Cartographer

Cartographer

Maps codebases of any size using parallel Sonnet subagents with 1M token context windows.

CRITICAL: Opus orchestrates, Sonnet reads. Never have Opus read codebase files directly. Always delegate file reading to Sonnet subagents - even for small codebases. Opus plans the work, spawns subagents, and synthesizes their reports.

Quick Start

1. Run the scanner script to get file tree with token counts
2. Analyze the scan output to plan subagent work assignments
3. Spawn Sonnet subagents in parallel to read and analyze file groups
4. Synthesize subagent reports into docs/CODEBASE_MAP.md
5. Update CLAUDE.md with summary pointing to the map

Workflow

Step 1: Check for Existing Map

First, check if docs/CODEBASE_MAP.md already exists:

If it exists:

1. Read the last_mapped timestamp from the map's frontmatter
2. Check for changes since last map:
   • Run git log --oneline --since="<last_mapped>" if git available
   • If no git, run the scanner and compare file counts/paths
3. If significant changes detected, proceed to update mode
4. If no changes, inform user the map is current

If it does not exist: Proceed to full mapping.

Step 2: Scan the Codebase

Run the scanner script to get an overview. Try these in order until one works:

# Option 1: If uv is available (preferred)
uv run ${CLAUDE_PLUGIN_ROOT}/skills/cartographer/scripts/scan-codebase.py . --format json

# Option 2: Direct execution (uses shebang)
${CLAUDE_PLUGIN_ROOT}/skills/cartographer/scripts/scan-codebase.py . --format json

# Option 3: Explicit python3
python3 ${CLAUDE_PLUGIN_ROOT}/skills/cartographer/scripts/scan-codebase.py . --format json

# Option 4: Explicit python (some systems)
python ${CLAUDE_PLUGIN_ROOT}/skills/cartographer/scripts/scan-codebase.py . --format json

If tiktoken is missing, install it:

# With uv (if available)
uv pip install tiktoken

# Or standard pip
pip install tiktoken
# or
pip3 install tiktoken

The output provides:

• Complete file tree with token counts per file
• Total token budget needed
• Skipped files (binary, too large)

Step 3: Plan Subagent Assignments

Analyze the scan output to divide work among subagents:

Token budget per subagent: ~500,000 tokens (safe margin under Sonnet's 1M limit)

Grouping strategy:

1. Group files by directory/module (keeps related code together)
2. Balance token counts across groups
3. Aim for 3-8 subagents depending on codebase size

For small codebases (<100k tokens): Still use a single Sonnet subagent. Opus orchestrates, Sonnet reads - never have Opus read the codebase directly.

Example assignment:

Subagent 1: src/api/, src/middleware/ (~450k tokens)
Subagent 2: src/components/, src/hooks/ (~480k tokens)
Subagent 3: src/lib/, src/utils/, tests/ (~420k tokens)

Step 4: Spawn Sonnet Subagents in Parallel

Use the Task tool with subagent_type: "Explore" and model: "sonnet" for each group.

CRITICAL: Spawn all subagents in a SINGLE message with multiple Task tool calls.

Each subagent prompt should:

1. List the specific files/directories to read
2. Request analysis of:
   • Purpose of each file/module
   • Key exports and public APIs
   • Dependencies (what it imports)
   • Dependents (what imports it, if discoverable)
   • Patterns and conventions used
   • Gotchas or non-obvious behavior
3. Request output as structured markdown

Example subagent prompt:

You are mapping part of a codebase. Read and analyze these files:
- src/api/routes.ts
- src/api/middleware/auth.ts
- src/api/middleware/rateLimit.ts
[... list all files in this group]

For each file, document:
1. **Purpose**: One-line description
2. **Exports**: Key functions, classes, types exported
3. **Imports**: Notable dependencies
4. **Patterns**: Design patterns or conventions used
5. **Gotchas**: Non-obvious behavior, edge cases, warnings

Also identify:
- How these files connect to each other
- Entry points and data flow
- Any configuration or environment dependencies

Return your analysis as markdown with clear headers per file/module.

Step 5: Synthesize Reports

Once all subagents complete, synthesize their outputs:

1. Merge all subagent reports
2. Deduplicate any overlapping analysis
3. Identify cross-cutting concerns (shared patterns, common gotchas)
4. Build the architecture diagram showing module relationships
5. Extract key navigation paths for common tasks

Step 6: Write CODEBASE_MAP.md

Create docs/CODEBASE_MAP.md using this structure:

---
last_mapped: YYYY-MM-DDTHH:MM:SSZ
total_files: N
total_tokens: N
---

# Codebase Map

> Auto-generated by Cartographer. Last mapped: [date]

## System Overview

[Mermaid diagram showing high-level architecture]

```mermaid
graph TB
    subgraph Client
        Web[Web App]
    end
    subgraph API
        Server[API Server]
        Auth[Auth Middleware]
    end
    subgraph Data
        DB[(Database)]
        Cache[(Cache)]
    end
    Web --> Server
    Server --> Auth
    Server --> DB
    Server --> Cache

[Adapt the above to match the actual architecture]

Directory Structure

[Tree with purpose annotations]

Module Guide

[Module Name]

Purpose: [description] Entry point: [file] Key files:

Exports: [key APIs] Dependencies: [what it needs] Dependents: [what needs it]

[Repeat for each module]

Data Flow

[Mermaid sequence diagrams for key flows]

sequenceDiagram
    participant User
    participant Web
    participant API
    participant DB

    User->>Web: Action
    Web->>API: Request
    API->>DB: Query
    DB-->>API: Result
    API-->>Web: Response
    Web-->>User: Update UI

[Create diagrams for: auth flow, main data operations, etc.]

Conventions

[Naming, patterns, style]

Gotchas

[Non-obvious behaviors, warnings]

Navigation Guide

To add a new API endpoint: [files to touch] To add a new component: [files to touch] To modify auth: [files to touch] [etc.]

### Step 7: Update CLAUDE.md

Add or update the codebase summary in CLAUDE.md:

```markdown
## Codebase Overview

[2-3 sentence summary]

**Stack**: [key technologies]
**Structure**: [high-level layout]

For detailed architecture, see [docs/CODEBASE_MAP.md](docs/CODEBASE_MAP.md).

If AGENTS.md exists, update it similarly.

Update Mode

When updating an existing map:

1. Identify changed files from git or scanner diff
2. Spawn subagents only for changed modules
3. Merge new analysis with existing map
4. Update last_mapped timestamp
5. Preserve unchanged sections

Token Budget Reference

Always use Sonnet subagents for maximum file coverage.

Troubleshooting

Scanner fails with tiktoken error:

pip install tiktoken
# or
pip3 install tiktoken
# or with uv:
uv pip install tiktoken

Python not found: Try python3, python, or use uv run which handles Python automatically.

Codebase too large even for subagents:

• Increase number of subagents
• Focus on src/ directories, skip vendored code
• Use --max-tokens flag to skip huge files

Git not available:

• Fall back to file count/path comparison
• Store file list hash in map frontmatter for change detection