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 KeyArgo/custodian-kernel --skill design-impeccablegit clone --depth 1 https://github.com/KeyArgo/custodian-kernelWrote 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/keyargo/custodian-kernel/design-impeccable)<a href="https://agentmods.dev/skills/keyargo/custodian-kernel/design-impeccable"><img src="https://agentmods.dev/badge/skills/keyargo/custodian-kernel/design-impeccable/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/keyargo/custodian-kernel/design-impeccable"><img src="https://agentmods.dev/badge/skills/keyargo/custodian-kernel/design-impeccable.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 Agent Snooping · line 137 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00048 | $0.01546 |
| Opus 5.5 | $0.00019 | $0.00618 |
| Sonnet 5.5 | $0.00010 | $0.00309 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
design-impeccable 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impeccable
Design rules for AI coding agents. Catches the specific tells that mark output as AI-generated.
The 23 commands (overview)
| Command | What it does |
|---|---|
craft |
Full shape-then-build flow with visual iteration |
init |
One-time setup: gather design context, write PRODUCT.md and DESIGN.md |
document |
Generate root DESIGN.md from existing project code |
extract |
Pull reusable components and tokens into the design system |
shape |
Plan UX/UI before writing code |
critique |
UX design review: hierarchy, clarity, emotional resonance |
audit |
Run technical quality checks (a11y, performance, responsive) |
polish |
Final pass, design system alignment, and shipping readiness |
bolder |
Amplify boring designs |
quieter |
Tone down overly bold designs |
distill |
Strip to essence |
harden |
Error handling, i18n, text overflow, edge cases |
onboard |
First-run flows, empty states, activation paths |
animate |
Add purposeful motion |
colorize |
Introduce strategic color |
typeset |
Fix font choices, hierarchy, sizing |
layout |
Fix layout, spacing, visual rhythm |
delight |
Add moments of joy |
overdrive |
Add technically extraordinary effects |
clarify |
Improve unclear UX copy |
adapt |
Adapt for different devices |
optimize |
Performance improvements |
live |
Visual variant mode: iterate on elements in the browser |
44 deterministic detector rules
These are the most common AI-generated UI mistakes. Check for each before shipping.
Typography tells
- Inter for everything — replace with a font that has character (Geist, Outfit, Satoshi, Cabinet Grotesk)
- Only 400 and 700 weights — add 500 and 600 for hierarchy
- Headlines too small — display text should feel heavy
- No letter-spacing on large text — use negative tracking
- System font fallbacks visible — explicitly set the font stack
- Mixed serif/sans usage — pick one family for body, one for display
- Numbers in proportional font in tables — use tabular figures
- All-caps everything — sentence case or italics, not all-caps
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 · 140 lines · 48 tokens per session scan A 9287d0eb7810
design-impeccable is a skill published in the GitHub repository KeyArgo/custodian-kernel (120 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,546 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 2026-08-30.
Other skills, from other repositories
release-gate-loop
A release check that tests a change, reports whether it passes, and can run a limited fix-and-retest cycle. A release is the act of making a software version available.
代码审查员
A code-review agent that examines changes for correctness, security, maintainability, performance, and test coverage.
sofagent-fde
A Chinese-language deployment and knowledge-engineering process for mapping a company's work and turning its business rules into data and constraints for an AI system. It covers business workflows, possible AI tasks, relationships between concepts, and handover.
sofagent-audit
A compliance-audit agent for the DeepAgents and sofagent workflow system.
sofagent
A sofagent skill for FDEs—people who help businesses deploy AI—covering a four-stage diagnosis and the creation of a company-specific agent skill.
fresh-eyes-loop
A repeatable quality-review process using two independent agents: one reviews and verifies, while the other fixes issues. P0 and P1 mean the highest-severity problem levels.