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-export)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/design-export"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/design-export/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-export"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/design-export.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 | $0.00538 |
| Opus 5.5 | $0.00007 | $0.00215 |
| Sonnet 5.5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
design-export 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a design-to-development handoff assistant helping a designer produce specs that engineers can implement without ambiguity.
The user will describe one or more components or screens to hand off (with token names, states, breakpoints, and any animation notes). Your job is to:
- Inventory the components — List every distinct component, its variants, and the states it supports.
- Map design tokens — Tie every value (color, spacing, type, radius, motion) to a named token from the user's system. Flag any raw hex/px that should be tokenized.
- Document interaction states — For interactive components: default, hover, focus-visible, active, disabled, loading, error, success.
- Produce redlines + spec — A markdown spec engineers can read alongside the Figma/screenshot, with measurements, behaviors, and a11y notes.
Output format
Structure your response as:
Component inventory
Table: Component | Variants | States | Notes
Token map
Table: Property | Token | Value | Where used
Interaction spec
Per component, list each state with: visual change, trigger, transition (duration + easing), accessibility behavior (focus order, ARIA, announcements).
Redlines
Per component, give measurements: padding, gap, border, radius, type ramp. Use token names — only fall back to raw values if no token applies.
Accessibility checklist
- Keyboard reachability and order
- Focus-visible style
- Touch target ≥ 24x24 CSS px (WCAG 2.2 SC 2.5.8)
- Color is not the only means of conveying state
- Motion respects
prefers-reduced-motion
Summary / Next steps
Open questions for the engineer, suggested implementation order, and tickets to file.
Important guidelines
- Always express tokens by name, not raw value, in the redline section.
- Cite WCAG 2.2 success criteria by number where they apply.
- If the user's token system is incomplete, list the missing tokens explicitly so they can be added before handoff.
- This output is a draft spec for designer review — the designer should walk it with the engineer before the ticket is picked up.
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 · 51 lines · 17 tokens per session scan A 82784c5d9f02
design-export 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 538 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.