Lobe Icons is a collection of AI and large-language-model brand logos supplied as dependency-free SVG, PNG, and WebP assets for React and React Native applications. Developers use it to display model and service brands in their interfaces, and the catalogue contains a rule and skill for working with the icon set.
Borrowing it
Nothing to install: this file belongs to lobehub/lobe-icons. 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/lobehub/lobe-icons/master/AGENTS.mdgit clone --depth 1 https://github.com/lobehub/lobe-iconsWrote 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/lobehub/lobe-icons/agents-md)<a href="https://agentmods.dev/instructions/lobehub/lobe-icons/agents-md"><img src="https://agentmods.dev/badge/instructions/lobehub/lobe-icons/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/lobehub/lobe-icons/agents-md"><img src="https://agentmods.dev/badge/instructions/lobehub/lobe-icons/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 | $0.02719 | $0.02719 |
| Opus 5.5 | $0.01088 | $0.01088 |
| Sonnet 5.5 | $0.00544 | $0.00544 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade A, and why
lobe-icons 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 2d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guide for AI agents working in this repository.
Overview
@lobehub/icons is a library of AI / LLM brand logos (models, providers, applications) shipped as React components, plus generated static SVG / PNG / WEBP / avatar packages, a React Native port, and a Vue 3 package. The docs site is https://icons.lobehub.com, built with @lobehub/docs-kit (lobedocs).
Key paths:
| Path | What |
|---|---|
src/<Brand>/ |
One folder per brand: index.ts, style.ts, index.mdx, components/*.tsx |
src/icons.ts |
Export list of every brand. The source of truth for which icons exist |
src/features/ |
ModelIcon, ProviderIcon, ProviderCombine, AgentIcon, IconAvatar, IconCombine, mappings |
src/toc.json |
Generated icon catalog (bun run build:toc). Never edit by hand |
docs/, docs.config.ts |
Docs home, guide pages and site config |
packages/react-native/ |
@lobehub/icons-rn, a separate copy of icons and mapping configs |
packages/vue/ |
@lobehub/icons-vue, generated from the React icons and mappings; native Vue primitives in src/ |
packages/static-{svg,png,webp,avatar}/ |
Generated by CI. Never edit by hand |
scripts/ |
toc, static, README and RN conversion workflows |
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.
- 2d ago Changed · +3 lines · +123 tokens per session c61bc6e7afbc
- 15d ago Changed · +2 lines · +180 tokens per session 9e540939867a
- 16d ago First seen · 102 lines · 2,416 tokens per session scan A 13b646bbead4
lobe-icons AGENTS.md is an instructions file published in the GitHub repository lobehub/lobe-icons (2,675 stars, last pushed 3d ago), licensed MIT. It adds 2,719 tokens to every session, about $0.0109 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 2026-10-22.
lobe-icons AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lobe-icons AGENTS.mdlobehub/lobe-icons | Instructions file | 2.7k | 3d ago | MIT | A | 2,719 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |