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/lenxism/ives/refinement-playbooknpx skills add lenxism/ives --skill refinement-playbookgit clone --depth 1 https://github.com/lenxism/ivesWrote 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/lenxism/ives/refinement-playbook)<a href="https://agentmods.dev/skills/lenxism/ives/refinement-playbook"><img src="https://agentmods.dev/badge/skills/lenxism/ives/refinement-playbook.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 | $0.00104 | $0.01112 |
| Opus 5 | $0.00052 | $0.00556 |
| Sonnet 5 | $0.00021 | $0.00222 |
| Haiku 4.5 | $0.00010 | $0.00111 |
Grade A, and why
refinement-playbook 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refinement Playbook
Each change may seem small on its own, but through deliberate choices to remove redundancy, simplify treatments, and let content speak, the interface transforms.
The Refinement Sequence
Work through these categories in order. Each builds on the previous.
1. Remove Redundancy
Start by eliminating what doesn't need to exist.
- Redundant labels. If the page title says "Analytics," the subtitle "Your analytics dashboard" adds nothing. Remove it.
- Duplicate visual signals. If color indicates state, you don't also need an icon and a label.
- Unnecessary containers. Four separate cards for four sibling metrics create noise. A single consolidated scoreboard reads better.
- Verbose headers. "Edition Performance" → "Performance." "Top Performing Links" → "Top Links."
The test: For every element, ask: "If I removed this, would meaning be lost?" If no, remove it.
2. Simplify Visual Treatments
- Reduce stroke weight — heavy borders add noise. Consider removing strokes entirely if spacing creates sufficient separation.
- Tighten shadow blur radius and y-offset for crisper depth.
- Reserve display typefaces for page titles only. Section headers work better in clean sans-serif.
- Establish a clear typographic scale: 2-3 sizes maximum for body content.
- Use dividers consistently or not at all. Often, spacing alone is sufficient.
3. Tighten Spacing and Proportion
This is where most interfaces feel "off" without people being able to articulate why.
- Balance padding within containers. Too much vertical padding at top creates top-heaviness.
- Reduce gaps between related elements. Labels and values, icons and text should feel tightly coupled.
- Increase gaps between unrelated sections. Make grouping obvious through spacing.
- Equalize gaps between peer sections. Inconsistent spacing between siblings feels uneven.
- Optical alignment. Elements sharing a left edge should actually share it — across nested containers.
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 · 104 lines · 104 tokens per session scan A faa4b32a183d
refinement-playbook is a skill published in the GitHub repository lenxism/ives (5 stars, last pushed 6mo ago), licensed MIT. It adds 104 tokens to every session and 1,112 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
make-resume
中文可编辑简历制作技能:默认基于 ASu 单栏高密度技术简历模板,根据用户经历制作或复刻可编辑 HTML/PDF;用户也可以指定仓库内其他模板、本地 HTML 或参考截图。用户输入“/make-resume”“我要阿酥同款简历”或要求制作、修改、复刻简历文件时使用。.