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 lugassawan/swe-workbench --skill principle-product-designgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/principle-product-design)<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/principle-product-design"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/principle-product-design/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/lugassawan/swe-workbench/principle-product-design"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/principle-product-design.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 | $0.00081 | $0.02231 |
| Opus 5.5 | $0.00032 | $0.00892 |
| Sonnet 5.5 | $0.00016 | $0.00446 |
| Haiku 4.5 | $0.00008 | $0.00223 |
Grade A, and why
principle-product-design 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 2mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Design Principles
Usability Heuristics (Nielsen's 10)
Every user-facing component must satisfy these. Violations block progress.
| Heuristic | Rule | Common Violation |
|---|---|---|
| Visibility of system status | Users always know what's happening | No loading indicator during async operations; silent failures with no feedback |
| Match between system and real world | Use language and concepts users know | Developer jargon in UI labels ("null", "undefined", "404"); unfamiliar abbreviations |
| User control and freedom | Provide undo, cancel, and escape routes | Destructive action with no confirmation; no way to cancel an in-progress operation |
| Consistency and standards | Same action, same result, everywhere | Button styles that vary across views; inconsistent terminology for the same concept |
| Error prevention | Prevent errors before they happen | Allowing invalid input submission; no constraints on date ranges or numeric fields |
| Recognition over recall | Show options, don't force memorization | Hidden navigation requiring memorized paths; no search/filter on long lists |
| Flexibility and efficiency | Support both novice and expert users | No keyboard shortcuts for power users; no progressive disclosure for complex forms |
| Aesthetic and minimalist design | Every element earns its place | Cluttered layouts with competing visual weights; information overload on a single view |
| Error recovery | Clear error messages with actionable next steps | "Something went wrong" with no guidance; error messages using technical stack traces |
| Help and documentation | Contextual help where users need it | No tooltips on ambiguous icons; no onboarding for complex features |
Visual Hierarchy
Users scan, they don't read. Guide their attention.
| Principle | Rule | Common Violation |
|---|---|---|
| Size communicates importance | Primary content largest, secondary smaller, tertiary smallest | All text same size; critical numbers not emphasized |
| Weight directs attention | Bold for key data, regular for supporting content | Everything bold (nothing stands out) or everything light (nothing anchors) |
| Color creates meaning | Semantic colors for states (profit/loss, success/error), muted for secondary | Arbitrary color usage; profit shown in red (wrong cultural mapping) |
| Spacing creates grouping | Related items closer together, unrelated items further apart | Uniform spacing everywhere; no visual relationship between elements |
| Alignment creates order | Consistent alignment grid; numbers right-aligned in tables | Mixed alignment; numbers left-aligned making comparison impossible |
| Whitespace prevents overload | Generous padding around content blocks; breathing room between sections | Cramped layouts; every pixel filled with content |
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.
- 2mo ago First seen · 145 lines · 81 tokens per session scan A 07016a69c513
principle-product-design is a skill published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed 7d ago), licensed MIT. It adds 81 tokens to every session and 2,231 once invoked, about $0.0003 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 2026-09-03.
principle-product-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| principle-product-designlugassawan/swe-workbench | Skill | 3 | 7d ago | MIT | A | 81 | Claude Code |
| modern-cssccheney/robust-skills | Skill | 61 | 1mo ago | MIT | A | 38 | Claude Code, Codex |
| designlang-tokensManavarya09/design-extract | Skill | 5.1k | yesterday | MIT | A | 30 | Claude Code |
| scroll-craftnateherkai/scroll-craft | Skill | 5.0k | 1mo ago | MIT | A | 177 | Claude Code |
| refactoring-uiwondelai/skills | Skill | 2.7k | today | MIT | A | 132 | Claude Code, Codex |
| shiny-bslib-themingposit-dev/skills | Skill | 565 | yesterday | MIT | A | 87 | Claude Code |
| interface-redesigncbrock84/headcount | Skill | 2.6k | 26d ago | MIT | A | 77 | Claude Code |