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 2233admin/design-pipeline --skill skillgit clone --depth 1 https://github.com/2233admin/design-pipelineWrote 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/2233admin/design-pipeline/skill)<a href="https://agentmods.dev/skills/2233admin/design-pipeline/skill"><img src="https://agentmods.dev/badge/skills/2233admin/design-pipeline/skill/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/2233admin/design-pipeline/skill"><img src="https://agentmods.dev/badge/skills/2233admin/design-pipeline/skill.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 | $0.00062 | $0.02524 |
| Opus 5.5 | $0.00025 | $0.01010 |
| Sonnet 5.5 | $0.00012 | $0.00505 |
| Haiku 4.5 | $0.00006 | $0.00252 |
Grade A, and why
design-pipeline 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 today.
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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-pipeline
Use this entry for the current task only. Resolve <skill-root> from this loaded SKILL.md path.
The CLI is node "<skill-root>/scripts/designer-pipeline.cjs" (below: designer-pipeline). Run
it from the user's project, or pass --root <project> for project files. Skill scripts and
resources stay relative to <skill-root> regardless of the working directory.
Route the task
Pick one row, open what it names, and open nothing else until the task needs it.
| The task | Start here | Then |
|---|---|---|
| A complete deliverable (UI, web page, film, edit) | designer-pipeline next --project-root <project> |
Follow next |
| The user gave a reference page or screenshot to follow | designer-pipeline next --project-root <project> --deliverable web|ui --mode replicate |
Follow next |
| One supporting job: drawing, image placement, text fitting, comparison, motion maps | tools/README.md |
one selected guide → its implementation/example |
| Workflow stages, UI, references, implementation and review | references/stages.md |
the stage the task is in |
| New website, redesign, visual critique, style, image-to-code, brand board | references/taste-skill.md |
the selected original source |
| No direction yet: style library with rendered specimens, three-direction method, brand-asset protocol, critique guide | references/design-direction-library.md |
the style entry or handbook it names (reference only) |
| The brief names a real brand or product (logo, colours, product facts) | references/brand-facts.md |
DESIGN.md Product Context and design-system/tokens.json |
| CSS authoring or review in any stack | references/good-css.md |
its matched source entries |
| UI polish, accessibility, motion principles, shadcn/ui, browser driving | references/ui-craft-sources.md |
a source only when a rule needs it |
| Web treatment, section briefs, review rules W1-W7 | references/web-direction.md |
references/workflow-web.md |
| Animation decisions | references/animation-thinking.md |
see Animation |
| Film direction, storyboards and runtime | references/product-film-direction.md |
see Film and edit |
| Reference analysis, reconstruction, scene/runtime contracts | references/reference-spec.md |
references/reconstruction-spec.md, references/scene-runtime-spec.md |
| Captured runtime review and developer handoff | references/runtime-review.md |
its schemas |
| Improving a design prompt or skill instruction offline | references/gepa.md |
frozen cases and reviewable candidates |
| Installation, upgrade and skill location | references/installation.md |
|
| Route, CLI, gate and receipt contracts | references/pipeline-reference.md |
designer-pipeline --help |
What ships with it
60 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.
- adapters/agent-browser.cjs 8.8 KB runs code
- adapters/astryx-provider.mjs 7.8 KB runs code
- adapters/playwright.cjs 2.7 KB runs code
- evals/evals.json 8.3 KB
- evals/film/film-benchmark.json 2.7 KB
- evals/film/README.md 2.7 KB
- evals/film/slideshow.storyboard.json 3.7 KB
- references/3d-spec.md 2.1 KB
- references/adaptation-contract.schema.json 8.3 KB
- references/adaptation.md 8.6 KB
- references/adapter-intake.schema.json 737 B
- references/adapter-registry.json 17 KB
- references/adapter-registry.schema.json 4.5 KB
- references/agent-interface.md 3.9 KB
- references/ai-interaction-patterns.md 4.3 KB
- references/animation-opportunity-and-review.md 8.4 KB
- references/animation-thinking.md 11 KB
- references/anti-slop-evidence.schema.json 1.8 KB
- references/anti-slop-review.md 4.2 KB
- references/anti-slop-review.schema.json 891 B
- references/anti-slop-rubric.json 8.4 KB
- references/anti-slop-rubric.schema.json 3.7 KB
- references/art-motion.md 5.7 KB
- references/art-motion/grammars/t1_3b1b.md 12 KB
