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/joaquimscosta/arkhe-claude-plugins/save-patternsgit 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/save-patterns)<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/save-patterns"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/save-patterns.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 5.1 | $0.00014 | $0.00852 |
| Opus 5 | $0.00007 | $0.00426 |
| Sonnet 5 | $0.00003 | $0.00170 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
save-patterns 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 6d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/save-patterns
Purpose: Analyze recent work and suggest design patterns that should be preserved as design intent
Usage: /save-patterns [category]
Examples:
/save-patterns- Analyze all recent work for patterns/save-patterns components- Focus on component patterns only/save-patterns foundations- Focus on spacing, typography, color patterns/save-patterns layouts- Focus on layout and grid patterns
What This Command Does
- Reviews Recent Work - Analyzes code changes, components created, and design decisions made in the current session
- Identifies Reusable Patterns - Finds design decisions that could benefit other features
- Suggests Documentation Locations - Recommends where each pattern should be documented (components/, foundations/, patterns/)
- Presents Summary for Review - Shows findings to user for manual decision-making
- Waits for User Direction - Does NOT automatically document anything
Analysis Focus
The agent will look for:
Custom Design Decisions
- Layout patterns that deviate from standard design system
- Spacing decisions that aren't standard tokens
- Component compositions unique to your application
- Content hierarchies and information architecture patterns
Reusable Components
- Custom components created during implementation
- Extensions to existing components
- Component variations that could be reused
Responsive Patterns
- Breakpoint-specific behaviors
- Mobile optimization strategies
- Layout adaptations across screen sizes
Visual Treatments
- Color usage beyond design system tokens
- Typography treatments for specific contexts
- Shadow, border, and elevation patterns
Output Format
The agent will present findings as:
## Design Intent Candidates
### Components Patterns
- **CustomDataCard** → `components/data-card.md`
- Reason: Unique hover states and nested action buttons
- Reusability: High - used in 3+ contexts
### Foundation Patterns
- **48px Section Spacing** → `foundations/custom-spacing.md`
- Reason: Consistent spacing between major page sections
- Reusability: Medium - applies to L1 layouts
### Layout Patterns
- **Three-Column Dashboard** → `patterns/dashboard-layout.md`
- Reason: Specific grid system for dashboard pages
- Reusability: High - dashboard variations
## Not Recommended for Documentation
- Standard Fluent spacing tokens (already in design system)
- Default component behaviors (documented in Fluent)
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.
- 6d ago First seen · 114 lines · 14 tokens per session scan A d94dc027a3e8
save-patterns is a command published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 22d ago), licensed MIT. It adds 14 tokens to every session and 852 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
sheet-report
Analyze a Numbers or Excel file and generate a report with charts.
watch
You are executing the /hydra:watch command. Live monitoring of all background agents with real-time status updates.
infogenius
Research-First Image Generation - Facts → Visual Prompt → High-Quality Image.
ops
Weekly operations loop — triage the inquiry inbox, advance the CRM pipeline, sweep open PRs across repos, and surface the content plan. Loads the ops skill.