iterative-polish-autoloop

iterative-polish-autoloop is a skill for Claude Code from vindm/dotclaude. It costs 92 tokens per session (2,198 once invoked), scanned A, original, MIT.

An iterative review process for improving a multi-screen product flow one change at a time. It captures each state, checks the interface and backend results, and repeats the cycle.

In plain words
What is it for?
Use it to test a complete flow from a clean starting state, grade its screens, apply the highest-value fix, and verify the result again.
Why use it?
It helps find visual problems, broken states, and differences between what the interface says and what the backend actually does.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the dotclaude-design plugin — 5 skills, 7 agents shipped together

Good fit Use it to test a complete flow from a clean starting state…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vindm/dotclaude/iterative-polish-autoloop
Install

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.

Any agent
npx skills add vindm/dotclaude --skill iterative-polish-autoloop
Clone the repo
git clone --depth 1 https://github.com/vindm/dotclaude

Made for: Claude Code.

Or install dotclaude-design, the plugin that ships this one along with the rest of its 5 skills, 7 agents.

Wrote 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.

agentmods badge for iterative-polish-autoloop

README.md
[![agentmods](https://agentmods.dev/badge/skills/vindm/dotclaude/iterative-polish-autoloop.svg)](https://agentmods.dev/skills/vindm/dotclaude/iterative-polish-autoloop)
Your own site
<a href="https://agentmods.dev/skills/vindm/dotclaude/iterative-polish-autoloop"><img src="https://agentmods.dev/badge/skills/vindm/dotclaude/iterative-polish-autoloop.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.02198
Opus 5 $0.00046 $0.01099
Sonnet 5 $0.00018 $0.00440
Haiku 4.5 $0.00009 $0.00220

Measured 6d ago against content hash d5253cd2614b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

iterative-polish-autoloop 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 6d 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.

plugins/design/skills/iterative-polish-autoloop/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iterative polish autoloop

A single audit produces a verdict; a verdict is not a polished flow. This skill closes the loop: each iteration produces a measurable grade delta, one fix at a time, with backend-truth verification at every step. It exists because, without the loop, polish stalls at "B+ feels good enough", per-iteration fixes regress other screens, fixes batch into un-attributable PRs, composition-level bugs survive macro grading, and the UI ships claims the backend contradicts.

Purpose: drive a flow from raw to award-quality through tight iterative loops. Each iteration: drive end-to-end on a clean fixture → capture every state → grade ruthlessly → pick ONE highest-ROI fix → apply + commit atomically → schedule next.

Derive this project's inputs first

Read the project at runtime to resolve these — do not assume:

  • Fixture reset command — the seed/cleanup that returns a known clean state.
  • Flow capture harness — the auto-driver (Maestro YAML chain / Playwright spec / a shell script) that runs the flow without user input.
  • Reviewer agent — the L1 grader for multi-screen flows (or the single-screen UX reviewer when drilling down).
  • Backend-truth probe queries — 3–5 project-specific SQL/API calls, each with a known-good shape; deviation = a bug.
  • Semantic-count audit patterns — where a rendered count can lie for this project (pipeline-subset vs user truth on generative surfaces; filter-scoped vs unfiltered counts on dashboards).
  • Iteration caps — a hard cap (the budget ceiling, e.g. 10) and a soft cap (pivot-or-escalate trigger, e.g. 6).
  • Audit report dir — where reports, ledger, and captures land.
  • Safety invariants — the do-not-edit list (migrations, the package manifest, the design-token structure, fixture files, the capture-harness file itself except sanctioned navigation fixes).
  • Quality bar / design-north-star — read the project's stated quality reference to anchor what "award-quality" means; do not hardcode benchmark apps.

Read the full file on GitHub · 108 lines

Changes

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.

  1. 6d ago First seen · 108 lines · 92 tokens per session scan A d5253cd2614b

Subscribe to this mod's changes

iterative-polish-autoloop is a skill published in the GitHub repository vindm/dotclaude (1 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 2,198 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.

Related

Other skills, from other repositories

Accessibility Checklist

A concrete, checklist-driven pass for semantic HTML, ARIA, keyboard navigation, contrast, alt text, and focus management.

niels-emmer/myace · 28 tokens

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

shajith003/awesome-claude-skills · 59 tokens

artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

shajith003/awesome-claude-skills · 63 tokens

theme-factory

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

shajith003/awesome-claude-skills · 62 tokens

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

shajith003/awesome-claude-skills · 50 tokens

ui-design

Use this to design a nice UI in single html as inspiration & UI exploration.

shajith003/awesome-claude-skills · 19 tokens