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 skillmds/skillmd --skill opencode-design-analysisgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/opencode-design-analysis)<a href="https://agentmods.dev/skills/skillmds/skillmd/opencode-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/opencode-design-analysis/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/skillmds/skillmd/opencode-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/opencode-design-analysis.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 | $0.00187 | $0.08388 |
| Opus 5.5 | $0.00075 | $0.03355 |
| Sonnet 5 | $0.00037 | $0.01678 |
| Haiku 4.5 | $0.00019 | $0.00839 |
Grade C, and why
OpenCode-design-analysis scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Contains the literal `curl -fsSL https://opencode.ai/install | bash` command with a small copy-icon at the right edge. Sits below the install-method tab strip. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Used in the install-method tab strip on the home page (`curl` / `npm` / `bun` / `brew` / `yay`). How it starts
The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
OpenCode's marketing site is rendered entirely in Berkeley Mono — every word on the page, from the 38px hero headline down to the 14px footer fine print, sits in the same monospaced face. The visual identity comes from that single typographic decision: the page reads like a manpage or a static-site README, complete with bracketed [+] / [-] / [x] ASCII markers used in place of icons or bullets, and a wordmark rendered as block-pixel ASCII art at the top of the nav. There is no sans-serif anywhere, no display face, no italics, no decorative ornament — the system is one font and one weight away from being a 1990s whatis page rendered at modern resolutions.
The chrome is austere: warm cream canvas ({colors.canvas} — #fdfcfc with a faint blush), nearly-black ink ({colors.ink} — #201d1d), and a 4-tier neutral gray ladder for body, metadata, and disabled text. Cards don't exist as raised surfaces — sections are just hairline-bordered text blocks ({colors.hairline} 1px) sitting directly on the canvas with {spacing.section} (96px) air between them. The single "visual" moment in the entire system is a full-bleed dark hero card ({colors.surface-dark} — true near-black) that mocks up the OpenCode TUI itself: a terminal frame with tab / ctrl-p keybinding hints, a "Build" command line, and the OpenCode wordmark rendered as a pixel-block ASCII title.
The semantic palette is unusual for a brand-marketing site: it ships the full Apple Human Interface Guidelines accent ramp — {colors.accent} (Apple Blue #007aff), {colors.danger} (#ff3b30), {colors.warning} (#ff9f0a), {colors.success} (#30d158) plus their hover/active deepenings — even though the marketing surfaces themselves only use these colors in the dark hero TUI mockup as syntax-highlight stand-ins. The wider palette belongs to the in-product TUI; the marketing pages mostly stay in monochrome.
Key Characteristics:
- 100% Berkeley Mono typography across every text role — no sans-serif fallback anywhere in the chrome
- Warm cream
{colors.canvas}(#fdfcfc) as the only body background — no surface alternation across sections - Single dark surface (
{colors.surface-dark}— #201d1d) reserved exclusively for the hero TUI mockup - 4px radius (
{rounded.sm}) on every interactive element; sections themselves are sharp rectangles bordered in 1px hairline - ASCII bracket markers (
[+],[-],[x]) used as bullet glyphs in feature lists and FAQ rows - Block-pixel ASCII wordmark in the primary nav and inside the hero TUI — the brand identity is its own ASCII art
- 96px
{spacing.section}rhythm between every section, with no decorative dividers; only thin 1px{colors.hairline}rules separate content blocks
What ships with it
1 file 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.
- 4d ago First seen · 522 lines · 187 tokens per session scan C 25495526f0d1
OpenCode-design-analysis is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 187 tokens to every session and 8,388 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
Other skills, from other repositories
get-context
Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.
antv-infographic
Create beautiful infographics based on given text content. Use when users request to create infographics.
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…