Privacy choices: we'd like to measure visits anonymously (our own cookie-free counter plus Google Analytics, which sets its own cookies; no ads) and load Beehiiv's newsletter sign-up, which may set its own cookies. Nothing optional runs until you choose. Privacy policy

AgentScout / coding / Impeccable
codingOpen sourceNewAdded Nov 9, 2026

Impeccable logoImpeccable

No ratings yet★ Rate this tool

Impeccable gives coding agents a design vocabulary: install it into a project and steer with commands such as polish and bolder, review with critique and audit, and catch typical AI-generated design clichés before they ship; works with Claude Code, Cursor, Codex CLI, Copilot, Gemini CLI and more.

Updated

✨ Try AgentScout's free AI image generator →

Good for: writing code, coding in the terminal

Use cases

Get featured

About Impeccable

Impeccable is listed in our coding category and is aimed at builders. Impeccable gives coding agents a design vocabulary: install it into a project and steer with commands such as polish and bolder, review with critique and audit, and catch typical AI-generated design clichés before they ship; works with Claude Code, Cursor, Codex CLI, Copilot, Gemini CLI and more. Pricing, as the maker states it: Open source. Maturity: Mature. We last checked the official link on 2026-11-09.

What is Impeccable?

Impeccable is an Apache-2.0 design vocabulary for coding agents. From the project root, npx impeccable install detects the coding tool. You then run /impeccable init (or $impeccable init on Codex), which writes PRODUCT.md. Later commands read that file. The README lists 24 commands in groups: steer (bolder, quieter, distill, and others), review (critique and audit), finish (polish, harden, clarify), live iteration, and setup (shape, init, document, extract). craft is a deprecated alias.

A detector of 62 deterministic rules flags common generated-UI patterns. The README says it uses no LLM and no API key. It can run as an agent hook, as npx impeccable detect on a directory or a URL, or as a Chrome extension. Live mode opens a local dev server overlay and writes an accepted variant back to source. The README says live mode is for a local checkout, and that Apply can fall back to the codex or claude CLI with approvals and sandboxing off unless you set IMPECCABLE_LIVE_COPY_AGENT.

Sources: github.com/pbakaus/impeccable, github.com/pbakaus/impeccable/blob/main/README.md, impeccable.style and our directory listing, checked 2026-11-09.

Who is Impeccable for?

People who already have a UI in a repo and want a coding agent to restyle, review or audit one section at a time, with a detector that does not call a model.

Pros and cons

Pros

  • The detector is deterministic. The README says it does not call an LLM or need an API key.
  • Commands take a target, such as the pricing cards, instead of restyling the whole product at once.
  • The same detector runs in the agent, in CI, and in a Chrome extension.

Cons

  • Live mode's Apply path can launch codex or claude with sandboxing and approvals off if no chat session has polled in the last minute. The README says to set IMPECCABLE_LIVE_COPY_AGENT=chat or off to change that.
  • The README says not to inject live mode into a deployed site or weaken a production content-security policy for it.
  • In Claude Code, installed command hooks run even when you deny the model's own commands, so the first edit can download the engine.
  • Codex, Grok Build and Hermes Agent each need an extra trust step before the hook runs. The README lists those steps.

Setup

  1. From the project root, run npx impeccable install. The installer asks whether this project or a global install, and offers the design hook where the tool supports one.
  2. Reload the coding tool, then run /impeccable init. On Codex, use $impeccable init. That writes PRODUCT.md.
  3. In Codex, open /hooks and approve the project hook. In Grok Build, run /hooks-trust or launch with --trust. In Hermes Agent, run hermes plugins enable impeccable-design-hook once.
  4. Point a command at one target, for example /impeccable critique the pricing cards. Run npx impeccable detect on src or on a local URL when you want the detector without an agent.

Impeccable at a glance

  • Open source: Yes (Apache License 2.0)
  • GitHub: pbakaus/impeccable · 106,611 stars (as of Nov 9, 2026)

Key features

  • npx impeccable install, then /impeccable init to write PRODUCT.md
  • 24 commands, including critique, audit, polish, live, document and extract
  • 62-rule detector with no LLM and no API key, plus a Chrome extension
  • Live mode for Vite, Next, SvelteKit, Astro, Nuxt and plain HTML
  • Apache-2.0. Docs at impeccable.style/docs

Impeccable alternatives

Similar coding tools: opencode, Ponytail, Claude Code, CC Switch, UI UX Pro Max. Browse all coding tools →

Impeccable FAQ

What is Impeccable?

