Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

explore-codebase — Claude Code skill: what it does, how to install

Guides coding agents through repository structure using the code-review-graph MCP knowledge graph under tight token budgets.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add tirth8205/code-review-graph --skill explore-codebase -a claude-code
Open on GitHub

What explore-codebase does

This skill guides agents through codebase architecture using code-review-graph MCP tools. It organizes navigation into concrete steps: pulling minimal context via get_minimal_context_tool, checking community module structure with get_architecture_overview_tool, finding nodes by keyword, and querying caller or import links via query_graph_tool.

The main requirement is having the code-review-graph MCP server running in your setup. The skill strictly limits resource consumption: it sets a budget of roughly five tool calls and 800 output tokens per task, mandating detail_level="minimal" wherever accepted.

The graph only narrows down scope. Agents are required to inspect the actual implementation and test files before writing code changes.

What it helps with

  • map repository architecture using graph community structures
  • trace callers, callees, and imports via query_graph_tool
  • follow execution paths using graph flow inspection tools
  • locate oversized functions across the codebase

Example prompts for the agent

  • Use explore-codebase to trace the call hierarchy of processOrder
  • Find oversized functions in the project using the knowledge graph
  • Map out which components depend on the auth module

How to install explore-codebase

1Skills CLI (Vercel)

npx skills add tirth8205/code-review-graph --skill explore-codebase -a claude-code

2Manually: put the files in place

~/.claude/skills/explore-codebase/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/explore-codebase/

From the same set7

The whole set →
build-graph tirth8205 Builds or updates a repository knowledge graph for code review. Use it during first setup, after a branch switch, or following a large refactor. Claude Code CX Codex Cursor +1 1,300installs review-delta tirth8205 This skill reviews changes since the last commit and maps their blast radius. Use it for focused code review without loading the whole project. Claude Code CX Codex Cursor +1 1,200installs review-changes tirth8205 Reviews a change set through a knowledge graph, scoring risk and tracing impact. Use it to inspect changed functions, affected flows, and missing tests. Claude Code CX Codex Cursor +1 1,100installs refactor-safely tirth8205 Plans a refactor from a dependency graph, lists edits before a rename and checks the impact radius before large changes. Claude Code CX Codex Cursor +1 1,100installs review-pr tirth8205 This skill reviews a PR or branch through a code knowledge graph, showing risk, affected flows, and test gaps. Use it when a diff needs structural context. Claude Code CX Codex Cursor +1 1,100installs debug-issue tirth8205 This skill traces bugs through a code graph before source inspection, then checks call paths and change impact. Use it when an issue needs a narrower debugging scope. Claude Code CX Codex Cursor +1 1,000installs

Similar

qa garrytan Automate bug hunting in browser, API, CLI, jobs, workers, and webhooks. Searches code, runs commands, checks logs, and asks clarifying questions. Claude Code CX Codex Cursor +1 457installs workers-profiling cloudflare Skill for analyzing CPU and memory usage in deployed Cloudflare Workers and Durable Objects. Finds expensive functions and proposes code optimizations. Claude Code CX Codex Cursor +1 12,100installs code-reviewer https://github.com/Jeffallan Analyzes code diffs and files to spot bugs, security vulnerabilities (SQL injection, XSS), code smells, N+1 queries, and returns a prioritized review report. Use for pull request reviews and code audits. Claude Code CX Codex Cursor +1 6,500installs claude-code Hermes Agent + Teknium Delegates coding tasks to the Claude Code CLI through terminal commands. Useful for running automated refactoring, bug fixes, and tests in one-shot or interactive sessions. Claude Code CX Codex Cursor +1 433installs review-agent-setup Tom Farley This skill gates AI review actions behind manual human approval before pull requests or CI pipelines change. Every attempt generates an Ed25519-signed receipt for offline auditing. Claude Code CX Codex Cursor 5,200installs codebase-inspection Hermes Agent Counts code lines, files, languages, and code-to-comment ratios with pygount. Use it to inspect a repository’s size and composition. Claude Code CX Codex Cursor +1 420installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs

Questions about explore-codebase

How to install explore-codebase in Claude Code?

Run npx skills add tirth8205/code-review-graph --skill explore-codebase -a claude-code. You can also configure it manually at ~/.claude/skills/explore-codebase/SKILL.md.

What does the explore-codebase skill do?

It provides a workflow for inspecting codebase architecture, execution flows, and node relationships through specialized knowledge graph MCP tools.

What is required to run explore-codebase?

You must have the code-review-graph MCP server configured, as this skill directly invokes its graph inspection tools.

Source text

SKILL.md · MIT 
---
name: explore-codebase
description: Navigate and understand codebase structure using the knowledge graph
---

## Explore Codebase

Use the code-review-graph MCP tools to find your way around the codebase.

### Steps

1. Call `get_architecture_overview_tool` for the community structure. Call `list_communities_tool`, then `get_community_tool`, only for the modules you need.
2. Call `semantic_search_nodes_tool` to find a function or class by name or keyword.
3. Call `query_graph_tool` with `callers_of`, `callees_of` or `imports_of` to trace relationships. `children_of` on a file lists its functions and classes.
4. Call `list_flows_tool`, then `get_flow_tool` for one flow, to follow an execution path.
5. Call `find_large_functions_tool` to find oversized functions.
6. Call `list_graph_stats_tool` only when you need node, edge and language counts.

## Token Efficiency Rules
- Call `get_minimal_context_tool(task="<your task>")` before any other graph tool.
- Pass `detail_level="minimal"` wherever a tool accepts it. Use "standard" only when minimal is not enough.
- Prefer a targeted `query_graph_tool` call over a broad listing call.
- Budget: about five tool calls and 800 tokens of graph output per task.
- Read the implementation and its tests before changing code. The graph narrows scope; it does not replace the source.

© tirth8205 · MIT · tirth8205/code-review-graph

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor