Skip to content

AGENTS.md

Latest commit

 

History

History
69 lines (53 loc) · 3.41 KB

AGENTS.md

File metadata and controls

69 lines (53 loc) · 3.41 KB

AGENTS.md

IMPORTANT: Codebase Intelligence Instructions for code-intelligence

This repository is indexed by Repowise. Use the MCP tools below for orientation, discovery, and enriched context (documentation, ownership, history, decisions). Always verify against actual source files before making changes — the index may be stale.

Last indexed: 2026-05-14 (commit 1e064c4)

Tech Stack

Languages: Node.js, TypeScript

Hotspots (High Churn)

File Churn 90d Commits Owner
src/mcp-server.ts 98.3th %ile 9 Roshan Choudhary
src/project-memory.ts 96.6th %ile 5 Roshan Choudhary
src/git.ts 94.8th %ile 5 Roshan Choudhary
src/project-intent.ts 93.1th %ile 2 Roshan Choudhary
src/engineering-insights.ts 91.4th %ile 3 Roshan Choudhary

Repowise MCP Tools

This project has a Repowise MCP server configured. These tools provide documentation, ownership, architectural decisions, and risk signals. Use them for orientation and discovery — then read actual source to verify before editing.

Recommended workflow:

  1. Start with get_overview() on a new task to orient yourself.
  2. Call get_context(targets=["path/to/file.py"]) for enriched context on unfamiliar files — but always read the source before editing.
  3. Call get_risk(targets=["path/to/file.py"]) before changing hotspot files.
  4. Don't know where something lives? Call search_codebase(query="authentication flow").
  5. Need to understand why code is structured a certain way? Call get_why(query="why JWT over sessions") before architectural changes.
  6. After architectural changes, consider calling update_decision_records(action="create", ...) to record the rationale.
  7. Need to understand how two modules connect? Call get_dependency_path(source="src/auth", target="src/db").
  8. Before cleanup tasks, call get_dead_code() to find confirmed unused code.
  9. For documentation or diagrams, call get_architecture_diagram(scope="src/auth").

Note: MCP tool responses reflect the last index run. If the index is stale, verify against source files.

Tool When to use
get_overview() Orient yourself on a new task
get_context(targets=[...]) Enriched context on unfamiliar files
get_risk(targets=[...]) Before changing hotspot files
get_why(query="...") Before architectural changes
update_decision_records(action=...) After architectural changes — record decisions
search_codebase(query="...") When locating code
get_dependency_path(source=..., target=...) When tracing module connections
get_dead_code() Before any cleanup or removal
get_architecture_diagram(scope=...) For visual structure or documentation

Codebase Conventions

Commands:

  • Build: npm run build
  • Test: npm run test
  • Dev: npm run dev
  • Typecheck: npm run typecheck

Imported Claude Cowork project instructions

It's an intelligence mcp, which processes the project, adds semantic and data layer to provide information the ai agent for improved coding