Anatomia

Anatomia is a CLI and agent harness for Claude Code and Codex. It scans your codebase — detecting your stack, conventions, and patterns — then runs every change through a five-agent pipeline that saves every artifact: scope, spec, contract, build report, and independent verification. Other harnesses are prompt libraries. This one has an engine.

Scan any project in 10 seconds

npx anatomia-cli scan .

No install. One command. See more examples →

Install

Install globally to use the ana command directly:

npm install -g anatomia-cli

Requires Node.js 22+. To update: npm update -g anatomia-cli

Quick start

ana init                      # generate context + agents
ana init commit               # persist to git (so teammates get it too)
ana doctor                    # verify installation is healthy
ana run setup                 # enrich with your team's knowledge (optional, recommended, ~10 min)
ana run                       # start working — "hey Ana"

Tell Ana what you want to build. It'll investigate the codebase, surface tradeoffs, and push back if the approach has problems. When the scope is right, it hands off to Plan, Build, and Verify.

init runs scan automatically and works standalone. The pipeline and setup run through Claude Code or Codex, and scan output works with any markdown-aware AI tool.

init commit commits to the artifact branch — staging, develop, or your pre-production branch if one exists, otherwise main. Check with ana config get artifactBranch before your first commit.

After updating the CLI, run ana init again to refresh scan data and skill detection. Your rules, context, and proof chain are preserved.

What it does

Scan + init

ana scan reads your project and detects framework, database, auth, testing, services, conventions, and patterns. In monorepos, scan identifies each surface (package or app) and detects per-surface commands. Re-running ana init refreshes scan data without overwriting your edits.

ana init writes that intelligence to files agents read:

• ana.json — project config: build/test/lint commands, surfaces, artifact branch, branch prefix. Every agent and CLI command reads this.
• scan.json — full structured scan data for agent consumption
• CLAUDE.md and AGENTS.md — cross-tool project context
• 5 core + 3 conditional skill templates with scan-driven Detected sections
• 16 stack-specific gotchas with compound triggers

Setup (ana run setup) bridges the gap between what scan detects and what your team knows. A ~10 minute session that investigates your codebase, asks 2-3 questions, and writes enriched context. After setup, agents understand your product and decisions — not just your stack.

The pipeline