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 Dragoon0x/everything-design-taste --skill design-mentoringgit clone --depth 1 https://github.com/Dragoon0x/everything-design-tasteWrote 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/dragoon0x/everything-design-taste/design-mentoring)<a href="https://agentmods.dev/skills/dragoon0x/everything-design-taste/design-mentoring"><img src="https://agentmods.dev/badge/skills/dragoon0x/everything-design-taste/design-mentoring/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/dragoon0x/everything-design-taste/design-mentoring"><img src="https://agentmods.dev/badge/skills/dragoon0x/everything-design-taste/design-mentoring.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 | $0.00019 | $0.00309 |
| Opus 5.5 | $0.00008 | $0.00124 |
| Sonnet 5.5 | $0.00004 | $0.00062 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
design-mentoring 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 1mo 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.
What it actually says
Design Mentoring
Mentoring Structure
- Weekly 1:1 (30 min): Current work, blockers, growth
- Portfolio review (monthly): Review recent work deeply
- Skill development (quarterly): Identify growth areas, set goals
Giving Growth Feedback
- Be specific: 'The spacing between these sections creates unclear grouping' not 'The layout needs work'
- Explain why: Connect the feedback to a principle
- Show alternatives: Don't just criticize, demonstrate
- Acknowledge progress: Note improvements from previous feedback
- Separate craft from taste: Craft is learnable (spacing, hierarchy). Taste develops with exposure.
Growth Path
| Level | Focus | Key Skills |
|---|---|---|
| Junior | Execution | Craft, tools, following direction |
| Mid | Problem-solving | Research, strategy, self-direction |
| Senior | Leadership | Vision, mentoring, stakeholder influence |
| Lead | Multiplication | Team building, culture, business impact |
Common Junior Mistakes (address kindly)
- Skipping research and jumping to solutions
- Designing for themselves, not users
- Pixel perfection before direction is right
- Not presenting work well (just sharing screenshots)
- Taking feedback personally
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.
- 1mo ago First seen · 35 lines · 19 tokens per session scan A 6fbc479dd268
design-mentoring is a skill published in the GitHub repository Dragoon0x/everything-design-taste (13 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 309 once invoked, about $0.0001 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.
Other skills, from other repositories
antislop
Anti Slop: Rules for AI Coding Agents. The core filter. Load always to stop generic AI slop.
antislop-human
Human and accessibility skill for antislop. Contrast, keyboard, focus, and states for real people. Includes the contrast checker.
antislop-ui
UI and visual skill for antislop. Use when building or editing any interface: color, layout, components, motion. Load with the core.
Design Resources
This skill provides a curated design reference library for all Maxim design agents. It contains typography scales, color systems, component patterns, animation specs, accessibility checklists, critique frameworks, and the 9-section DESIGN.md standard template.
wcag-guide
Explain WCAG 2.2 criteria, conformance levels and what changed.
wcag3-preview
WCAG 3.0 preview: outcomes, APCA contrast and functional needs.