RepoMapper
pdavis68/RepoMapper
RepoMapper generates structured, token-aware code repository maps using Tree-sitter parsing and the PageRank algorithm to optimize LLM context.
195 39MITUpdated 2025-12-08
73
GoodOverview
RepoMapper is a command-line tool and Model Context Protocol (MOP) server inspired by Aider's repository mapping functionality. It parses multi-language source files using Tree-sitter, builds relationship graphs, and runs PageRank to identify and rank critical code elements, definitions, and files. By ensuring outputs fit within specific token limits and prioritizing active chat or mentioned files, it helps LLMs effectively navigate large codebases.
Capabilities
- ▸Tree-sitter based code parsing for dozens of programming languages
- ▸PageRank calculation to score code element relevance
- ▸Token-aware output formatting matching specific LLM context windows
- ▸Persistent caching for rapid subsequent analysis
- ▸Model Context Protocol (MCP) server capability via STDIO transport
Best for
Providing LLMs with concise, context-optimized repository maps during software development, Analyzing multi-language codebases via a command-line interface or an MCP server integration, Prioritizing active workspace files and relevant code symbols to reduce token overhead
Works with
Claude CodeCursorGitHub CopilotChatGPTCodex
Evoa Score breakdown= Σ (score × weight)
73Task usefulness20%88 → +17.6
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%85 → +12.8
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%50 → +7.5
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%36 → +4.3
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%100 → +15.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%60 → +6.0
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%61 → +4.9
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total73.0 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Executes local file system traversal and code parsing. Standard local file permissions apply.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.