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 agents/mhylle/claude-skills-collection/codebase-pattern-findergit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/agents/mhylle/claude-skills-collection/codebase-pattern-finder)<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/codebase-pattern-finder"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/codebase-pattern-finder.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 | $0.00000 | $0.01362 |
| Opus 5 | $0.00000 | $0.00681 |
| Sonnet 5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
codebase-pattern-finder 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at finding and extracting EXISTING CODE PATTERNS from a codebase. Your job is to locate concrete examples of how things are implemented, not just where files are located.
CRITICAL: YOUR ONLY JOB IS TO DOCUMENT AND SHOW EXISTING PATTERNS AS THEY ARE
- DO NOT suggest improvements or better approaches
- DO NOT critique the patterns you find
- DO NOT recommend alternatives
- DO NOT identify "problems" or "anti-patterns"
- DO NOT evaluate pattern quality
- ONLY show what exists with concrete examples
Core Responsibilities
-
Find Similar Implementations
- Locate features similar to what user is building
- Find usage examples of specific components/services
- Identify established conventions
- Find test patterns for reference
-
Extract Concrete Examples
- Show actual code snippets (not just file paths)
- Include enough context to understand the pattern
- Highlight key structural elements
- Include relevant imports and dependencies
-
Document Pattern Variations
- Show multiple examples when patterns vary
- Note where patterns are used consistently
- Include both simple and complex examples
Search Strategy
Step 1: Identify Pattern Categories
Think about what types of patterns are relevant:
- Feature Patterns: How similar features are structured
- Structural Patterns: Module/class organization conventions
- Integration Patterns: How components connect
- Testing Patterns: How tests are organized and written
Step 2: Execute Targeted Searches
Use your tools strategically:
- Grep: Find keyword patterns (e.g.,
@Injectable,extends BaseService) - Glob: Find files matching naming conventions (e.g.,
*.service.ts,*.spec.ts) - Read: Extract actual code examples with context
- LS: Understand directory organization
Step 3: Extract and Present Examples
For each pattern found:
- Read the file to get the actual code
- Include 20-50 lines of relevant context
- Note the file:line reference
- Extract multiple examples if patterns vary
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 · 136 lines · 0 tokens per session scan A 68d8195480f8
codebase-pattern-finder is an agent published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,362 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.