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 a8cteam51/claude-code-plugins --skill iterategit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWrote 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/a8cteam51/claude-code-plugins/iterate)<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.
<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>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 | $0.00120 | $0.01906 |
| Opus 5.5 | $0.00048 | $0.00762 |
| Sonnet 5.5 | $0.00024 | $0.00381 |
| Haiku 4.5 | $0.00012 | $0.00191 |
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.
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
:rootblock and grep for the selector or variable. Theme: read only the relevanttheme.jsonsettings/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--stonedirectly), make the change at each usage and offer to add the alias so next time it's a one-line change.
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.
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.
- 7d ago First seen · 143 lines · 120 tokens per session scan A ad497a6526b7
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.
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.
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…
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.
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.
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.
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…