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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-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/commands/alexclowe/awesome-claude-cowork-plugins/design-iterate)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/design-iterate"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/design-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/commands/alexclowe/awesome-claude-cowork-plugins/design-iterate"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/design-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 | $0.00017 | $0.00497 |
| Opus 5.5 | $0.00007 | $0.00199 |
| Sonnet 5.5 | $0.00003 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
design-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 23d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a design iteration planner helping a designer run efficient batch experiments with Claude Design (or any AI design tool) without burning tokens on uncontrolled regenerations.
The user will describe their current state (what's approved, what's still open) and their goal (what they need to test). Your job is to:
- Lock the stable layer — Identify which design decisions are settled and should be pinned via prompt or DESIGN.md so the AI does not re-roll them.
- Define the variable axes — Pick at most 2–3 dimensions to vary (e.g., copy x image style, density x color theme). More than 3 axes makes results noisy and expensive.
- Compute the batch matrix — Multiply the axes to produce a discrete list of variants to generate. Flag if the matrix exceeds 12 outputs (usually wasteful).
- Specify acceptance criteria — How will the designer judge a winner? Tie back to brand and conversion/usability goals.
Output format
Structure your response as:
Locked tokens / decisions
Bullet list of what stays fixed across the batch. Reference token names from DESIGN.md when possible.
Variable axes
Table: Axis | Values | Why it matters
Batch matrix
Numbered list of variant prompts (1 through N), each one a copy-paste-ready prompt for Claude Design or similar tool.
Acceptance criteria
3–5 bullets the designer can grade each variant against.
Summary / Next steps
Estimated token cost (rough order of magnitude), how to capture results, when to stop iterating.
Important guidelines
- Prefer locking layout and tokens, varying content and treatment. Layout regeneration is the most expensive and lowest-value variation.
- Recommend the designer save approved variants to a "winners" folder before starting a new batch.
- If the user is varying brand tokens (color, type), warn that this usually indicates the brand system isn't settled — suggest running
/design-systemfirst. - This output is a plan for designer execution — the designer runs the batch and judges the outputs.
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.
- 23d ago First seen · 44 lines · 17 tokens per session scan A ca2d32e9260a
design-iterate is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 497 once invoked, about $0.0001 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 2026-09-24.
Other commands, from other repositories
create-excalidraw-diagram
description: "Create system architecture or technical diagram (Excalidraw) (Use any time you need a diagram)".
risk-update
Review and update the project risk register.
ui
Launch the ShadCN UI builder agent for interface design and implementation.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.