create-mac-icon

create-mac-icon is a skill for Claude Code, Codex from fledgeling-co/fledgeling-plugins. It costs 158 tokens per session (5,652 once invoked), scanned A, original, MIT.

A workflow for designing and checking macOS application icons. It uses a catalogue of existing icons, creates vector or raster designs, and compares rendered results against a reference image.

In plain words
What is it for?
Use it to choose an icon direction, create an icon master, render it at different sizes, score its similarity to a reference, and iterate on the design.
Why use it?
It helps turn an app idea into a consistent icon and identify visual weaknesses through repeatable checks instead of relying only on visual judgment.

Skill for Claude CodeCodex

Part of the create-mac-icon plugin — 1 skill shipped together

Install

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.

agentmods
npx agentmods add skills/fledgeling-co/fledgeling-plugins/create-mac-icon
Any agent
npx skills add fledgeling-co/fledgeling-plugins --skill create-mac-icon
Clone the repo
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code, Codex.

Or install create-mac-icon, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for create-mac-icon

README.md
[![agentmods](https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/create-mac-icon.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/create-mac-icon)
Your own site
<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/create-mac-icon"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/create-mac-icon.svg" alt="Measured on agentmods" height="20"></a>
Per session 158 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,652 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00158 $0.05652
Opus 5 $0.00079 $0.02826
Sonnet 5 $0.00032 $0.01130
Haiku 4.5 $0.00016 $0.00565

Measured 5d ago against content hash 8f464d678954, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

create-mac-icon 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 5d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/alpha_bleed.py, scripts/audit_sheet.py, scripts/fidelity.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

authored blue in a warm-lit scene, a curl drawn lighter than the ground
plugins/create-mac-icon/skills/create-mac-icon/SKILL.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Mac Icon

Design a macOS app icon that is native to the platform (correct era grammar), committed to one direction (ownable), and — the part most pipelines skip — materially rich in the shipped vector master, proven by scoring it against a raster reference rather than by eyeballing it.

The whole skill exists because of one repeated observation: hand-authored SVG masters win composition and 16px survival but lose material (volumetric shading, lighting, translucency) to diffusion rasters at equal audit scores. The fix is not "try harder" — it's a measured loop.

First, two quick exits. If the request is empty, ask in one line what the app is and what it does, then stop. If it is exactly one of structure, score, gate, check, render or iterate, it is a subcommand or a workflow name and not a brief — say which command you think they meant and confirm. But do not design an icon named "score": if what follows describes something an icon could be for — a cashflow tracker, an export tool, a pottery-studio booking app — it is a brief, so design it.

Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It converts the rubric's stated maxima — one soft light, two hue families, no baked corners — into a bound ledger read back off the emitted SVG, and refuses an audit.html score cell whose render nobody opened. Other models skip it.

Where a commission lands

Learn the anatomy before building it. Everything below sits in the commission directory you were given:

icon.svg                  the layered master that ships (glob-required name)
build_icon.py             the generator: geometry + material as named constants
icon-<engine>-<id>.svg    the Arrow take
icon-<engine>-<id>.png    the raster take (+ -masked.png)
audit.html                the contact sheet — a gated deliverable, not a note
audit-renders/            <take>-{1024,256,128,96,64,32}.png
  render-manifest.json    what was rendered, from what, as what kind
loop-runs/rNN/            score.json · residual-1024.png · edges-{candidate,reference}.png
                          candidate-1024.png · reference-1024.png · brief.md
                          gate.txt · review.html · review-feedback.json · _before/
                          panel/{bundle/, bundle-swapped/, verdict-*.json, panel.json}
loop-runs/last-accepted/  the gate's rollback point
loop-runs/best-promoted/  the best take a blind panel ever preferred — what ships

Read the full file on GitHub · 381 lines

Files

What ships with it

50 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.

Changes

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.

  1. 5d ago First seen · 381 lines · 158 tokens per session scan A 8f464d678954

Subscribe to this mod's changes

create-mac-icon is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed today), licensed MIT. It adds 158 tokens to every session and 5,652 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens