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 lossless-group/lossless-agent-skills --skill maintain-design-mdgit clone --depth 1 https://github.com/lossless-group/lossless-agent-skillsWrote 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/lossless-group/lossless-agent-skills/maintain-design-md)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/maintain-design-md"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/maintain-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/lossless-group/lossless-agent-skills/maintain-design-md"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/maintain-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 | $0.00303 | $0.04451 |
| Opus 5.5 | $0.00121 | $0.01780 |
| Sonnet 5.5 | $0.00061 | $0.00890 |
| Haiku 4.5 | $0.00030 | $0.00445 |
Grade A, and why
maintain-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.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain DESIGN.md
Every Lossless project with a visual surface should have a
DESIGN.mdat its root. It is the agent-readable contract that explains the project's visual identity — colors, typography, spacing, components, behavior under hover/focus/dark/light. Both humans and AI agents read it. When the codebase's CSS custom properties drift away from whatDESIGN.mdsays, fixDESIGN.md.
When to use this skill
- Bootstrapping a new project that needs a
DESIGN.mdfrom scratch — splash, site, plugin landing, fundraise deck - Maintaining an existing
DESIGN.mdwhen the runtime CSS / component vocabulary has evolved past what's documented - Auditing drift — the codebase says one thing (e.g.
--radius-md: 12px), the document says another (e.g.rounded.md: 8px); reconcile - Adding a project-specific off-spec section — like the
imagery:block for thegenerate-consistent-og-imagesskill — and you want to know where it belongs and how spec-compliant consumers will handle it - A sibling skill (
generate-consistent-og-images,theme-system,astro-knots,open-graph-share-seo-geo) needs to read locked design values and they're not inDESIGN.mdyet - The user says: "the agent doesn't know what color we use", "let's write down the design system", "we need a DESIGN.md", "is there a DESIGN.md for this site?", "update the design doc"
The spec
Lossless DESIGN.md files follow Google Stitch's open spec, version alpha (current):
- Reference repo: https://github.com/google-labs-code/design.md
- Full spec: https://github.com/google-labs-code/design.md/blob/main/docs/spec.md
- Examples: the
examples/directory of the spec repo (atmospheric-glass,paws-and-paths,totality-festival) - Lossless reference implementation:
content-farm/splash/DESIGN.md— full canonical example with both standard Stitch sections and an off-specimagery:extension
A DESIGN.md has two parts: YAML frontmatter (machine-readable tokens) and a markdown body (human-readable rationale).
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.
- 1mo ago First seen · 225 lines · 303 tokens per session scan A feeab5c06b70
maintain-design-md is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed today), licensed MIT. It adds 303 tokens to every session and 4,451 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
gsd-ui-phase
Generate UI design contract (UI-SPEC.md) for frontend phases.
visual-acceptance
A visual final-review method for user-interface changes. It checks the rendered result with repeatable screenshots, pixel values, computed styles, and CSS layering checks across themes.
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
design-an-interface
Produce 3+ radically different designs for a module, API, or interface, compare them in prose, and synthesize a recommendation. Use when asked to "design an interface", "shape this API", "design it twice", "explore module boundaries", or when planning a new deep module and the first idea is unlikely to be the best.…
tool-design-sprint-readiness
Pre-sprint diagnostic that determines whether a team should run a Design Sprint now, postpone it, or do prerequisite work first. Produces a Go / Conditional Go / Wait verdict with diagnosis, recommended preconditions, attendee list, customer recruiting plan, and pre-sprint activities. Use when a team is considering…