Skip to content

[Resource]: repo-scan #1120

Description

@haibindev

Display Name

repo-scan

Category

Agent Skills

Sub-Category

General

Primary Link

https://github.com/haibindev/repo-scan

Author Name

haibindev

Author Link

https://github.com/haibindev

License

MIT

Other License

No response

Description

Cross-stack source code asset audit Skill for Claude Code. Scans C/C++, Java/Android, iOS, and Web projects in one pass — classifying every file as project code, third-party, or build artifact. Auto-detects 50+ embedded libraries (FFmpeg, Boost, OpenSSL…) with version extraction. Delivers four-level verdicts per module (Core Asset / Extract & Merge / Rebuild / Deprecate) and generates interactive HTML reports. Designed as an Agent Skill with token-efficient three-layer analysis: filename inference → key file reading → quality sampling. Zero dependencies, works on Windows/macOS/Linux.

Validate Claims

Clone the repo, copy the repo-scan folder into your .claude/skills/ directory, then run /repo-scan in Claude Code on any codebase. The Skill will scan the project and generate an HTML report in the working directory.

Specific Task(s)

Point Claude Code at a multi-stack monorepo and run /repo-scan. It will produce: (1) a structured JSON with file classification and dependency inventory, (2) an interactive HTML report with drill-down navigation and verdict distribution. On a 50,000-file codebase it found: legacy FFmpeg 2.x still in production, the same SDK wrapper duplicated 3 times, and 636 MB of committed build artifacts.

Specific Prompt(s)

/repo-scan — Full audit of the current project
/repo-scan deep — Deep analysis adding thread safety, memory management, and API consistency checks

Additional Comments

Built for real-world large codebases (tested on 50,000+ source files). The hierarchical scanning mode auto-splits monorepos into summary + sub-project reports, keeping AI context manageable. Complements code review tools by focusing on structural/architectural audit rather than line-level review.

Recommendation Checklist

  • I have checked that this resource hasn't already been submitted
  • It has been over one week since the first public commit to the repo I am recommending
  • All provided links are working and publicly accessible
  • I do NOT have any other open issues in this repository
  • I am primarily composed of human-y stuff and not electrical circuits

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions