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 agentmods add skills/keyargo/custodian-kernel/design-impeccablenpx 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.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.01546 |
| Opus 5 | $0.00024 | $0.00773 |
| Sonnet 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 6d 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.
- 6d 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 (118 stars, last pushed 14d ago), licensed MIT. It adds 48 tokens to every session and 1,546 once invoked, about $0.0002 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
gnt-check-action
Check a side-effectful action against this organization's approved gnt rules before taking it, and stop on a blocked or needshuman verdict.
dev-standards
Enforces development workflows, quality gates, coding standards, and release processes for the deterministic-agent-control-protocol project. Use when implementing features, fixing bugs, refactoring architecture, adding integrations, updating policies, writing tests, updating documentation, or preparing releases.
openbot-data-access
Governs how the OpenBot browser app reads and writes server data — every request goes through client in app/src/lib/client.ts, every read is a queryOptions factory in app/src/lib/ /queries.ts, every write is a mutationOptions factory in app/src/lib/ /mutations.ts, and components consume them through…
dep-updates
Plan and apply Go dependency updates, including advisory-driven bumps, Trivy/govulncheck validation, and supply-chain review. Use when the user asks to update dependencies, refresh modules for security alerts, or run dependency vulnerability scans.
repro
Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally scaffold a failing regression test that pins it. Use this the moment a bug, defect, crash, 500, wrong count, broken…
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.