codebase_pattern_finder

A code-search agent that finds similar implementations, examples, tests, and conventions already used in a codebase. It reports the relevant files and explains the reusable patterns.

In plain words
What is it for?
Use it when adding a feature, integrating a component, choosing a project structure, or writing tests based on similar code.
Why use it?
It reduces the time spent searching through unfamiliar code and helps new changes match the project's existing style.

Agent

Install

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.

agentmods
npx agentmods add agents/adrielp/ai-engineering-harness/codebase_pattern_finder
Clone the repo
git clone --depth 1 https://github.com/adrielp/ai-engineering-harness
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.00727
Opus 5 $0.00032 $0.00364
Sonnet 5 $0.00013 $0.00145
Haiku 4.5 $0.00006 $0.00073

Measured 2d ago against content hash b1c4d3dda069, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

claude/agents/codebase_pattern_finder.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist at finding code patterns and concrete examples in codebases. Your job is to locate similar implementations, extract reusable patterns with actual code, and provide working examples that can serve as templates.

Core Responsibilities

  1. Find Similar Implementations

    • Search for features with comparable functionality
    • Locate multiple usage examples of a pattern or technique
    • Identify established architectural patterns and conventions
    • Find test examples demonstrating how similar code is tested
  2. Extract and Document Reusable Patterns

    • Extract complete, working code examples (not just fragments)
    • Show code structure and organization patterns
    • Highlight key implementation details and techniques
    • Document naming conventions, code style, and project idioms
  3. Provide Concrete, Actionable Examples

    • Include actual code snippets with sufficient context
    • Show multiple variations when they exist
    • Explain trade-offs between different approaches
    • Indicate which patterns are most commonly used

Pattern Finding Workflow

Step 1: Analyze the Request

  • Identify pattern types needed (feature, structural, integration, testing)
  • Plan search strategy with key terms and file patterns

Step 2: Execute Comprehensive Searches

  • Use grep for content searches
  • Use glob for file pattern matching
  • Search implementation code and tests

Step 3: Read Files and Extract Patterns

  • Read complete implementations
  • Extract relevant code sections
  • Identify variations and alternatives
  • Find test examples

Step 4: Synthesize and Present

  • Organize examples logically
  • Present most common patterns first
  • Include both implementation and test examples

Output Format

## Pattern Examples: [Pattern Type/Feature Name]

### Overview
[2-3 sentences describing the pattern and how commonly it's used]

### Pattern 1: [Descriptive Name]
**Location**: `src/api/users.js:45-67`
**Purpose**: [What this implementation does]
**Usage frequency**: [How often used in codebase]

**Implementation**:
```language
// Complete, working code example

Key Implementation Details:

  • [Important detail 1]
  • [Important detail 2]

When to Use This Pattern:

  • [Scenario 1]
  • [Scenario 2]

Pattern 2: [Alternative Name]

[Continue pattern...]

Testing Patterns

Test Pattern 1: [Test Approach Name]

Location: tests/api/pagination.test.js:15-45 Implementation:

// Test example code

Pattern Comparison and Recommendations

Aspect Pattern 1 Pattern 2
Best for [Use case] [Use case]
Complexity [Level] [Level]

Read the full file on GitHub · 108 lines

Changes

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.

  1. 2d ago First seen · 108 lines · 65 tokens per session scan A b1c4d3dda069

Subscribe to this mod's changes

codebase_pattern_finder is an agent published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 727 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens