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 evoelsewhere/evoflux --skill design-blueprintgit clone --depth 1 https://github.com/evoelsewhere/evofluxWrote 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/evoelsewhere/evoflux/design-blueprint)<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/design-blueprint"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/design-blueprint/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/evoelsewhere/evoflux/design-blueprint"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/design-blueprint.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 | $0.00128 | $0.03363 |
| Opus 5.5 | $0.00051 | $0.01345 |
| Sonnet 5.5 | $0.00026 | $0.00673 |
| Haiku 4.5 | $0.00013 | $0.00336 |
Grade A, and why
design-blueprint 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 22d 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.
This is a copy
92% identical to design-blueprint — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Blueprint
Act as a design director, not a code generator. The job on this turn is a blueprint — a structured design specification the user (or a downstream implementer) can execute against. Code comes later, or from another skill. Blueprints come first.
Why: AI-generated designs collapse to a recognizable "slop" median — same gradient hero, same card grid, same rounded 16px, same emoji-bullet feature list — because the model renders pixels before it has a point of view. Forcing a spec first is the difference between "a designer thought about this" and "an autocomplete produced this."
The six-layer model, compressed
The full framework has six layers (Instructions / Taste / Constraints / Feedback / Memory / Orchestration). A single blueprint turn operates three explicitly and inherits the others:
- Taste: produce a
DESIGN.md— a persistent, brand-side spec - Constraints: check output against the anti-slop patterns
- Feedback: record a Decision Trace for every non-obvious choice
Read references/six-layer-model.md only if the user asks about the framework itself, or is auditing an existing design system.
Workflow
Follow these moves in order. Each has a reason; understand the reason and adapt the move to the situation instead of following it robotically.
Move 0 — Reuse before regenerate
Check whether a DESIGN.md already exists for this brand or project (in the working directory or wherever the user points). If one exists:
- Read it and treat it as the Taste layer. Skip Move 3, or emit only a short delta — the sections this artifact forces you to extend or amend, with a Decision Trace entry per amendment.
- Continue with Moves 1, 2, 4, 5, executing inside the existing spec.
Why: A DESIGN.md compounds across artifacts. Regenerating it every turn destroys that and drifts the brand. An existing spec, even a mediocre one, beats a fresh contradictory one.
Move 1 — Embody
Choose the one designer identity that best fits the artifact and state it in one line at the top of the response:
What ships with it
7 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.
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.
- 22d ago Changed · -4 lines · +39 tokens per session 04a550e67264
- 1mo ago First seen · 188 lines · 89 tokens per session scan A 8f4f3194f896
design-blueprint is a skill published in the GitHub repository evoelsewhere/evoflux (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 128 tokens to every session and 3,363 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to design-blueprint, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
visualize
Create visualizations and interactive tools directly in conversation. Use when asked to show how something works, make simulators or labs, maps, plots, charts or graphs, comparisons, UI mockups, scenarios, adjustable inputs, and exploration beyond regular text.
doc-typeset
A document formatter that turns text and design settings into complete, styled HTML. It includes templates for contracts, academic papers, official documents, business reports, meeting notes, research reports, and annual reports.
format-extract
A low-level tool that converts a Word document (.docx) into semantic HTML and extracts embedded images. It also reports on the quality of the resulting HTML conversion.
component-instance
Instructions for creating and changing instances of reusable components. A component is a shared design element, such as a button or card, that can be reused with different text or settings.
html-review
An automated checker for HTML documents that tests structure, styling rules, typography, document tone, and decorative elements, then produces a structured report.
design-variables
Bind/unbind design variables (tokens) on node props with $: : or $ ; create via applyvariables; switch node variable modes via batchedit variableModes.