Impeccable is an Apache-2.0 design vocabulary for coding agents. From the project root, npx impeccable install detects the coding tool. You then run /impeccable init (or $impeccable init on Codex), which writes PRODUCT.md. Later commands read that file. The README lists 24 commands in groups: steer (bolder, quieter, distill, and others), review (critique and audit), finish (polish, harden, clarify), live iteration, and setup (shape, init, document, extract). craft is a deprecated alias.

Who is Impeccable for?

People who already have a UI in a repo and want a coding agent to restyle, review or audit one section at a time, with a detector that does not call a model.

Is Impeccable free?

Impeccable's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.

Is Impeccable open source?

Yes. Impeccable is released under the Apache License 2.0, according to its GitHub repository.

What are the pros and cons of Impeccable?

Pros: The detector is deterministic. The README says it does not call an LLM or need an API key., Commands take a target, such as the pricing cards, instead of restyling the whole product at once., The same detector runs in the agent, in CI, and in a Chrome extension. Cons: Live mode's Apply path can launch codex or claude with sandboxing and approvals off if no chat session has polled in the last minute. The README says to set IMPECCABLE_LIVE_COPY_AGENT=chat or off to change that., The README says not to inject live mode into a deployed site or weaken a production content-security policy for it., In Claude Code, installed command hooks run even when you deny the model's own commands, so the first edit can download the engine., Codex, Grok Build and Hermes Agent each need an extra trust step before the hook runs. The README lists those steps.

How do I set up Impeccable?

1. From the project root, run npx impeccable install. The installer asks whether this project or a global install, and offers the design hook where the tool supports one. 2. Reload the coding tool, then run /impeccable init. On Codex, use $impeccable init. That writes PRODUCT.md. 3. In Codex, open /hooks and approve the project hook. In Grok Build, run /hooks-trust or launch with --trust. In Hermes Agent, run hermes plugins enable impeccable-design-hook once. 4. Point a command at one target, for example /impeccable critique the pricing cards. Run npx impeccable detect on src or on a local URL when you want the detector without an agent.

What are alternatives to Impeccable?

Similar tools include Understand-Anything, Agentic Awesome Skills, CloudCLI, HTML Anything, GSD Core and Sphinx.

Impeccable ratings and reviews

No ratings yet. Be the first to review Impeccable.

Be the first to rate Impeccable: tap 1 to 5 stars below. A written review is optional.

Your rating of Impeccable

Star ratings count right away; written reviews appear after a quick check. One rating per tool per visitor. Reviews are from site visitors, not verified users. How reviews work

Impeccable alternatives

Other coding tools in our directory. See all coding tools →

Understand-Anything logo

Understand-Anything

Turns any codebase, knowledge base or docs folder into an interactive knowledge graph you can explore and question, working inside Claude Code, Codex, Cursor, Copilot and Gemini CLI.

Agentic Awesome Skills logo

Agentic Awesome Skills

Agentic Awesome Skills, formerly Antigravity Awesome Skills, is a library of more than 2,900 installable SKILL.md playbooks for Claude Code, Codex, Cursor, Gemini CLI and other coding agents, with AAS Core, a tool that lets Codex or Claude search the full local catalog, record the skills it picks and preview a plan before changing your project; the code is MIT and imported skills keep their own licences.

CloudCLI logo

CloudCLI

A web and mobile interface for Claude Code, Codex and Gemini CLI, so you can run and steer coding sessions from a browser or phone. Self-host free or use the hosted CloudCLI service.

HTML Anything logo

HTML Anything

An agentic HTML editor from the Open Design team. Your local coding-agent CLI (Claude Code, Cursor, Codex, Gemini and others) writes HTML decks, posters, reports and prototypes from 75 skills, shows them in a sandboxed preview, and exports in one click. No API key is needed.

GSD Core logo

GSD Core

GSD Core is a spec-driven development and context-engineering framework that runs Claude Code, Codex, Cursor, Copilot and other coding agents through a discuss, plan, execute, verify and ship loop, doing heavy research and execution in fresh-context subagents to avoid context rot.

Sphinx logo

Sphinx

Open-source Git hook for agent-assisted coding: before code your agent wrote is pushed to a protected branch, it reads the diff and quizzes you on what the change actually does when things go wrong, and only lets the push through once you answer correctly. Works with Claude Code, Codex, Cursor and OpenCode.

Get your badge

Built Impeccable? Optional. Showing this badge does not change your rank or earn a Featured spot. It links to this page. About badges

Listed on AgentScout (light)