megacode
mitkox/megacode
Execute privacy-preserving, tool-driven security audits on large .NET codebases using a local DSPy RLM workflow. It prevents context overflow by utilizing bounded file access and indexed manifests.
77 19MITUpdated 2026-02-09
69
GoodOverview
This skill provides a structured workflow for running automated security audits via the audit.py script using DSPy RLM. It enables developers and security auditors to scan large repositories without loading the entire codebase into the model context window. Through bounded host tools and local execution, it generates markdown reports, metadata json, and jsonl manifests detailing findings, severity levels, and remediation steps.
Capabilities
- ▸Run baseline security audits on source code repositories
- ▸Tune RLM planner parameters and tool limits to handle large codebases
- ▸Troubleshoot stalled runs, truncation issues, and execution timeouts
- ▸Produce structured audit outputs including executive summaries and remediation guidance
Best for
Scanning large legacy .NET repositories for security vulnerabilities without context overload, Configuring and tuning RLM iteration, output, and tool call limits for performance, Generating actionable security audit reports in markdown and json formats
Works with
Claude CodeCursorGitHub CopilotCodex
Evoa Score breakdown= Σ (score × weight)
69Task usefulness20%77 → +15.4
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%33 → +4.0
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%80 → +12.0
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%80 → +8.0
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%52 → +4.2
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 total68.8 / 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
The tool analyzes source code for vulnerabilities and may expose secrets or sensitive information in output reports. Audit findings should always be verified manually before making production changes.
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.