- references/art-motion/grammars/t2_keynote_ui.md 11 KB
- references/art-motion/grammars/t3_finance_chart.md 11 KB
- references/art-motion/grammars/y1_kurzgesagt.md 14 KB
- references/art-motion/grammars/y2_vox.md 13 KB
- references/art-motion/grammars/y3_whiteboard.md 13 KB
- references/art-motion/grammars/y4_storytime.md 17 KB
- references/art-motion/grammars/y5_kinetic_type.md 16 KB
- references/art-motion/grammars/y6_presenter_explainer.md 2.0 KB
- references/art-motion/methods/01-reference-breakdown.md 4.8 KB
- references/art-motion/methods/02-mechanisms.md 4.7 KB
- references/art-motion/methods/03-first-frame-routes.md 4.3 KB
- references/art-motion/methods/04-code-drawing.md 11 KB
- references/art-motion/methods/05-rhythm-and-score.md 1.6 KB
- references/art-motion/methods/06-speech-driven-shorts.md 2.7 KB
- references/art-motion/methods/07-proven-practice.md 20 KB
- references/art-motion/methods/08-style-authoring.md 5.6 KB
- references/art-motion/methods/09-clip-grammar.md 42 KB
- references/art-motion/methods/10-characters.md 3.3 KB
- references/art-motion/methods/11-long-scroll-films.md 4.5 KB
- references/art-motion/methods/12-full-film-iteration.md 2.3 KB
- references/art-motion/methods/13-voice-and-cloning.md 827 B
- references/art-motion/methods/era-scene-spec.md 4.5 KB
- references/art-motion/methods/images.md 3.5 KB
- references/art-motion/methods/voice-api.md 5.5 KB
- references/art-motion/methods/voice-configuration.md 4.6 KB
- references/art-motion/styles/01_cave.md 7.0 KB
- references/art-motion/styles/02_egypt.md 8.8 KB
- references/art-motion/styles/03_greek.md 8.7 KB
- references/art-motion/styles/04_roman.md 12 KB
- references/art-motion/styles/05_gothic.md 4.1 KB
- references/art-motion/styles/06_renaissance.md 4.0 KB
- references/art-motion/styles/08_impressionism.md 4.1 KB
- references/art-motion/styles/09_postimp.md 1.5 KB
- references/art-motion/styles/10_nouveau.md 5.0 KB
- references/art-motion/styles/11_cubism.md 5.3 KB
- references/art-motion/styles/12_bauhaus.md 4.4 KB
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.
- today Changed · +39 lines d6361e167cee
- 5d ago Changed · +8 lines c2fb1f7ad6cd
- 6d ago Changed · +7 lines 06e65375fe70
- 7d ago Changed · +3 lines 67a2d871807d
- 8d ago Changed · +9 lines 2e84fdcb28f3
- 9d ago Changed · +1 lines 4126a6d38d4f
- 10d ago Changed · +15 lines 1342a2d60187
- 13d ago Changed · +4 lines · -29 tokens per session 984ba0ae1184
- 21d ago Changed · -1,125 lines · +21 tokens per session 9801bf5f0e40
- 1mo ago First seen · 1,199 lines · 70 tokens per session scan A 438e5b83eadb
design-pipeline is a skill published in the GitHub repository 2233admin/design-pipeline (12 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 2,524 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 2026-08-31.
Other skills, from other repositories
accessibility-per-component
Audit one design system component's accessibility against WCAG 2.2 AA: keyboard, screen reader, contrast, focus, ARIA, target size. Trigger: a11y audit, is this accessible, WCAG check, screen reader support, keyboard navigation check. Not for page- or product-wide audits.
figma-variable-audit
Audit Figma variable collections: tier mapping, naming, alias chains, modes, orphans; can fix in place with Figma Console MCP. Triggers: audit my Figma variables, review variable collections, Figma variable health. For token files in code use token-audit.
schema-validator
Validate token files structurally against DTCG 2025.10 (including resolvers), Style Dictionary 3 to 5 or Tokens Studio: parse errors, $type/$value, name rules, broken or circular aliases. Trigger: validate token JSON, DTCG compliance, are my token files valid. Naming or architecture: token-audit.
change-communication
Write release notes, a migration guide and a team announcement for a design system change that is already decided, scaled to its impact. Triggers: release notes, announce this change, tell teams about a breaking change. Semver call: version-bump-advisor. Deprecation plan: deprecation-process.
onboarding
Onboarding guide for a designer or engineer joining a team that uses the design system, grounded in the repo and Figma library rather than a template. Triggers: onboard a new designer, onboard a new engineer, getting-started guide, first week with the system, developer or designer onboarding.
use-design-md
Apply a Korean brand's published DESIGN.md from the ko-design-md catalog (getdesign.kr) — colors, typography, spacing, radius, components, do's & don'ts — to the UI you are building in the CURRENT project. Use this skill whenever the user wants UI built or restyled in the style of a catalogued Korean service — "토스…