skills.rest
agentsope
agentsopeCOMMUNITY
Explore all skills by this author →
GitHub

agentsop-repo-map

Build symbol-level repo maps from tree-sitter extraction and PageRank-style ranking.

287|16|Updated May 20, 2026
Search Tags:#code navigation#tree-sitter#PageRank#repo map#multi-file editing#LLM coder-agents
One-click install
npx skills add https://github.com/agentsope/SkillAlchemy --skill agentsop-repo-map
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agentsop-repo-map
Source: https://github.com/agentsope/SkillAlchemy/tree/main/skills/agentsop-repo-map
Command: npx skills add https://github.com/agentsope/SkillAlchemy --skill agentsop-repo-map

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the problem of LLM coder-agents editing the wrong files in large repositories by giving them a framework-agnostic, auditable map of symbols and where they are referenced.

Core Features & Use Cases

  • Symbol-level repo navigation (skeletons): uses tree-sitter to extract class/function signatures and types, then ranks importance via a PageRank-style cross-file reference graph.
  • Token-budgeted, read-only context: provides a token-aware, dynamically sized map that expands when the chat is empty and shrinks when real code is loaded, avoiding wasted context.
  • Operational SOP for build/use/refresh/scope/audit: includes explicit operations for building the map, refreshing after edits, scoping for monorepos, printing for reviewer audit, and locating candidate files for write authorization.

Quick Start

Ask your coder-agent harness to build a repo-map, then instruct the agent to use the map to propose up to a few candidate target files for your change before adding any files to the write set.

Frequently Asked Questions about agentsop-repo-map

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

FAQPage Schema
How do I stop LLM coder-agents from editing the wrong files in a large codebase?▼

You can prevent wrong file edits by providing LLM coder-agents a framework-agnostic, symbol-level repo map that ranks file importance via a PageRank-style cross-file reference graph.

What is a tree-sitter repo map for multi-file editing?▼

A tree-sitter repo map is a read-only skeleton of class and function signatures that provides token-aware context to LLM coder-agents for safe cross-module refactors.

How do I build and refresh a repo map for monorepo navigation?▼

You build and refresh a repo map for monorepo navigation by applying an explicit operational SOP to extract symbols, scope to relevant directories, and refresh the map after edits.

Does repo map context dynamically adjust token budget during LLM code generation?▼

Yes, the repo map dynamically adjusts token budget by expanding when the chat is empty and shrinking when real code is loaded, preventing wasted context during LLM code generation.

Can I audit cross-file reference changes before authorizing LLM write access?▼

Yes, you can audit cross-file reference changes before authorizing LLM write access because the repo map explicitly separates read-only navigation from write authorization with print and diff support.

Related Skills

Explore More Software Engineering Skills→
Heyo-ComputerHeyo-Computer
1

codegraph-search

Locate definitions and references in Rust, Python, JavaScript, and TypeScript projects using tree-sitter parsing.

Official
Intermediate
CloudyWingCloudyWing

context-map

Generate change impact analyses and dependency maps for codebase modifications.

Community
Intermediate
Abstract-FoundationAbstract-Foundation
1

reading-agw-wallet

Retrieve targeted Abstract Global Wallet context with field trimming and paginated token listings.

Official
Intermediate
MadAppGangMadAppGang
278

claudemem-search

Analyze codebases with tree-sitter AST parsing and PageRank symbol ranking.

Official
Advanced