codebase-report
Made by JeffProduce reusable technical architecture documents from codebase exploration. Use when onboarding, "write up what this does", architecture docs, or handoff.
Works With
Quality and Utility come from canonical skill metadata. Community ratings appear separately as stars when subscriber reviews exist.
Subscribe to download
Public previews are available, but downloads, CLI sync, and premium content require an active subscription.
Sign In to Subscribe- Full skill content with deterministic versioning
- CLI sync + local search index
- Access to Jeffrey’s premium library
Save to your account
Saved skills live in your cloud list. Run jsm sync on each machine to pull them locally.
What's New with this Skill
1Updates, enhancements, and release notes for this skill.
New: Codebase Report, produce a reusable architecture document that survives context compaction
Understanding is ephemeral. Documents survive context compaction. This skill turns an exploration session into a durable architecture report (executive summary, entry points, key types, data flow, external dependencies, configuration, test infrastructure) so the next session doesn't have to re-derive any of it.
- Auto-scaffold mode: ./scripts/scaffold-report.py /path/to/project > ARCHITECTURE.md fills entry points, types, and dependencies from static signals; the agent fills the judgment sections
- Every claim cites file:line so the report can be checked against the code instead of taken on trust
- Seven-section template: executive summary, entry points, key types (3–5 max), data flow, external dependencies, configuration with precedence, test infrastructure
- Three report modes: quick scan (10 min, under 150 lines), standard (30 min, full template), deep dive (1+ hr, diagrams and all paths)
- Differs from codebase-archaeology by output: archaeology produces understanding, this produces a document
The differentiator from codebase-archaeology: archaeology is understanding, this is producing a document. The skill ships a scaffold-report.py that auto-fills what it can detect (entry points by fn main / func main / if __name__, key types by grepping for Rust pub struct and Go struct declarations, dependencies from Cargo.toml or package.json) and leaves the human-judgment sections for the agent to fill.