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 agentmods add commands/madappgang/magus/create-stylegit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/create-style)<a href="https://agentmods.dev/commands/madappgang/magus/create-style"><img src="https://agentmods.dev/badge/commands/madappgang/magus/create-style.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.06011 |
| Opus 5 | $0.00023 | $0.03005 |
| Sonnet 5 | $0.00009 | $0.01202 |
| Haiku 4.5 | $0.00005 | $0.00601 |
Grade A, and why
create-style 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 5d 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.
This is a copy
100% identical to create-style — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 770 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<user_request> $ARGUMENTS </user_request>
**You MUST:**
- Use AskUserQuestion for all user input gates
- Use Write to create .claude/design-style.md
- Use Read to check for existing style file
- Use Tasks to track wizard progress
- Use Bash for file operations in `.claude/` directory
**You MUST NOT:**
- Use Agent tool (this is not an orchestrator)
- Modify any source code files outside `.claude/` directory
- Make assumptions about user preferences
**You MAY:**
- Create and modify files in `.claude/` directory (design-style.md, design-references/)
- Copy user-provided images to `.claude/design-references/`
- Delete reference images when user confirms removal
</implementer_role>
<todowrite_requirement>
Track wizard progress through phases. For main wizard (create/update):
1. Check existing style
2. Select base reference
3. Define brand colors
4. Configure typography
5. Set spacing scale
6. Document component patterns
7. Add dos and donts
8. Save style file
For action-specific workflows:
**capture action:**
1. Parse capture arguments
2. Determine capture method
3. Execute capture or copy
4. Update style file references
5. Confirm completion
**add-reference action:**
1. Validate source file
2. Get description and mode
3. Copy to design-references
4. Update style file
5. Confirm completion
**remove-reference action:**
1. Find reference in style file
2. Confirm deletion with user
3. Delete file and update style
4. Confirm completion
**list-references action:**
1. Read style file
2. List directory contents
3. Cross-reference and report
</todowrite_requirement>
</critical_constraints>
<steps>
<step>Initialize Tasks with wizard phases</step>
<step>Use Read tool to check if .claude/design-style.md exists</step>
<step>If exists, ask: Update existing or create new?</step>
<step>If updating, read existing file as base</step>
</steps>
<quality_gate>User confirmed action (new/update)</quality_gate>
</phase>
<phase number="2" name="Base Reference">
<objective>Select predefined design system as starting point</objective>
<steps>
<step>Present available design references using AskUserQuestion with options:
1. Material Design 3 - Google's design system
2. Apple Human Interface Guidelines - iOS/macOS patterns
3. Tailwind UI - Utility-first CSS patterns
4. Ant Design - Enterprise-level design system
5. Shadcn/ui - Modern React component patterns
6. Start from scratch (no base reference)
</step>
<step>Store selected base reference</step>
</steps>
<quality_gate>Base reference selected</quality_gate>
</phase>
<phase number="3" name="Brand Colors">
<objective>Define project color palette</objective>
<steps>
<step>Ask for primary brand color (hex value or description)</step>
<step>Ask for secondary/accent colors</step>
<step>Ask for semantic colors (success, warning, error)</step>
<step>Ask if dark mode colors differ</step>
<step>Generate color section for style file</step>
</steps>
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.
- 5d ago First seen · 770 lines · 45 tokens per session scan A 3e40ce3a7539
create-style is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 6,011 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to create-style, differing in 22 lines, and is treated as a copy.
Other commands, from other repositories
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.