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 serejaris/personal-corp-os --skill parallel-design-variantsgit clone --depth 1 https://github.com/serejaris/personal-corp-osWrote 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/serejaris/personal-corp-os/parallel-design-variants)<a href="https://agentmods.dev/skills/serejaris/personal-corp-os/parallel-design-variants"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/parallel-design-variants/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/serejaris/personal-corp-os/parallel-design-variants"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/parallel-design-variants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 61 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00091 | $0.01284 |
| Opus 5 | $0.00046 | $0.00642 |
| Sonnet 5 | $0.00018 | $0.00257 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
parallel-design-variants 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 12d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Design Variants
Overview
Generate N genuinely different design directions at once, each built by its own subagent locked to a distinct visual reference, collect them in one gallery, pick winners, then run a second round that mixes the winning styles.
Core principle: divergence comes from reference anchors, not from asking "be creative." Ten subagents told "make a nice hero" produce ten similar heroes. Ten subagents anchored to terminal / broadsheet / brutalist / swiss / zine produce ten different worlds. Same content, different reference → real choice.
When to Use
- You'd otherwise build one design and iterate — but you don't yet know the direction.
- Redesign, landing, hero, thumbnail layout, email, slide system, any visual surface.
- Live/stream or team bake-off where people vote on options.
Not for: a single known direction (just build it), or pixel-level refinement of one chosen design (that's normal iteration).
The Loop
ask how many variants (N)
→ spec issue (constant content + N reference anchors + briefs)
→ N subagents in parallel (blind to each other)
→ gallery index.html (side by side)
→ pick winners (optionally by vote)
→ second round: mix winning styles
Workflow
- Ask how many variants (N) — first, before anything else. Don't silently pick a number; ask the user. Suggest 6–10 as the sweet spot (enough for real divergence, few enough to review side by side) and offer the default, but the count is theirs. Their answer is N for the rest of the flow.
- Write ONE spec issue — it is the orchestration doc, not a throwaway prompt. It contains:
- Constant content: the real data and the required sections every variant must render (identical across all). You compare style, never completeness.
- Result layout:
redesign/index.html(gallery) +redesign/{slug}/index.htmlper direction. Self-contained HTML — inline CSS, vanilla JS, Google Fonts ok, no build step, no framework (so the gallery just opens). - A table of N directions:
slug · name · reference / media-analog. - A shared prompt scaffold (identity, required sections, real data, output files) — every subagent gets the same scaffold + its own brief.
- Per-direction briefs: 2–4 sentences each, naming the reference and its concrete cues (fonts, palette, layout move).
- Pick N divergent anchors (the N the user chose). Each anchor a recognizable, different reference — adjacent styles waste a variant. Starter palette:
What ships with it
2 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.
- 12d ago First seen · 72 lines · 91 tokens per session scan A ba027d236a0e
parallel-design-variants is a skill published in the GitHub repository serejaris/personal-corp-os (225 stars, last pushed 17d ago), licensed MIT. It adds 91 tokens to every session and 1,284 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
architecture-diagram
Generate architecture diagrams as fully editable SVG with native AWS, Azure, and GCP icons for cloud diagrams, or hand-drawn generic icons for everything else. Optionally deliver a self-contained editable draw.io mxGraph companion. Deterministic layout computes zone nesting and orthogonal routing instead of…
concept-to-image
Turn concepts into static HTML visuals exported as PNG or SVG files via HTML/CSS/SVG. Triggers on: "create an image of", "export as PNG", "save as SVG", "concept to image", "screenshot this HTML". NOT for interactive HTML, use static-web-artifacts-builder.
tldraw
Generate hand-drawn whiteboard-style diagrams (.tldr) from natural language and export to PNG/SVG via tldraw-cli, with vision-based self-check and an iterative review loop. Covers flowcharts, sequence diagrams, ERDs, UML sketches, and ML model diagrams. Triggers on: "whiteboard diagram", "sketch this out", "tldraw…
static-web-artifacts-builder
Build self-contained static HTML artifacts opened in a browser: interactive diagrams, dashboards, infographics. Pure HTML5+CSS3+inline SVG, zero toolchain. Triggers on: "interactive HTML", "open in browser", "HTML artifact", "visual dashboard", "HTML infographic". NOT for PNG/SVG output, use concept-to-image.
ux-expert
UX design expert for auditing and redesigning pages, dashboards, and data-dense interfaces via 4-phase collaborative reviews across 8 UX dimensions. Triggers on: "review UX", "audit this page", "redesign the dashboard", "UX review", "improve the layout", "dashboard UX audit", "component recommendations".
chart-clarity
Create, review, and restyle data visualizations using Edward Tufte principles: high data-ink ratio, direct labels, range-frame axes, small multiples, accessible color, responsive charts, and honest comparisons. Triggers on: "create a chart", "style this chart", "review this graph", "Tufte chart", "data visualization"…