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 OKHP3/skillz --skill okhp3-replit-design-pipelinegit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/okhp3-replit-design-pipeline)<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-replit-design-pipeline"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-replit-design-pipeline/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/okhp3/skillz/okhp3-replit-design-pipeline"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-replit-design-pipeline.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 | $0.00135 | $0.02579 |
| Opus 5 | $0.00068 | $0.01290 |
| Sonnet 5 | $0.00027 | $0.00516 |
| Haiku 4.5 | $0.00014 | $0.00258 |
Grade A, and why
okhp3-replit-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 7d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okhp3-replit-design-pipeline
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Replit's design canvas exposes five interlocking skills: mockup-sandbox, mockup-extract, mockup-graduate, design-exploration, and the design (DESIGN subagent) skill. None of them explains the full loop as a decision tree. This skill does.
Scope
| In scope | Out of scope |
|---|---|
| Decision tree: extract vs. build from scratch | Canvas callback schemas — read the canvas skill |
| Full pipeline narration: extract → sandbox → variant → graduate | Sandbox setup and URL patterns — read mockup-sandbox |
| DESIGN subagent brief anatomy | Import tracing during extraction — read mockup-extract |
| Variant labelling on canvas | Production wiring — read mockup-graduate |
| Graduation decision gate | Launching subagents — read the design skill |
The decision tree: start here
User asks to improve / redesign / create variants / show options
↓
Does the component already exist in the main app codebase?
│
YES ───┤ NO
↓ ↓
EXTRACT first BUILD from scratch
(mockup-extract) (mockup-sandbox + DESIGN subagent)
then iterate ↓
│ Is this a net-new component
↓ the user described, or one
Proceed to the agent is inventing?
VARIANT phase │
Both → Build from scratch,
then proceed to VARIANT phase
The golden rule: if the component exists in the codebase, extract it. Never rebuild from memory. You will get dimensions, colours, spacing, opacity values, and font sizes wrong. The real source code has the correct values.
Phase 1 — Extract (when component already exists)
Read the mockup-extract skill (read .local/skills/mockup-extract/SKILL.md) for the full process. The high-level steps are:
What ships with it
3 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.
- 7d ago First seen · 236 lines · 135 tokens per session scan A 997786ca1fb5
okhp3-replit-design-pipeline is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 2,579 once invoked, about $0.0007 per session on Opus 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 2026-09-05.
Other skills, from other repositories
frontend-design
A front-end coding tool for building distinctive web pages and interface components. It focuses on unusual layouts, visual styling, animations, and production-ready code rather than generic-looking screens.
web-design-analyzer
A web-design analysis helper that extracts colours, typography, and component patterns from a webpage screenshot, then produces structured design-system data and a coding prompt.
shiny-bslib-theming
Advanced theming for Shiny apps using bslib and Bootstrap 5. Use when customizing app appearance with bstheme(), Bootswatch themes, custom colors, typography, brand.yml integration, Bootstrap Sass variables, custom Sass/CSS rules, dark mode and color modes, dynamic theme switching, real-time theming, theme inspection…
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…
web-ui-best-practices
Signs of taste in web UI. Use when building or reviewing web interfaces, dashboards, SaaS apps, or internal tools.