Skip to content

feat(agents): add code-explorer and code-architect agents#60

Merged
amondnet merged 2 commits into
mainfrom
feat/code-explorer
Dec 23, 2025
Merged

feat(agents): add code-explorer and code-architect agents#60
amondnet merged 2 commits into
mainfrom
feat/code-explorer

Conversation

@amondnet

Copy link
Copy Markdown
Contributor

Summary

  • Add code-explorer agent for deep codebase analysis (tracing execution paths, mapping architecture layers, understanding patterns)
  • Add code-architect agent for architecture blueprints (analyzing patterns, designing components, providing implementation plans)

Changes

code-explorer agent

  • Specializes in tracing feature implementations across codebases
  • Maps architecture layers and execution flows
  • Documents dependencies and provides file:line references

code-architect agent

  • Designs feature architectures based on existing codebase patterns
  • Provides comprehensive implementation blueprints
  • Includes component designs, data flows, and build sequences
  • Integrates with organizational standards (engineering-standards, ADR, TDD)

Test plan

  • Verify agents load correctly in Claude Code
  • Test code-explorer with sample feature analysis
  • Test code-architect with sample architecture design request

Add a new agent that specializes in tracing and understanding feature
implementations across codebases by mapping architecture layers,
execution paths, and dependencies.
Add a new agent that designs feature architectures by analyzing existing
codebase patterns and providing comprehensive implementation blueprints
with file mappings, component designs, and build sequences.
@gemini-code-assist

Copy link
Copy Markdown

Summary of Changes

Hello @amondnet, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly expands the agent capabilities by integrating two specialized agents: code-explorer and code-architect. The code-explorer agent is tailored for in-depth understanding of existing features and their implementations, while the code-architect agent focuses on designing robust and compliant architectures for new features, ensuring adherence to organizational standards and best practices.

Highlights

  • New Code-Explorer Agent: Introduced a new agent designed for deep codebase analysis, capable of tracing execution paths, mapping architectural layers, and understanding code patterns.
  • New Code-Architect Agent: Added a new agent focused on creating architecture blueprints, analyzing existing patterns, designing components, and providing detailed implementation plans.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

@cloudflare-workers-and-pages

Copy link
Copy Markdown

Deploying code-please with  Cloudflare Pages  Cloudflare Pages

Latest commit: 33d6009
Status:🚫  Build failed.

View logs

@gemini-code-assist gemini-code-assist Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces two new agents, code-explorer and code-architect, for codebase analysis and architecture design. The agent definitions are well-structured and detailed. My review focuses on enhancing their effectiveness by suggesting they leverage the powerful ast-grep skill for structural code analysis, which appears to be a core capability of the platform. This will enable them to perform their tasks more accurately and efficiently.

Comment thread agents/code-architect.md
## Core Process

**1. Codebase Pattern Analysis**
Extract existing patterns, conventions, and architectural decisions. Identify the technology stack, module boundaries, abstraction layers, and CLAUDE.md guidelines. Find similar features to understand established approaches.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To improve the agent's ability to analyze codebase patterns, it's beneficial to explicitly guide it to use the ast-grep skill. This tool is designed for structural code search and will make the analysis more powerful and accurate.

Suggested change
Extract existing patterns, conventions, and architectural decisions. Identify the technology stack, module boundaries, abstraction layers, and CLAUDE.md guidelines. Find similar features to understand established approaches.
Extract existing patterns, conventions, and architectural decisions, leveraging structural search with Skill("ast-grep") where possible. Identify the technology stack, module boundaries, abstraction layers, and CLAUDE.md guidelines. Find similar features to understand established approaches.

Comment thread agents/code-explorer.md
Provide a complete understanding of how a specific feature works by tracing its implementation from entry points to data storage, through all abstraction layers.

## Analysis Approach

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The code-explorer agent's primary mission is to trace and analyze code. The ast-grep skill is an extremely powerful tool for this. Explicitly mentioning it in the analysis approach will guide the agent to use it, leading to more effective and deeper code exploration.

Suggested change
You should leverage structural search tools like Skill("ast-grep") to efficiently trace code, identify patterns, and understand relationships between different parts of the codebase.

@amondnet
amondnet merged commit 2851b5a into main Dec 23, 2025
2 of 4 checks passed
@amondnet
amondnet deleted the feat/code-explorer branch December 23, 2025 06:19
@passionfactory-bot passionfactory-bot Bot mentioned this pull request Dec 23, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant