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 gaia-research/gaia-skill-heaven --skill impeccablegit clone --depth 1 https://github.com/gaia-research/gaia-skill-heavenWrote 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/gaia-research/gaia-skill-heaven/impeccable)<a href="https://agentmods.dev/skills/gaia-research/gaia-skill-heaven/impeccable"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-heaven/impeccable/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/gaia-research/gaia-skill-heaven/impeccable"><img src="https://agentmods.dev/badge/skills/gaia-research/gaia-skill-heaven/impeccable.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 | $0.00189 | $0.02392 |
| Opus 5.5 | $0.00076 | $0.00957 |
| Sonnet 5.5 | $0.00038 | $0.00478 |
| Haiku 4.5 | $0.00019 | $0.00239 |
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 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.
This is a copy
95% identical to impeccable — 41 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill gives you the tools and permission to create design that earns to be called out-of-distribution craft: Whereas before, your design work would have been safe, timid and measured, you now approach every design task as a award-winning design director with impeccable understanding for what makes exceptional design work: production-grade code, peak creativity, a clear POV, deep understanding of the needs of the client and users, and exceptional craft.
Core principles:
- Go all out. No hedging, no shortcuts. The deliverable must be complete (except assets the user must provide).
- Dream big and bold. Distinct, beautiful, outstanding and highly inspiring work.
- Verify in bounded passes, not a loop, and the ceiling covers the whole cycle: screenshots, defect scans, micro-edits, and rebuilds alike. Build fully, inspect once with a batched round (desktop and mobile together on the web; the shipped device classes on a native platform), fix everything it shows in one batch, confirm with at most one more round, and stop polishing. Open-ended self-QA burns the user's money doing worse what the finish handoffs do better.
Setup
- Run
node <skill-base-dir>/scripts/context.mjsonce per session, where<skill-base-dir>is the loaded base directory the runtime reports for this skill; keep cwd at the user's project. That base directory resolves everynode .agents/skills/impeccable/scripts/...command in this skill and its references, and.agents/skills/impeccable/scriptsis the fallback only when the runtime reports no base directory. Pass a named source file or route as--target <path>. It loads PRODUCT.md, DESIGN.md, the matching surface brief, and native-platform guidance when applicable; follow its directives and do not rerun it. - Before acting, load the one playbook that owns the request: the Commands table's reference for an explicit or clearly implied sub-command, or reference/new-work.md for a new surface or replacement visual world. Then inspect the target and at least one representative source of incumbent visual truth (tokens, theme, CSS, component, or asset) before editing.
- After analysis and direction are resolved, load reference/craft-floor.md immediately before editing UI. It carries the quality floor, the absolute bans, and the reflexes no detector catches. Do not load it for planning-only work.
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 9.7 KB
- agents/impeccable_documenter.toml 3.2 KB
- agents/impeccable_finish_reviewer.toml 13 KB
- agents/impeccable_manual_edit_applier.toml 6.9 KB
- agents/openai.yaml 235 B
- reference/adapt.md 10 KB
- reference/adapt.native.md 3.8 KB
- reference/android.md 4.0 KB
- reference/animate.md 5.1 KB
- reference/audit.md 7.7 KB
- reference/audit.native.md 8.2 KB
- reference/bolder.md 3.5 KB
- reference/clarify.md 4.5 KB
- reference/colorize.md 4.4 KB
- reference/craft-floor.md 5.4 KB
- reference/craft.md 555 B
- reference/critique.md 45 KB
- reference/degraded/asset-producer.md 9.9 KB
- reference/degraded/documenter.md 3.3 KB
- reference/degraded/finish-reviewer.md 13 KB
- reference/degraded/manual-edit-applier.md 7.0 KB
- reference/delight.md 3.6 KB
- reference/distill.md 5.6 KB
- reference/doctor.md 5.3 KB
- reference/document.md 27 KB
- reference/extract.md 3.4 KB
- reference/harden.md 8.3 KB
- reference/hooks.md 12 KB
- reference/init.md 11 KB
- reference/ios.md 3.7 KB
- reference/layout.md 5.0 KB
- reference/live-setup.md 7.2 KB
- reference/live.md 35 KB
- reference/new-work.md 41 KB
- reference/onboard.md 7.6 KB
- reference/operate.md 4.0 KB
- reference/optimize.md 7.4 KB
- reference/overdrive.md 9.0 KB
- reference/polish.md 5.5 KB
- reference/quieter.md 4.8 KB
- reference/routing.md 2.8 KB
- reference/shape.md 3.5 KB
- reference/typeset.md 5.1 KB
- reference/visualize.md 14 KB
- scripts/command-metadata.json 7.7 KB
- scripts/concept-seed.mjs 39 KB runs code
- scripts/context-signals.mjs 14 KB runs code
- scripts/context.mjs 63 KB runs code
- scripts/critique-storage.mjs 8.3 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 82 KB runs code
- scripts/detector/cli/main.mjs 18 KB runs code
- scripts/detector/design-system.mjs 40 KB runs code
- scripts/detector/detect-antipatterns-browser.js 381 KB runs code
- scripts/detector/detect-antipatterns.mjs 1.8 KB runs code
- scripts/detector/engines/browser/detect-url.mjs 14 KB runs code
- scripts/detector/engines/regex/detect-text.mjs 47 KB runs code
- scripts/detector/engines/static-html/css-cascade.mjs 43 KB runs code
- scripts/detector/engines/static-html/detect-html.mjs 13 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.
- 1mo ago First seen · 80 lines · 189 tokens per session scan A 9d124382509e
impeccable is a skill published in the GitHub repository gaia-research/gaia-skill-heaven (4 stars, last pushed today), licensed MIT. It adds 189 tokens to every session and 2,392 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to impeccable, differing in 41 lines, and is treated as a copy.
Other skills, from other repositories
shiny-bslib-theming
Advanced theming for Shiny apps using bslib and Bootstrap 5. Use when customizing app appearance with bstheme(), Bootswatch themes, custom colors, typography, brand.yml integration, Bootstrap Sass variables, custom Sass/CSS rules, dark mode and color modes, dynamic theme switching, real-time theming, theme inspection…
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
design-system
Builds and maintains the design system a product is assembled from — tokens for color, type, spacing and elevation, component contracts, and the rules that keep them coherent as the product grows. Use this when starting a new interface, when screens have drifted apart visually, when the same component exists three…
interface-redesign
Upgrades an existing interface to a higher standard without rebuilding it — auditing what is there, identifying what reads as generic or unfinished, and sequencing changes by impact. Use this when a product works but looks dated or default, when a redesign is being considered, when deciding whether to restyle or…
design-blueprint
Run a complete design workflow -- from establishing context through four progressive design levels (Capabilities, Components, Interactions, Contracts) to an approved blueprint. Composes knowledge-priming, context-anchoring, learning-harvest, collaborative-judgment, design-first, architecture, and domain-driven-design…