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.
git clone --depth 1 https://github.com/AgentsORG/design-engineeringWrote 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/commands/agentsorg/design-engineering/apply-design-md)<a href="https://agentmods.dev/commands/agentsorg/design-engineering/apply-design-md"><img src="https://agentmods.dev/badge/commands/agentsorg/design-engineering/apply-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/commands/agentsorg/design-engineering/apply-design-md"><img src="https://agentmods.dev/badge/commands/agentsorg/design-engineering/apply-design-md.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 | $0.00036 | $0.00346 |
| Opus 5.5 | $0.00014 | $0.00138 |
| Sonnet 5.5 | $0.00007 | $0.00069 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
apply-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
Apply the design contract
Spawn or emulate the design-md-consumer subagent (agents/design-md-consumer.md).
- Discover the contract, nearest wins: walk up for a
.design/*.design, resolvingextends. Then check forDESIGN.mdat the root,docs/, ordesign/. If both exist,.designis the contract and DESIGN.md is rationale. - Load
skills/design-engineering/references/meta/using-design-file.md(orusing-design-md.md) pluspov.md. - For a
.design, read the normative core before generating:agent.instructions→intent→constraints→policy/decisions→tokens→voice→components. - Output token mappings and apply them to the target UI the user specified. If
integrations.shadcn.enabled, writecss_varsinto the declared CSS file — tokens outrank stale literals. - Tokens and structured rules are normative;
rationaleand DESIGN.md prose are context.
Precedence when they disagree: user prompt → the contract → this skill → model defaults.
If no contract exists, say so and offer to bootstrap one — copy templates/design-engineering.design (this skill's canonical motion and surface defaults) or scaffold a DESIGN.md from spec/design-md-spec.md. Scan adjacent signals first; never invent an untracked system silently.
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 · 19 lines · 36 tokens per session scan A 671ed5895a37
apply-design-md is a command published in the GitHub repository AgentsORG/design-engineering (34 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 346 once invoked, about $0.0001 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 commands, from other repositories
color-palette
Run the full colour workflow — tonal scales, semantic mapping, contrast checks, dark mode, and chart colours — and output a documented palette.
design-screen
Design a complete screen layout from a description or requirements.
responsive-audit
Audit a design's responsive behaviour across breakpoints — layout, touch targets, and content reflow.
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
dark-mode-specialist
Use when dark mode looks wrong. Pure black surfaces, elevation that disappears, brand colours that vibrate against dark, a white flash on load, or a mode toggle that does not persist.
motion-designer
Use when animation feels wrong. Transitions too slow or too bouncy, motion with no purpose, blanket transitions on every property, no reduced-motion support, or animation that drops frames.