Understand large codebases

Trace request flows, unfamiliar modules, ownership boundaries, and the files that matter before the first edit.

Map a repository before changing it

Analysis Discovery and planning Discovery Analysis

autohand -p "Map this codebase and show me the safest first files to inspect"

A readable architecture brief with key entry points, risk areas, and next commands.

Understand large codebases with Autohand Code is a repository discovery workflow that maps real entry points, owners, data paths, tests, generated files, and risk areas before a developer changes code. ### At a glance | Question | Answer | | --- | --- | | Best for | joining a large repository, debugging unfamiliar behavior, or scoping a change across several modules | | Primary inputs | Product area, route, command, subsystem, or error path; Relevant issue text, logs, screenshots, or customer report; Constraints such as do not edit yet, backend only, or ignore generated files | | Autohand Code returns | A readable architecture brief with key entry points, risk areas, and next commands. | | Avoid when | the exact failing line is already known and the team only needs a small patch | ### How Autohand Code handles this workflow 1. Reads the repo structure, entry points, package scripts, tests, and recent local context. 2. Groups confirmed files, likely owners, data paths, and risky generated or shared surfaces. 3. Separates verified behavior from assumptions so the next change starts with evidence. 4. Returns the first safe validation commands for the area under review. ### Best inputs - Product area, route, command, subsystem, or error path - Relevant issue text, logs, screenshots, or customer report - Constraints such as do not edit yet, backend only, or ignore generated files ### Strong prompt autohand -p "Map this codebase and show me the safest first files to inspect" ### Autohand Code CLI options - Run `autohand -p "Map the code path for checkout creation..." --path apps/web` for a one-shot architecture map in the right workspace. - Use `/plan` or Shift+Tab in an interactive session when the first output should be read-only investigation. - Add sibling repositories with `--add-dir ../api` when the request path crosses service boundaries. ### Review before accepting A useful result names real files, explains why each file matters, calls out uncertainty, and lists validation commands that can run in the repository. ### Source and validation signals Autohand AI maintains this workflow as first-party product guidance for Autohand Code. Use the [Autohand CLI Playbook](https://github.com/autohandai/code-cli/blob/main/docs/AUTOHAND_PLAYBOOK.md), [CLI reference](/docs/working-with-autohand-code/cli-reference.html), and [configuration reference](https://github.com/autohandai/code-cli/blob/main/docs/config-reference.md) when choosing between interactive mode, command mode, auto-mode, feature-enabled /goal, /settings, skills, MCP, and permission settings. The related resources below link to product docs and tutorials for the workflow, and the final answer should name repository-specific files, commands, outputs, or docs that a reviewer can verify. ### Frequently asked questions ### What is Understand large codebases with Autohand Code? Understand large codebases with Autohand Code is a repository discovery workflow that maps real entry points, owners, data paths, tests, generated files, and risk areas before a developer changes code. ### When should a team use Understand large codebases? Use it before assigning work in an unfamiliar codebase, changing a shared subsystem, or asking another agent to make edits. ### What evidence should reviewers check for Understand large codebases? A useful result names real files, explains why each file matters, calls out uncertainty, and lists validation commands that can run in the repository.

Guide Best Practices for AI Code Agents Set expectations for context gathering, validation, and agent handoffs before edits begin. /docs/guides/ace/best-practices.html Guide LSP Code Intelligence Use language-server context to understand symbols, references, and project structure. /docs/guides/lsp-code-intelligence.html Reference Memory System Carry repository conventions and prior decisions into future sessions. /docs/working-with-autohand-code/memory.html