An automated wrapper for npm codegraph that simplifies codebase indexing, structural search, impact analysis, and context injection for AI programming.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install codegraph-assistant
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install codegraph-assistant using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is CodeGraph Assistant?
CodeGraph Assistant functions as an accelerated wrapper for npm codegraph, eliminating the friction of manual, multi-step code graph initialization, indexing, and querying. Designed to seamlessly integrate into environments like DeepSeek TUI, this skill enables developers to retrieve comprehensive project structures, look up precise symbol indices, and evaluate potential impact areas with a single command.
By unifying several complex workflows into straightforward operations, it helps developers focus on coding rather than project parsing configuration. It optimizes AI code comprehension by gathering essential task contexts and automatically formatting them into clean Markdown or structural data.
CodeGraph Assistant Use Cases
- Quick Repository Onboarding: Instantly initialize and build a comprehensive structural index for new or unfamiliar code repositories.
- AI Context Gathering: Generate highly relevant, Markdown-formatted task contexts outlining entry points and call chains for specific programming prompts.
- Impact Analysis: Identify exactly which files, functions, or modules will be affected before modifying code.
- Memory Augmentation: Inject indexed repository summaries directly into project documentation like MEMORY.md for future AI context retrieval.
How CodeGraph Assistant Works
- Project Setup and Scanning: The tool runs a unified routine that initializes the code graph configuration and thoroughly indexes the target codebase.
- Symbol Parsing and Querying: Developers or AI agents query the assistant for specific symbol definitions, classes, or code relationships.
- Context Compilation: When a programming task is specified, the assistant traces dependencies, maps out entry points, and extracts relevant files into structured Markdown.
- Context Injection: The gathered context can be systematically written out to project files or piped directly into AI terminal interfaces.
CodeGraph Assistant Setup
Prerequisites
- Python 3.11+
- Global installation of
@colbymchenry/codegraphvia npm
Installation
Ensure your base dependencies are configured, then execute the assist script commands from your project root or add them to your environment PATH.
# Initialize and index a project
python codegraph_assist.py setup /path/to/project
CodeGraph Assistant Data Schema & Taxonomy
CodeGraph Assistant orchestrates local metadata profiles and interacts with the underlying codegraph project architecture. It supports structured schemas to optimize indexing and reporting:
| Feature / Asset | Data Target / Format | Description |
|---|---|---|
| Context Exports | Markdown Format | Aggregated file entry points, symbols, and call chains |
| TUI Shell Output | Structured JSON (-j) |
Programmatic results tailored for direct AI shell execution |
| Memory Sync | MEMORY.md |
Persistent codebase taxonomy summary injected for persistent context |
CodeGraph Assistant Advanced Features
- Automated AI Terminal Execution: Pass the
-jflag to output pure JSON data directly consumable by custom agent tasks and terminal scripts. - Pre-emptive Impact Analysis: Execute impact queries on individual files to discover dependent nodes throughout the entire dependency graph before checking in code.
- Unified Memory Pipeline: Automatically inject code graphs directly into local persistent memory structures, ensuring continuous synchronization between repository changes and agent memory models.
SKILL.md
Loading
Related Openclaw Skills
wutrix
An intelligent film pre-production toolkit designed to seamlessly capture creative ideas, manage scripts, organize character details, and research worldviews directly from your AI workspace.
Artifact Gallery
Converts local files generated by headless AI agents into secure, mobile-accessible HTTPS viewer links.
OpenRouter Rankings Screenshot & Lark/Feishu Digest
An automated workflow tool for Openclaw Skills that scrapes OpenRouter rankings, generates summarized digests, and publishes structured reports with screenshots directly to Lark/Feishu.
Coin Flip & Dice Guessing Game
An interactive gaming skill enabling AI agents to play coin flip and dice guessing games, returning rich media and text results.
Scientific Figure Analysis
An end-to-end multi-stage pipeline that extracts figures from scientific PDFs, analyzes them with Kimi K2.6 multimodal vision AI, and reverse-engineers their generation workflows.
WeChat Mini-Program Vibe Coding Starter
An AI agent skill designed to help non-engineers and product managers build, iterate, and launch WeChat Mini-Program MVPs from scratch using Vibe Coding methodologies.
Featured*
