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.
git 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/update-models-gemini)<a href="https://agentmods.dev/commands/enricoros/big-agi/update-models-gemini"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/update-models-gemini.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 | $0.00009 | $0.00561 |
| Opus 5 | $0.00005 | $0.00280 |
| Sonnet 5 | $0.00002 | $0.00112 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
update-models-gemini 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 8d 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):** If `.env.api-keys` has `GEMINI_API_KEY`, scan the served model list as ground-truth for what's new/available and cross-check the docs above: `curl "https://generativelanguage.googleapis. What it actually says
Update src/modules/llms/server/gemini/gemini.models.ts with latest model definitions.
Reference src/modules/llms/server/llm.types.ts, src/modules/llms/server/llm.server.types.ts, and src/modules/llms/server/models.mappings.ts for context only. Focus on the model file, do not descend into other code.
Primary Sources:
- Models: https://ai.google.dev/gemini-api/docs/models
- Pricing: https://ai.google.dev/gemini-api/docs/pricing
- Changelog: https://ai.google.dev/gemini-api/docs/changelog
- Deprecations: https://ai.google.dev/gemini-api/docs/deprecations - the authoritative table of release + shutdown dates per model id; it overrides dates inferred from the changelog. "No shutdown date announced" means the def must carry NO
deprecatedfield (Google does not auto-retire a stable model one year after release)
Fallbacks if blocked: Check Google AI JS SDK at https://github.com/googleapis/js-genai, search "gemini models latest pricing", "gemini latest models", or search GitHub for latest model prices and context windows
Live endpoint (extra signal): If .env.api-keys has GEMINI_API_KEY, scan the served model list as ground-truth for what's new/available and cross-check the docs above: curl "https://generativelanguage.googleapis.com/v1beta/models?pageSize=1000&key=$GEMINI_API_KEY". pageSize is required: the default is 50 and the tail (newest models included) is silently dropped behind a nextPageToken. Never commit or echo the key. When looping ids in zsh, write ${m}:generateContent - bare $m:ge... is eaten as a zsh history modifier and every probe silently 404s.
Listed != reachable: the list endpoint keeps returning models that 404 on generateContent (filterNotFoundModelNames), and returns retired-preview aliases that still serve (sometimes routed to their successor - check modelVersion in the response). Re-verify both with a 1-token POST per suspect id before adding or removing a def.
Important:
- Ignore context windows (auto-determined at runtime) and training cutoffs (not supported)
- Review the full model list for additions, removals, and price changes
- Minimize whitespace/comment changes, focus on content
- Preserve comments to make diffs easy to review, do NOT remove comments
- Flag broken links or unexpected content
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.
- 8d ago First seen · 27 lines · 9 tokens per session scan A 428a7947ab36
update-models-gemini is a command published in the GitHub repository enricoros/big-AGI (7,114 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 561 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
prompt
A command that creates AI prompts and applies fixed rules for constraints, principles, and when the command may run.
prompt-sync
A command that synchronizes a prompt-generation system with a local folder, a personal vault, and a deployment repository. It keeps the same source structure across those locations.
prompt-update
A command for updating and combining prompt-engineering guidance, meaning methods for writing clearer instructions for AI.
auto-prompt
A command for automatically generating AI prompts in a format compatible with K-AI Station. The available description does not specify which prompt tasks or models it supports.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.