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/rapidai/maclaw/impeccablenpx skills add RapidAI/MaClaw --skill impeccablegit clone --depth 1 https://github.com/RapidAI/MaClawWrote 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/rapidai/maclaw/impeccable)<a href="https://agentmods.dev/skills/rapidai/maclaw/impeccable"><img src="https://agentmods.dev/badge/skills/rapidai/maclaw/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 | $0.00189 | $0.04916 |
| Opus 5 | $0.00095 | $0.02458 |
| Sonnet 5 | $0.00038 | $0.00983 |
| Haiku 4.5 | $0.00019 | $0.00492 |
Grade A, and why
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 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files 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.
- agents/impeccable_asset_producer.toml 8.1 KB
- agents/impeccable_manual_edit_applier.toml 6.9 KB
- agents/openai.yaml 236 B
- reference/adapt.md 9.9 KB
- reference/animate.md 10 KB
- reference/audit.md 7.1 KB
- reference/bolder.md 6.4 KB
- reference/brand.md 10 KB
- reference/clarify.md 10 KB
- reference/codex.md 6.8 KB
- reference/colorize.md 13 KB
- reference/craft.md 12 KB
- reference/critique.md 39 KB
- reference/delight.md 9.6 KB
- reference/distill.md 5.6 KB
- reference/document.md 27 KB
- reference/extract.md 3.3 KB
- reference/harden.md 8.4 KB
- reference/init.md 13 KB
- reference/interaction-design.md 6.4 KB
- reference/layout.md 8.5 KB
- reference/live.md 59 KB
- reference/onboard.md 7.6 KB
- reference/optimize.md 7.4 KB
- reference/overdrive.md 8.9 KB
- reference/polish.md 13 KB
- reference/product.md 3.7 KB
- reference/quieter.md 4.8 KB
- reference/shape.md 11 KB
- reference/typeset.md 14 KB
- scripts/command-metadata.json 7.8 KB
- scripts/context-signals.mjs 7.9 KB runs code
- scripts/context.mjs 9.7 KB runs code
- scripts/critique-storage.mjs 8.8 KB runs code
- scripts/detect-csp.mjs 6.6 KB runs code
- scripts/detect.mjs 620 B runs code
- scripts/detector/browser/injected/index.mjs 67 KB runs code
- scripts/detector/cli/main.mjs 9.5 KB runs code
- scripts/detector/detect-antipatterns-browser.js 203 KB runs code
- scripts/detector/detect-antipatterns.mjs 1.6 KB runs code
- scripts/detector/engines/browser/detect-url.mjs 8.6 KB runs code
- scripts/detector/engines/regex/detect-text.mjs 23 KB runs code
- scripts/detector/engines/static-html/css-cascade.mjs 34 KB runs code
- scripts/detector/engines/static-html/detect-html.mjs 8.9 KB runs code
- scripts/detector/engines/visual/screenshot-contrast.mjs 6.4 KB runs code
- scripts/detector/findings.mjs 363 B runs code
- scripts/detector/node/file-system.mjs 6.7 KB runs code
- scripts/detector/profile/profiler.mjs 4.4 KB runs code
- scripts/detector/registry/antipatterns.mjs 17 KB runs code
- scripts/detector/rules/checks.mjs 113 KB runs code
- scripts/detector/shared/color.mjs 4.4 KB runs code
- scripts/detector/shared/constants.mjs 4.1 KB runs code
- scripts/detector/shared/page.mjs 252 B runs code
- scripts/lib/design-parser.mjs 25 KB runs code
- scripts/lib/impeccable-paths.mjs 3.8 KB runs code
- scripts/lib/is-generated.mjs 2.2 KB runs code
- scripts/live-accept.mjs 30 KB runs code
- scripts/live-browser-dom.js 4.2 KB runs code
- scripts/live-browser-session.js 3.2 KB runs code
- scripts/live-browser.js 416 KB runs code
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 · 170 lines · 189 tokens per session scan A e7ec8066610c
impeccable is a skill published in the GitHub repository RapidAI/MaClaw (141 stars, last pushed 4d ago), with no licence file. It adds 189 tokens to every session and 4,916 once invoked, about $0.0009 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
ui-aesthetics
Raise frontend visual judgment for web interfaces with a bias toward refined product-grade composition, precise component craftsmanship, disciplined interaction states, controlled motion, and coherent depth systems. Use when generating, reviewing, or refactoring web UI that feels generic, cluttered, flat, over-styled…
absolute-ui
Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and…
design-system
Dotbot CRT/retro-futuristic design system: tokens, components, patterns, and anti-patterns for the control panel UI.
前端设计师
创建独特、高品质的前端界面，避免千篇一律的 AI 风格。 触发场景: (1) 用户需要创建网页、HTML 页面 (2) 用户需要设计 UI 界面、组件 (3) 用户询问"帮我做个网页"、"设计界面"、"前端开发" (4) 其他 skill 生成 HTML 输出时自动应用 设计原则: 避免 AI 味、追求独特性、注重细节、强调品味.
business-web-design
Generate dynamic, hand-crafted static websites for real businesses (restaurants, clinics, shops, trades, studios) that read as designed by a human studio — never as an AI template. Use this skill for ANY request to create, redesign, or improve a web page, landing, demo, home, subpage, or showcase for a business — "haz…
Eria-a-ui
Use this skill when the user or another AI needs UI/UX design, component architecture, styling, responsive layout, or front-end design. Eria is a feminine AI specialized in clean cute UI/UX design.