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 ByteFlipper-58/material-icons-agent-skill --skill material-iconsgit clone --depth 1 https://github.com/ByteFlipper-58/material-icons-agent-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/byteflipper-58/material-icons-agent-skill/material-icons)<a href="https://agentmods.dev/skills/byteflipper-58/material-icons-agent-skill/material-icons"><img src="https://agentmods.dev/badge/skills/byteflipper-58/material-icons-agent-skill/material-icons/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/byteflipper-58/material-icons-agent-skill/material-icons"><img src="https://agentmods.dev/badge/skills/byteflipper-58/material-icons-agent-skill/material-icons.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 | $0.00088 | $0.03128 |
| Opus 5 | $0.00044 | $0.01564 |
| Sonnet 5 | $0.00018 | $0.00626 |
| Haiku 4.5 | $0.00009 | $0.00313 |
Grade A, and why
material-icons 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 8d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Material Icons
Use official Material Symbols by default. Use classic Material Icons only when the project already uses them, requires two-tone, or explicitly asks for them.
Workflow
- Detect the target environment before choosing an integration path: Android Compose, Android Views/XML, Flutter, web, or native SVG framework. Reuse its existing local-asset conventions and established icon style where possible.
- Extract filters from the request. Ask one concise question only if the intended action is ambiguous. Infer
outlined, 24 px, and accessible labels when omitted. - Search names with
scripts/search_material_symbols.pyfor reproducible candidates. If a visual or semantic decision is important, verify shortlisted candidates at Google Fonts Icons. - Return or use 2-4 candidates with their exact symbol names. Prefer the most literal, familiar action over a metaphor.
- Integrate only the selected icon. Do not add a global font or an entire icon bundle when a single SVG/vector asset is sufficient.
- Add an accessible label for interactive icons; use a null/decorative label only where the icon is explicitly redundant to adjacent text.
- Read
material-icons-policy.jsonat the repository root before asking configuration questions. Create it only with user approval, usingscripts/project_icon_policy.py init. - Detect the language of the user's prompt. Formulate all questions, suggestions, choice options, and answers exclusively in that language. Do not output slash-separated bilingual text (e.g. "English / Russian").
Filters and selection
Accept meaning, platform, set, style, fill, weight, grade, opticalSize, size, color, format, and accessibilityLabel.
set: defaultMaterial Symbols;Material Iconsis legacy and has no new icons.style:outlined(default),rounded, orsharp.fill: Symbols support 0 to 100; use filled states sparingly to indicate selection or a saved state.weight: 100 to 700, default 400.grade: -50 to 200, default 0.opticalSize: 20 to 48, default 24.- Prefer 20 or 24 px if pixel-grid crispness matters.
- Avoid using Material Symbols for third-party brand logos; use the brand's approved assets instead.
What ships with it
11 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 224 B
- references/aliases.json 360 B
- references/host-adapters.md 1.3 KB
- scripts/agent_features.py 4.3 KB runs code
- scripts/audit_icon_assets.py 1.2 KB runs code
- scripts/delete_material_symbol.py 923 B runs code
- scripts/import_material_symbol.py 3.3 KB runs code
- scripts/preview_material_symbols.py 1.4 KB runs code
- scripts/project_icon_policy.py 1.2 KB runs code
- scripts/search_material_symbols.py 5.7 KB runs code
- scripts/sync_offline_catalog.py 772 B 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.
- 8d ago First seen · 180 lines · 88 tokens per session scan A 35a7520ca822
material-icons is a skill published in the GitHub repository ByteFlipper-58/material-icons-agent-skill (0 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 3,128 once invoked, about $0.0004 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
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
fireworks-tech-graph
Create technical diagrams such as software architecture, data flow, flowcharts, sequence diagrams, C4 reviews, cloud deployments, event streams, observability investigations, agent/memory systems, UML, ER, network topology, timelines, and technical concept maps, then export SVG, PNG, focused semantic SVG-to-GIF…
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…