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 commands/koolamusic/claudefiles/refinegit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/commands/koolamusic/claudefiles/refine)<a href="https://agentmods.dev/commands/koolamusic/claudefiles/refine"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/refine.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 | $0.00055 | $0.01457 |
| Opus 5 | $0.00028 | $0.00728 |
| Sonnet 5 | $0.00011 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
refine 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 4d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refine specific UX dimensions. Pick the one that needs attention.
First: Use the ux skill for design principles and anti-patterns.
MANDATORY PREPARATION
Gather context: target audience, brand personality, and what's appropriate for this domain. If you can't infer these confidently, STOP and ask via AskUserQuestion.
Pick the focus
$ARGUMENTS:
- copy — Fix unclear UX writing, error messages, labels, instructions
- onboard — Design first-time user experiences, empty states, feature discovery
- motion — Add purposeful animations and micro-interactions
- delight — Add personality, joy, and unexpected touches
- empty — Assess the interface and recommend which focus
Copy
Identify and fix unclear interface text.
Error messages: Explain what went wrong in plain language, suggest how to fix it, don't blame the user. Bad: "Error 403: Forbidden". Good: "You don't have permission to view this page. Contact your admin for access."
Form labels: Specific names, not generic. Show format expectations with examples. Explain why you're asking.
Buttons/CTAs: Describe the action specifically (verb + noun). "Create account" not "Submit". "Save changes" not "OK".
Help text: Add value beyond the label. Answer the implicit question. Keep brief.
Empty states: Explain what will appear, why it's valuable, clear CTA to create first item. Never just "No items."
Success messages: Confirm what happened. Explain what's next. "Settings saved! Changes take effect immediately."
Loading states: Set expectations (how long?), explain what's happening, show progress.
Confirmation dialogs: State the specific action, explain consequences. "Delete 'Project Alpha'? This can't be undone." Buttons: "Delete project" not "Yes."
Principles: Be specific, concise, active voice, human, helpful, consistent. Never: jargon, blame, vagueness, humor for errors, placeholder-only labels.
Onboard
Get users to value as quickly as possible.
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.
- 4d ago First seen · 113 lines · 55 tokens per session scan A 830f28a088c6
refine is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 1,457 once invoked, about $0.0003 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 commands, from other repositories
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
template-ui
Design a Sent template-builder interface.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.
4-generate
Run Stage 4 of the design system skill generation pipeline: parallel skill file generation.
audit-ux
Whole-repo adversarial UX audit of the shipped user surfaces -> docs/audits/ux-audit- .md.