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 skills add qwwiwi/codex-gpt-image-2-subscription --skill logo-companygit clone --depth 1 https://github.com/qwwiwi/codex-gpt-image-2-subscriptionWrote 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/skills/qwwiwi/codex-gpt-image-2-subscription/logo-company)<a href="https://agentmods.dev/skills/qwwiwi/codex-gpt-image-2-subscription/logo-company"><img src="https://agentmods.dev/badge/skills/qwwiwi/codex-gpt-image-2-subscription/logo-company/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/skills/qwwiwi/codex-gpt-image-2-subscription/logo-company"><img src="https://agentmods.dev/badge/skills/qwwiwi/codex-gpt-image-2-subscription/logo-company.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 | $0.00141 | $0.00859 |
| Opus 5 | $0.00071 | $0.00430 |
| Sonnet 5 | $0.00028 | $0.00172 |
| Haiku 4.5 | $0.00014 | $0.00086 |
Grade A, and why
logo-company 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 12d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
logo-company — official brand SVG lookup
Source
Base: glincker/thesvg — 5 886 brands, 11 624 SVGs, MIT license. Structure: public/icons/<slug>/{default,mono,color,dark,light}.svg.
Local cache: <skill>/_cache/brand-icons/ — populated automatically on first request.
Which variant
default.svg— official brand colors. Use in full-color banners, covers, posts. Instantly recognizable.mono.svg— single-color, usuallyfill="currentColor". Use on styled backgrounds — recolor to any accent via CSScoloror by substituting the fill. Minimal, never breaks your palette.color.svg/dark.svg/light.svg— some brands ship variants for dark/light backgrounds.
Process
1. Find a logo
<skill>/scripts/find-logo.sh <brand-name> [variant]
<brand-name>— tolerant to typos / case / synonyms (claude, Claude, claude-code, anthropic, openai-chatgpt).[variant]— optional:default(default),mono,color,dark,light.
The script searches the local cache with fuzzy-match, falls back to raw.githubusercontent with slug auto-resolution, prints the SVG path. Exit 0 = found, exit 1 = not found.
2. Refresh the cache
<skill>/scripts/update-cache.sh [brand1] [brand2] ...
3. Use the SVG
- Composite onto a generated image: wrap the banner PNG + the logo path in an SVG and render to PNG (e.g.
@resvg/resvg-js). Formonorecolor by replacingcurrentColor. - As a generation reference: pass the rendered logo PNG as a reference image to the
codex-imageskill — gpt-image-2 will carry the mark into the artwork. - Inline in HTML: paste mono SVG inside a
<div style="color:#D4FF00">—currentColorpicks up the accent.
Frequently used slugs
Full catalog: references/brands-catalog.md. Highlights:
| Category | Slugs |
|---|---|
| Claude / Anthropic | claude, claude-ai, claude-code, anthropic |
| OpenAI | openai, openai-chatgpt, codex-openai, dall-e-openai, sora-openai |
| Other LLMs | google-gemini, xai-grok, mistral-ai, deepmind-google |
| Coding tools | cursor, github-copilot |
| Social | telegram, instagram, youtube, tiktok, x-formerly-twitter |
| Stack | notion, firebase, supabase, vercel, github, figma |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 63 lines · 0 tokens per session scan A 15d1d8b05086
logo-company is a skill published in the GitHub repository qwwiwi/codex-gpt-image-2-subscription (9 stars, last pushed 3mo ago), licensed MIT. It adds 141 tokens to every session and 859 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
ima2-uiux
Design direction discovery and UX judgment for ima2 users. Use for UI/UX direction and design judgment — vague visual briefs, onboarding, empty/error/loading states, layout vocabulary, typography breaks, favicons, logos, and brand identity choices. Pairs with ima2-front: this skill decides the design direction, then…
vision-review
A tool for reading images and checking screenshots, including text, layout, visual defects, watermarks, and logos.
codex-dream-skin
Apply, launch, verify, repair, update, or restore a full decorative skin for the Windows Codex desktop app. Use when the user asks for a Codex theme that goes beyond official color settings, wants the pink-purple Dream/Fiona-style interface, needs the skin reapplied after a Codex update, or needs a safe rollback…
codex-dream-skin-studio
Install, customize, launch, verify, repair, update, or restore Codex Dream Skin Studio on macOS. Use when a user wants to turn a personal image into one continuous full-window Codex wallpaper with adaptive readability layers while preserving the native interface, or needs safe CDP theme troubleshooting and rollback.
local-image-gen
A local command-line tool for generating or editing images with Codex, Grok, or Gemini/Antigravity accounts and optional API keys.
cowart
An infinite-canvas plugin that opens a tldraw drawing board inside Codex. It lets people and Codex sketch, annotate, generate images, and revise them together, with the canvas saved in the project folder.