← ClaudeAtlas

codebase-contextlisted

Use when analyzing an existing codebase for architecture, tech stack, conventions, and infrastructure. Covers project structure mapping, data model discovery, integration point cataloging, and constraint identification. Do not use for schema changes (use schema-design) or API contract definition (use api-design).
dtsong/agentic-council · ★ 0 · AI & Automation · score 78
Install: claude install-skill dtsong/agentic-council
# Codebase Context ## Purpose Analyze the existing codebase and produce a comprehensive context briefing covering architecture, data model, patterns, and constraints. This output becomes shared context for ALL council agents — it is the foundation every other skill builds on. ## Scope Constraints - Produces read-only analysis; does not modify any project files. - Covers architecture, data model, conventions, infrastructure, and integrations. - Does not design new schemas or API contracts — hand off to schema-design or api-design. ## Inputs - Project root directory ($WORKSPACE) - Any existing CLAUDE.md or project documentation - Package manifests (package.json, pyproject.toml, Cargo.toml, etc.) - Configuration files (tsconfig.json, next.config.js, .env.example, etc.) ## Input Sanitization No user-provided values are used in commands or file paths. All inputs are treated as read-only analysis targets. ## Procedure ### Progress Checklist <!-- Track completion across compaction boundaries --> - [ ] Step 1: Read Project Configuration - [ ] Step 2: Map Directory Structure - [ ] Step 3: Identify Core Architectural Patterns - [ ] Step 4: Map the Existing Data Model - [ ] Step 5: Catalog Key Conventions - [ ] Step 6: Note Infrastructure Constraints - [ ] Step 7: Identify Integration Points ### Step 1: Read Project Configuration Read CLAUDE.md, package.json (or equivalent), tsconfig, and any config files at the project root. Extract framework, language version, key dependen