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/joaquimscosta/arkhe-claude-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/joaquimscosta/arkhe-claude-plugins/prompt)<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/prompt"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/prompt/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/joaquimscosta/arkhe-claude-plugins/prompt"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/prompt.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 | $0.00015 | $0.01354 |
| Opus 5.5 | $0.00006 | $0.00542 |
| Sonnet 5.5 | $0.00003 | $0.00271 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
prompt 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 yesterday.
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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Command
Convert natural-language descriptions, revision notes, or spec files into Stitch-optimized prompts. This command gathers your preferences before generating to ensure the output matches your vision.
Usage
/prompt "Design a fintech dashboard with KPI cards and charts"
/prompt @specs/mobile-app.md
/prompt "Move the KPI cards above the chart and add a region filter"
Attach files or reference repository paths as needed; the Skill will read them before rewriting the prompt.
Inputs
$ARGUMENTS: user-provided brief, iteration note, or file path(s) to parse.- Attached files (optional): wireframes, specs, or references to include during analysis.
Interactive Flow
For new prompt generation (not revisions), this command asks about your preferences:
- Component Selection - Which UI components to include
- Style Preferences - Visual style (Enterprise, Consumer, Minimal, etc.)
- Structure Decision - Combined file or split by component
Select "Quick generation" at the first question to skip all questions and use smart defaults.
Questions are skipped when:
- Input is a revision request (starts with "change", "update", "move", "adjust")
- User selects "Quick generation"
- Single component detected (structure question only)
Execution
Step 1: Detect Request Type
Check if $ARGUMENTS is a revision request:
- If starts with: "change", "update", "move", "adjust", "resize", "reposition", "modify"
- → Skip all questions, invoke skill directly with
$ARGUMENTS
Step 2: Check for Design Context
Look for design-intent/memory/constitution.md:
- If found: Extract Project Type and Design System for style defaults
- If not found: Proceed without context
Step 3: Analyze Brief for Components
Parse $ARGUMENTS to identify UI components mentioned:
- Navigation elements (sidebar, header, menu, tabs)
- Content areas (cards, grids, tables, lists)
- Data visualization (charts, graphs, metrics, KPIs)
- Interactive elements (forms, buttons, modals, dialogs)
- Media (images, video, galleries)
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.
- yesterday First seen · 201 lines · 15 tokens per session scan A 86f27f7fef00
prompt is a command published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,354 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 2026-10-16.
Other commands, from other repositories
p3-ux-wireframes
Creates wireframes (ASCII art) for the most important screens with interaction descriptions.
p1-journeys
Develops detailed personas, user journeys, and usage scenarios based on the Discovery results. These artefacts form the user foundation for all further conception decisions.
p3-ux-a11y
Defines WCAG target, contrast requirements, keyboard navigation, screen reader requirements and testing methods.
p3-ux-darkmode
Defines the color strategy for dark mode with semantic colors and toggle mechanism.
p3-ux-navigation
Creates the navigation structure, sitemap and identifies critical flows.
p6-a11y-visual
Checks colour contrast (WCAG AA), colour-independence of information presentation, and dark mode conformance.