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-kimi)<a href="https://agentmods.dev/commands/enricoros/big-agi/update-models-kimi"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/update-models-kimi.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 | $0.00010 | $0.00693 |
| Opus 5 | $0.00005 | $0.00347 |
| Sonnet 5 | $0.00002 | $0.00139 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
update-models-kimi 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.
`curl -sL <url>.md` beats WebFetch on these: the .md still embeds those tables as a JSX `<DocTable rows={[...]}/>` literal, which curl gives you verbatim. What it actually says
Update src/modules/llms/server/openai/models/moonshot.models.ts with latest model definitions.
Reference 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 (fetch directly, no search needed): platform.kimi.ai (was platform.moonshot.ai - now 301 redirect).
Append .md to any docs URL to get clean markdown - the HTML pages render pricing/parameter tables via a JS component that WebFetch drops.
curl -sL <url>.md beats WebFetch on these: the .md still embeds those tables as a JSX <DocTable rows={[...]}/> literal, which curl gives you verbatim.
- Model list + deprecation/sunset notices: https://platform.kimi.ai/docs/models.md
- Pricing: https://platform.kimi.ai/docs/pricing/chat.md is only an index of cards; the numbers live in per-model pages
pricing/chat-k3.md,chat-k27-code.md,chat-k26.md,chat-k25.md,chat-v1.md(a page can outlive its index card - K2.5's card is gone but chat-k25.md still serves) - Skip https://platform.kimi.ai/docs/platform-changelog.md - abandoned, last entry 2025-04-07
- Per-model parameter matrix (thinking vs reasoning_effort, temperature/top_p/n locks, tool_choice): https://platform.kimi.ai/docs/api/models-overview.md
- API reference: https://platform.kimi.ai/docs/api/chat.md; machine-readable: https://platform.kimi.ai/docs/openapi.json (per-model request schemas)
- Full doc index: https://platform.kimi.ai/docs/llms.txt
Do NOT use web search. Fetch the URLs directly, or ask the user to provide data, if unaccessible.
Live endpoint (extra signal): If .env.api-keys has MOONSHOT_API_KEY, scan the served model list as ground-truth for what's new/available and cross-check the docs above: curl https://api.moonshot.ai/v1/models -H "Authorization: Bearer $MOONSHOT_API_KEY". Never commit or echo the key.
Each entry carries capability flags worth diffing against the file: supports_image_in, supports_video_in, supports_reasoning, supports_dynamic_tools, supports_thinking_type, think_efforts/reasoning_efforts (valid list + default), context_length.
Probing tips: request validation runs before engine dispatch, so invalid_request_error vs engine_overloaded_error already tells you whether a param is accepted (K3 capacity is often tight - retry with backoff). Note reasoning_effort is NOT strictly validated (bogus values pass), so confirm effort levels with a reasoning-token differential, not with an error probe.
Important:
- 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
- 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 · 31 lines · 10 tokens per session scan A 9ac1d810ba67
update-models-kimi is a command published in the GitHub repository enricoros/big-AGI (7,113 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 693 once invoked, about $0.0001 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
AGENTS
Per-command agent-optimized usage and structure guide.
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.
scout-explorer
Use the @scout-explorer agent for fast parallel codebase search: $ARGUMENTS.
agi-improve
Start a self-improvement cycle to enhance capabilities.