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/taste-skills --skill taste-gapgit clone --depth 1 https://github.com/Dragoon0x/taste-skillsWrote 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/taste-skills/taste-gap)<a href="https://agentmods.dev/skills/dragoon0x/taste-skills/taste-gap"><img src="https://agentmods.dev/badge/skills/dragoon0x/taste-skills/taste-gap/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/taste-skills/taste-gap"><img src="https://agentmods.dev/badge/skills/dragoon0x/taste-skills/taste-gap.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 | $0.00060 | $0.00736 |
| Opus 5.5 | $0.00024 | $0.00294 |
| Sonnet 5.5 | $0.00012 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
taste-gap 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taste Gap
The gap between your taste and your skill is not a problem. It's the work.
How to use
/taste-gapApply taste-gap awareness to creative development in this conversation.
Constraints
Understanding the Gap
- MUST recognize the gap as a sign of progress, not failure. You got into design because your taste is good. The gap means your taste is working. The pain means you can see the distance.
- MUST normalize the gap. Every designer who became great went through this. The ones who didn't become great are the ones who quit during it.
- NEVER tell someone the gap doesn't exist or that their work is fine when it isn't. Honest acknowledgment is more helpful than false encouragement.
- SHOULD frame the gap as information: it tells you exactly what to practice next.
Working Through It
- MUST increase volume of output. The gap closes through making, not through consuming more or thinking harder. Make bad work. Make a lot of it. Make it fast.
- MUST lower the stakes. Side projects, daily exercises, fake briefs, style copies. When the work doesn't matter, you take more risks. Risks close the gap faster than caution.
- MUST study the specific delta. Not "my work isn't as good." What specifically isn't as good? The type? The hierarchy? The color? The spacing? Name the gap to close it.
- SHOULD keep a gap journal. Save your work next to the references that show where you want to be. Revisit monthly. The distance should be shrinking.
The Dangerous Phases
- Early gap (months 1-6): You can see quality but can't produce it. Risk: quitting because the frustration is acute.
- Middle gap (months 6-18): Your work is improving but you can see new problems you couldn't before. The gap feels like it's growing. It's not. Your perception is sharpening faster than your execution. Risk: believing you're getting worse.
- Late gap (years 2+): Your work is good. Others think it's great. But you can still see the distance to where you want to be. Risk: perfectionism replacing productivity.
- MUST identify which phase someone is in before giving advice. The advice is different for each.
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 · 51 lines · 60 tokens per session scan A 07871ce1c5ac
taste-gap is a skill published in the GitHub repository Dragoon0x/taste-skills (7 stars, last pushed 8mo ago), licensed MIT. It adds 60 tokens to every session and 736 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 2026-08-31.
Other skills, from other repositories
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
work-with-creators-creator-vetting
Vets creators you have already named from their public pages. Covers the median views of their last 12 to 20 posts (sponsored and organic apart), a read of their comments, how often they post, audience fit with how sure it is, about 12 months of brand-safety checks, rival partnerships and rules for regulated…
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
Accessibility Manual Audit
Teach agents to guide manual accessibility audits for keyboard, screen reader, zoom, reflow, focus, and WCAG 2.2 criteria that scanners miss.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.