skills.rest
shihwesley
shihwesleyCOMMUNITY
Explore all skills by this author →
GitHub

mercator-ai

Orchestrate parallel subagents to map codebases with Merkle-based change detection.

4|Updated Feb 6, 2026
Search Tags:#automation#codebase#subagents#scanning#mapping#change-detection#merkle
One-click install
npx skills add https://github.com/shihwesley/mercator-ai --skill mercator-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mercator-ai
Source: https://github.com/shihwesley/mercator-ai/tree/main/plugins/mercator-ai/skills/mercator-ai
Command: npx skills add https://github.com/shihwesley/mercator-ai --skill mercator-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tiktoken, and includes scripts (resource) components.

What problem does it solve?

Maps and documents large codebases efficiently by orchestrating parallel subagents and Merkle-based change detection, reducing manual mapping effort and enabling incremental updates across projects of any size.

Core Features & Use Cases

  • Parallel subagent orchestration provides scalable codebase mapping for large repositories.
  • Merkle-based change detection enables instant diffs and targeted re-exploration, minimizing work.
  • Outputs CODEBASE_MAP.md and docs/.mercator.json, and updates CLAUDE.md with a concise summary of findings.

Quick Start

Run the Mercator AI scanner on your project directory to generate the codebase map and merkle manifest.

Frequently Asked Questions about mercator-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I map a large codebase and detect changes efficiently?▼

Yes, incremental codebase updates are supported using a Merkle manifest to track file changes. This enables instant diffs and targeted re-exploration, so you only re-scan modified files and update CLAUDE.md summaries without remapping the entire repository.

What is the best way to document a massive project repository?▼

To start codebase mapping, run the Mercator AI scanner on your project directory. The scan-codebase.py workflow reads and analyzes files via parallel subagents, ultimately generating a CODEBASE_MAP.md, a merkle manifest, and updated CLAUDE.md summaries.

Does codebase mapping with subagents work for small projects too?▼

Yes, codebase mapping with subagents scales from small to massive projects. The parallel orchestration and Merkle-based change detection adapt to the project size, ensuring efficient scanning and mapping regardless of the total repository scale.

Do I need tiktoken to run the codebase scanner?▼

Known limitations of Merkle-based change detection include its reliance on file hashes to identify modifications, meaning it tracks exact file changes but may not capture semantic relationships or non-file-based logic without a full re-scan of the codebase.

Related Skills

Explore More Software Engineering Skills→
lpjhelderlpjhelder

forge-setup

Install and configure kronon-forge with Node.js and npm.

Community
Intermediate
jayprimerjayprimer

update-kb

Synchronize knowledge base documentation with the current codebase.

Community
Advanced
AgenticFlowXAgenticFlowX
19

afx-discover

Scan codebases to discover infrastructure scripts, automation tools, and development capabilities.

Official
Advanced
ZTE-AICloudZTE-AICloud
52

ai-friendly-component-srp-orchestrate

Orchestrate multi-module SRP analysis and gate CI checks on thresholds.

Official
Advanced