Installation & configuration

Docs

Three ways to install. Drop-in template, Pi-mono extension, or MCP server. Pick the one that matches your workflow.

01 · Drop-in template

Copy one folder into any repository.

No CLI, no runtime, no dependencies. The core is structured Markdown and YAML. Works with any LLM that can read and write files.

Step 1: Copy the template
cp -r /path/to/CodeCartographer/.codecarto /path/to/your-repo/
Step 2: Pick a pipeline (optional)

Edit .codecarto/workflow/status.yaml and set the pipeline field. Defaults to the 7-phase full analysis with a split defect scan.

# Available pipeline paths:
pipeline: workflow/pipeline-full-with-deep-audit.yaml  # 7-phase (default)
pipeline: workflow/pipeline-full-with-audit.yaml       # 6-phase
pipeline: workflow/pipeline.yaml                       # 5-phase
pipeline: workflow/pipeline-defect-scan.yaml           # 2-phase
pipeline: workflow/pipeline-lite.yaml                  # 3-phase
pipeline: workflow/pipeline-architecture-only.yaml     # 1-phase
pipeline: workflow/pipeline-synthesis.yaml             # 4-phase forward synthesis (Pi/MCP only)
Step 3: Point an LLM at the guide
Read .codecarto/GUIDE.md and begin the analysis.

The LLM reads the guide, checks status.yaml for progress, and starts the next phase automatically. Each phase produces a validated output in .codecarto/findings/.

Works in Claude Code, OpenCode, Cursor, Windsurf, Aider, and any IDE copilot with file read/write access.

02 · Pi-mono extension

Slash commands, widgets, and tool gating.

Install the package directly into Pi-mono. Phase sub-agents run in parallel widgets with live token tracking and file-backed session transcripts.

Install
pi install npm:codecartographer-pi
# or, from a local checkout:
pi install /absolute/path/to/CodeCartographer
# or, from a git URL:
pi install git:github.com/HuginnIndustries/CodeCartographer
Available commands

/codecarto-init

Copy .codecarto/ into the current repository and select a pipeline.

/codecarto-next

Spawn the next eligible phase as a sub-agent. Optional --llm-steer flag for customized seed prompts.

/codecarto-status

Show current phase progress and pipeline state.

/codecarto-validate

Run validation against the current phase output.

/codecarto-complete

Atomically mark a phase complete after validation passes.

/codecarto-phase

Force a specific phase even out of pipeline order.

/codecarto-skill

Run a post-pipeline skill once all phases are complete.

/codecarto-usage

Show cumulative and per-phase token usage from local phase runs.

/codecarto-open

Activate an existing workspace without resetting state.

/codecarto-vision

Run a guided product discovery interview for the synthesis pipeline.

/codecarto-switch-pipeline

Switch the active pipeline without losing findings or progress.

/codecarto-publish

Publish the reimplementation spec to a configured library.

/codecarto-library-init

Initialize a library directory with marker and config.

/codecarto-config

Show the effective merged configuration.

/codecarto-dashboard

Regenerate the dashboard HTML.

03 · MCP server

18 tools for any MCP-compatible host.

The same core primitives exposed as a Model Context Protocol server. Wire it into Claude Code, Claude Desktop, or any MCP host. The host runs the LLM, isolates phase sessions, and controls compaction; CodeCartographer returns prompts, validates outputs, and manages durable workflow state.

Install
npm install --global codecartographer-pi
# or, in a project:
npm install codecartographer-pi
Host configuration

Add to your MCP host config. Claude Code uses ~/.config/claude-code/config.json; Claude Desktop uses claude_desktop_config.json.

{
  "mcpServers": {
    "codecartographer": {
      "command": "codecarto-mcp"
    }
  }
}

The server exposes 18 workflow and library tools: codecarto_init, codecarto_status, codecarto_switch_pipeline, codecarto_next, codecarto_phase, codecarto_validate, codecarto_complete, codecarto_skill, codecarto_publish, codecarto_library_list, codecarto_library_reindex, codecarto_library_init, codecarto_config, codecarto_vision, codecarto_open, codecarto_usage, codecarto_dashboard, and codecarto_list_skills. Workflow tools accept an absolute cwd for the target repository; library tools accept a configured or explicit library path.

04 · Forward synthesis

Turn confirmed software maps into a traceable build plan.

The synthesis pipeline runs through Pi or MCP. It combines a product vision with reusable, versioned reimplementation specs, pauses for explicit human selection, preserves conflicts, and produces work packages with a decision-level provenance ledger.

Start
/codecarto-init synthesis
# Fill .codecarto/inputs/vision.md
/codecarto-next --auto

The first run creates a ranked proposal, completes that phase, and then intentionally stops at the confirmation preflight.

Confirm and resume
# In proposal.md:
| [x] | event-router | v2 | ... |

/codecarto-next --auto

Merge and finalization read only the checked, version-pinned specs. An unknown entry or version is rejected before any LLM phase starts.

05 · Deploy with GitHub Pages

Merge to main and let GitHub Pages publish the site.

This site is plain HTML, CSS, and JavaScript. GitHub Pages serves the repository's main branch from the repository root at codecarto.dev.

  1. Open a pull request targeting main.
  2. Run npm test against the authoritative CodeCartographer checkout and wait for the pull-request checks to pass.
  3. Merge the pull request. GitHub Pages automatically starts a deployment from main at /(root).
  4. Confirm the latest build completed in Settings → Pages.
  5. Keep CNAME set to codecarto.dev. GitHub Pages manages the approved TLS certificate and enforces HTTPS.
  6. Visit https://codecarto.dev/ and hard refresh.
Published site files
  • index.html
  • features.html
  • docs.html
  • showcase.html
  • site.css
  • colors_and_type.css
  • script.js
  • CNAME
  • robots.txt
  • sitemap.xml
06 · Token usage and cost

What to expect on your first run.

CodeCartographer reads your source code multiple times across phases and produces thousands of words of structured output. The fixed template overhead is about 27,000 tokens across a 6-phase run. Source code reading is the dominant variable cost.

Medium codebase (~100k tokens)

A full 5-phase run costs roughly $2 to $4 in API fees. Larger codebases scale linearly. Start with architecture-only to test output quality before committing.

Tips to reduce cost

Use one session per phase for fresh context windows. The lite pipeline gives 80% of the value for understanding. Skip the defect scan on weaker models.