iterate

iterate is a skill for Claude Code from a8cteam51/claude-code-plugins. It costs 120 tokens per session (1,906 once invoked), scanned A, original, MIT.

A workflow for revising an existing web design or coded page without rebuilding the whole direction. It changes requested text, styles, tokens, properties, or sections and checks the affected result.

In plain words
What is it for?
Use it to adjust a design block, change CSS or design tokens, fix copy, revise a section, or apply a list of feedback to an existing page.
Why use it?
Small design changes can become slow when the entire project is reread or recreated. This keeps revisions focused on the existing HTML or theme.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Part of the sp-site-design-harness plugin — 7 skills shipped together

Good fit Use it to adjust a design block, change CSS or design tokens, fix copy, revise a section, or apply a list of feedback to an existing page.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a8cteam51/claude-code-plugins/iterate
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 a8cteam51/claude-code-plugins --skill iterate
Clone the repo
git clone --depth 1 https://github.com/a8cteam51/claude-code-plugins

Made for: Claude Code.

Or install sp-site-design-harness, the plugin that ships this one along with the rest of its 7 skills.

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 iterate

README.md
[![agentmods](https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/iterate/github.svg)](https://agentmods.dev/skills/a8cteam51/claude-code-plugins/iterate)
Your own site
<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/iterate"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/iterate/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.

agentmods 80×15 button for iterate

Your own site · 80×15
<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/iterate"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/iterate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,906 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 $0.00120 $0.01906
Opus 5.5 $0.00048 $0.00762
Sonnet 5.5 $0.00024 $0.00381
Haiku 4.5 $0.00012 $0.00191

Measured 7d ago against content hash ad497a6526b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

iterate 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 7d 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/sp-site-design-harness/skills/iterate/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iterate

Fast revision path for the sp-site-design-harness. create-design makes designs; this skill changes them. The whole point is speed: read as little as possible, edit directly, verify only what changed.

Do not load create-design's references, re-read research/brief.md, spawn critic subagents, re-run the deletion pass, or narrate CSS reasoning. The user is a designer who codes. When they name a variable, a selector, or a value, do exactly that.

Step 0 — Resolve the target (cheap)

Scope root: an explicit path in the arguments, else git rev-parse --show-toplevel, else $PWD (same resolution as /publish-design-options).

State Target
No handoff/DESIGN.md HTML phase. directions/NN-<slug>.html. Ask which one only if the request doesn't make it clear.
handoff/DESIGN.md exists and a theme path is known (arguments, or a .theme-path file at the scope root, absolute or relative to it) Theme phase. The block theme.
handoff/DESIGN.md exists, no theme path Ask once for the theme folder, then write it to .theme-path so nobody has to ask again.

After handoff, directions/*.html is frozen. Never edit it. If asked to, say it's frozen and make the change in the theme instead. Two live sources drift apart. See ../../DECISIONS.md (2026-09-25). If the request names a direction other than the one DESIGN.md describes, say so and ask before doing anything.

Step 1 — Classify, say so in one line, then act

Give each request a level and state it in one line, e.g. L0 — swapping --color-border to --stone in 02-conditions.html. The user can override ("just do it", "treat this as L1"). If the level isn't obvious, read references/levels.md.

L0 — Direct edit

Token or variable swap, copy change, one property.

  • HTML: read only the :root block and grep for the selector or variable. Theme: read only the relevant theme.json settings/styles key, or grep the pattern/template.
  • A color named in words ("plum", "the terracotta") means the palette token of that name if one exists. Otherwise pick a value that fits the palette and report it.
  • Edit. That's it: no screenshot unless asked, no references, no critique.
  • One exception, contrast. Whenever a color changes (a token's value, or a usage switched to a different token), check numerically against the surface each usage sits on: text 4.5:1 (3:1 at large sizes); borders, separators, focus rings and other UI 3:1. Reading the rules that set those surfaces is part of the check. Accessibility outranks everything (../../references/instruction-priority.md). Report a failure and suggest the nearest passing value rather than silently shipping it. Also update anything derived from the old value, such as a hard-coded hover shade or a contrast ratio recorded in .tokens.md.
  • If the file has no role alias for what was asked (e.g. no --color-border, so borders reference --stone directly), make the change at each usage and offer to add the alias so next time it's a one-line change.

Read the full file on GitHub · 143 lines

Files

What ships with it

1 file 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.

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. 7d ago First seen · 143 lines · 120 tokens per session scan A ad497a6526b7

Subscribe to this mod's changes

iterate is a skill published in the GitHub repository a8cteam51/claude-code-plugins (5 stars, last pushed 2d ago), licensed MIT. It adds 120 tokens to every session and 1,906 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-09.

Related

Other skills, from other repositories

anti-slop-design

Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.

sickn33/agentic-awesome-skills · 34 tokens

chakra-ui-builder

Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…

chakra-ui/chakra-ui · 214 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 52 tokens

frontend-ui-dark-ts

Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.

microsoft/skills · 48 tokens

prototype-web

A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.

nexu-io/html-anything · 24 tokens

frontend-visual-qa

Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…

daymade/claude-code-skills · 125 tokens