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 xzhih/app-icon-skill --skill app-icon-gengit clone --depth 1 https://github.com/xzhih/app-icon-skillWrote 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/xzhih/app-icon-skill/app-icon-gen)<a href="https://agentmods.dev/skills/xzhih/app-icon-skill/app-icon-gen"><img src="https://agentmods.dev/badge/skills/xzhih/app-icon-skill/app-icon-gen/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/xzhih/app-icon-skill/app-icon-gen"><img src="https://agentmods.dev/badge/skills/xzhih/app-icon-skill/app-icon-gen.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 | $0.00053 | $0.02411 |
| Opus 5 | $0.00026 | $0.01205 |
| Sonnet 5 | $0.00011 | $0.00482 |
| Haiku 4.5 | $0.00005 | $0.00241 |
Grade A, and why
app-icon-gen 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 10d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
44 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.
- agents/openai.yaml 323 B
- examples/flat-linked-mark-spec.json 2.7 KB
- examples/material-chain-base-spec.json 4.6 KB
- examples/semantic-image-prompts/black-stage-continuous-loop-loopvault.md 15 KB
- examples/semantic-image-prompts/black-stage-mark-signal-vault.md 9.2 KB
- examples/semantic-image-prompts/blue-field-cutout-badge.md 9.0 KB
- examples/semantic-image-prompts/connected-flow-flat-silver-compact.md 9.8 KB
- examples/semantic-image-prompts/dark-gradient-pale-orbit-cluster-quietseed.md 16 KB
- examples/semantic-image-prompts/glass-ribbon-filterwave.md 23 KB
- examples/semantic-image-prompts/kinetic-pop-tempostride-ribbon.md 12 KB
- examples/semantic-image-prompts/organic-blob-fusemap.md 8.3 KB
- examples/semantic-image-prompts/outlined-friendly-action-mark.md 10 KB
- examples/semantic-image-prompts/README.md 8.2 KB
- examples/semantic-image-prompts/silver-field-black-mask-catmask.md 12 KB
- examples/semantic-image-prompts/single-hue-gradient-cropped-silhouette-nighthop.md 16 KB
- examples/semantic-image-prompts/single-hue-gradient-outlined-mascot-charmbyte.md 15 KB
- examples/semantic-image-prompts/single-hue-gradient-soft-white-symbol-emberlite.md 14 KB
- examples/semantic-image-prompts/souvenir-decal-stickers.md 16 KB
- references/concept-prompts.md 7.0 KB
- references/cookbook.md 14 KB
- references/failure-modes.md 32 KB
- references/golden-examples.md 1.3 KB
- references/icon-composer.md 19 KB
- references/optimization-methods.md 20 KB
- references/semantic-authoring.md 30 KB
- references/semantic-icon-design.md 13 KB
- references/source-requirements.md 21 KB
- references/style-directions.md 28 KB
- references/verification.md 41 KB
- scripts/author_icon.mjs 69 KB runs code
- scripts/clean_sticker_matte.mjs 7.1 KB runs code
- scripts/geometry_audit.mjs 12 KB runs code
- scripts/lib/apple_export_profiles.mjs 1.1 KB runs code
- scripts/lib/icon_contract.mjs 4.7 KB runs code
- scripts/normalize_reference.mjs 2.6 KB runs code
- scripts/package-lock.json 8.4 KB
- scripts/package.json 933 B
- scripts/polish_svg_candidates.mjs 6.2 KB runs code
- scripts/polish_svg_geometry.mjs 14 KB runs code
- scripts/prepare_bitmap_layer.mjs 5.8 KB runs code
- scripts/prepare_foreground_layer.mjs 11 KB runs code
- scripts/shape_facts.mjs 22 KB runs code
- scripts/summarize_icon_run.mjs 7.8 KB runs code
- scripts/verify_icon_package.mjs 83 KB runs code
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.
- 10d ago First seen · 135 lines · 53 tokens per session scan A 78bf5abca223
app-icon-gen is a skill published in the GitHub repository xzhih/app-icon-skill (6 stars, last pushed 2mo ago), with no licence file. It adds 53 tokens to every session and 2,411 once invoked, about $0.0003 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
frame-logo-outro
Segmented logo assembly, glow bloom, and tagline reveal for video outros or brand closing frames.
visual-identity-prompt
Writes a comprehensive visual identity prompt for a show, channel, or publication — a master brief that defines the complete visual language and can be used to art-direct any asset in the project's visual system.
qiaomu-icon-generator
Generate multiple app, favicon, or website icon candidates with either the local QM Icon Studio CLI or Codex built-in image generation with reference icons, then present a contact sheet so the user can choose. Use when building websites or apps and needing reusable icon options.
new-template
Scaffolds a new visual (.tsx) in an existing BrandArtisan project, aligned with its brand.md guidelines. Use when the user wants to create a new image/cover/banner/OG in a project ("new visual", "add a cover for X", "create the OG for Y"). Always reads brands/ /brand.md and refuses if it is missing.
brand-assets
Generates or regenerates a project's brand assets (logo, favicon and their variants) through the brand toolchain, faithfully. Use when the user wants to "regenerate the logo / the favicon", "add an icon or logo variant", "a new brand variant", or "set up a project's brand toolchain". Works in tools/ / reusing…
x-page
Creates the X / Twitter profile visuals (profile photo and header / banner) at X's official dimensions. Use when the user wants an "X/Twitter profile photo", a "Twitter header", an "X banner" or "the X avatar" for a project. Produces one or two .tsx templates at the sizes X imposes (profile 400x400, header 1500x500)…