Borrowing it
Nothing to install: this file belongs to bifrost-proxy/bifrost. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bifrost-proxy/bifrost/main/.agents/skills/design-md/SKILL.mdgit clone --depth 1 https://github.com/bifrost-proxy/bifrostWrote 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/bifrost-proxy/bifrost/design-md)<a href="https://agentmods.dev/skills/bifrost-proxy/bifrost/design-md"><img src="https://agentmods.dev/badge/skills/bifrost-proxy/bifrost/design-md/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/bifrost-proxy/bifrost/design-md"><img src="https://agentmods.dev/badge/skills/bifrost-proxy/bifrost/design-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00477 |
| Opus 5.5 | $0.00023 | $0.00191 |
| Sonnet 5.5 | $0.00012 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
design-md 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 1mo 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.
What it actually says
Bifrost DESIGN.md
This skill keeps Bifrost product interaction work consistent across agents and sessions.
When to Use
Use this skill before modifying:
web/UI, layout, theme, navigation, dashboards, tables, modals, panels, or interaction copydesktop/shell UI and desktop-specific chromesite/,docs/, ordocs-en/visual style, homepage, navigation, screenshots, or docs theme- any user-facing feature where color, density, component choice, spacing, typography, or visual hierarchy could drift
Required Reading
- Read
DESIGN.mdfrom the repository root. - For process and verification details, read
design/design-md-system.md. - If the change touches site deployment, also follow the root
AGENTS.mdsite deployment boundary.
Working Rules
- Treat
DESIGN.mdYAML front matter as the normative design-token source. - Treat the Markdown sections as rationale for how to apply those tokens.
- Prefer existing Ant Design tokens in
web/and the existing CSS variables insite/home/styles.css. - Keep operational UI dense, stable, and scan-friendly. Do not turn WebUI screens into marketing layouts.
- Preserve light/dark parity. If a new color is needed in WebUI, route it through Ant Design token usage, CSS variables, or a documented DESIGN.md token.
- Use icons for tool actions when an established icon exists; use text buttons only for clear commands.
- Keep card usage restrained: repeated items, modals, and genuinely framed tools.
- When editing
DESIGN.md, runpnpm design:lint.
Verification
For design-token or design-rule changes:
pnpm design:lint
For UI implementation changes, add the normal module tests plus human_tests coverage required by the repository. At minimum, verify light and dark theme behavior for WebUI changes and record the result in the relevant human_tests/ document.
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.
- 1mo ago First seen · 45 lines · 58 tokens per session scan A 09978f833049
design-md is a skill published in the GitHub repository bifrost-proxy/bifrost (165 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 477 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
omh-frontend
This is an OMH frontend workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-accessibility-audit
This is an OMH accessibility-audit workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-visual-qa
This is an OMH visual-qa workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-design-quality-gate
This is an OMH design-quality-gate workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-apple-design
This is an OMH apple-design workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).