ts, assembly of the request messages (adapters) src/modules/aix/server/dispatch/chatGenerate/adapters/gemini.generateContent.ts, and parsing of the response in streaming or not src/modules/aix/server/dispatch/chatGenerate/parsers/gemini.parser.ts.
IMPORTANT: we only support the generateContent API, not other Gemini APIs such as embeddings, etc. Caching is only supported when implicit, we do not explicitly manage Gemini Caches. Same for file uploads and other systems. Image generation happens through models, i.e. 'Gemini 2.5 Flash - Nano Banana' generates images using AIX from generateContent (chat input).
Then take a look at the newest API information available. Try these sources, and be creative if some are blocked:
Primary Sources:
- Docs API 1/2: https://ai.google.dev/api/generate-content
- Docs API 2/2: https://ai.google.dev/api/caching#Content
- Release notes: https://ai.google.dev/gemini-api/docs/changelog
Alternative Sources if primary blocked:
- Google AI JavaScript SDK: https://github.com/googleapis/js-genai (check latest commits, README, type definitions) Recent news and announcements: Web Search for "gemini api changelog" or "nwe gemini api updates" or "new gemini api pricing"
If all blocked: Explain what you attempted and ask user to provide documentation manually.
Live endpoint (extra signal): If .env.api-keys has GEMINI_API_KEY, fire a real streaming generateContent request and inspect the raw SSE - ground-truth for new fields, event types, response shapes, and error formats that docs lag: POST https://generativelanguage.googleapis.com/v1beta/models/{model}:streamGenerateContent?alt=sse&key=$GEMINI_API_KEY. Never commit or echo the key.
$ARGUMENTS Check carefully and look if there are any discrepancies in the protocols, the available API surface, the structure of the messages, functionality, logic, etc. Make sure you look deep in the fields of the requests and responses, especially required fields, streaming event types, and any new response shapes.
Please point out all of the differences in the API whether it's in the final parsing and reassembly of the streaming message, or the protocol changed, etc. Prioritize breaking changes and new capabilities that would improve the user experience.
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 · 32 lines · 9 tokens per session scan A 094ac816626b
sync-gemini-api is a command published in the GitHub repository enricoros/big-AGI (7,109 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 559 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
AGENTS
Per-command agent-optimized usage and structure guide.
setup
Configure claude-delegator with Codex (GPT) or Gemini MCP servers.
netllm-connect
Wire Cursor, Claude Code, Codex, or Honcho to the local netllm router.
forge
You are in FORGE MODE. Execute the following.
apex-architect
Use the @apex-architect agent to help the user with the following architectural or debugging matter: $ARGUMENTS.
echo-analyst
Use the @echo-analyst agent to surface requirement gaps and assumptions for the following: $ARGUMENTS.