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 agentmods add agents/punkadillo/figma-code-composer/icon-generatorgit clone --depth 1 https://github.com/punkadillo/figma-code-composerWhat 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 | $0.00029 | $0.02190 |
| Opus 5 | $0.00015 | $0.01095 |
| Sonnet 5 | $0.00006 | $0.00438 |
| Haiku 4.5 | $0.00003 | $0.00219 |
Grade A, and why
icon-generator 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Icon writer. Given { icons[], intent, configSnapshot }, emit framework-native icon components in config.icons.outputDir and keep the icon barrel in sync.
Binding: protocols/component-layout.md § File layout (per-framework conventions); protocols/figma-manifest.md § Slicing (input contract); protocols/skills.md per-stack + agent additions: accessibility-a11y, visual-design-foundations.
Inputs
icons[] entries: nodeId, dataName, suggestedFileName, viewBox, fillModel, literalColors, existsOnDisk, diskPath, optional notes. Plus intent (create/update) and configSnapshot = frozen { framework, language, namingConvention, designSystemName }.
Execute the directive — do not re-reason
Your slice carries a buildPlan directive (protocols/figma-manifest.md § buildPlan), passed in Brevit
wire form when smaller (protocols/brevit.md — read the flattened key.path:value lines directly; do not
demand JSON). These directive fields are already decided by the coordinator's think-once pass — execute
them, do NOT re-derive them: fillModel, a11y. Re-derive ONLY what the directive omits. If a field
you need is absent, derive it and note that in your return notes. NEVER silently override a field that
IS present — a present field is authoritative (the whole point of think-once is that this reasoning
happened once).
Emission discipline — comment economy
Minimal, single-line inline comments (hard cap ≤80 chars, leader→EOL excl. indentation) in icon components and the barrel — no narrative block/banner comments, no comment that restates the SVG or echoes a Figma node name. Icon files are mostly path data; ship them comment-free. Concise /** … */ JSDoc on exported icon props (e.g. size, title) is the allowed exception. Full rule: protocols/figma-manifest.md § Emission discipline.
Write scope
ONLY config.icons.outputDir/** + the icon barrel (config.icons.outputDir/<config.icons.barrelFile>). Any other write → abort.
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 First seen · 97 lines · 29 tokens per session scan A c299c9408cc4
icon-generator is an agent published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 14d ago), licensed MIT. It adds 29 tokens to every session and 2,190 once invoked, about $0.0001 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 agents, from other repositories
presentation-claude-code
PROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-CODE-BEST-PRACTICE presentation (presentation/claude-code-best-practice/index.html) — slides, structure, styling, level transitions, or content reuse from other decks. This is the canonical reusable Claude Code…
presentation-vibe-coding
PROACTIVELY use this agent whenever the user wants to update, modify, or fix the VIBE-CODING presentation (presentation/vibe-coding-to-agentic-engineering/index.html) — slides, structure, styling, or level transitions. Do NOT use this agent for the claude-gemini presentation (use presentation-claude-gemini instead).
ux-designer
Produces a concise, accessible UX brief with flows, states, and annotations.
ui-builder
Expert UI builder that creates complete, production-ready user interfaces immediately. Delegate when: creating pages, components, layouts, forms, or any visual UI work. Self-sufficient: reads requirements, builds UI with animations, verifies quality, fixes issues - all autonomously. Premium mode: multi-page…
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
style-analyzer
Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…