Atris is a codebase intelligence tool that generates structured navigation maps with exact file and line references to eliminate redundant file scanning by AI agents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install atris
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 atris 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 Atris?
Atris provides a persistent, structured intelligence layer for any codebase. By generating a central navigation index in atris/MAP.md, it allows AI agents to bypass repetitive full-project scans, leading to an 80-95% reduction in token consumption. This tool is a cornerstone for developers using Openclaw Skills to maintain context across sessions.
The skill follows a MAP-first philosophy: always consult the existing map before performing a search. If a symbol isn't found, the agent performs a targeted search once and immediately updates the map. This ensures that the codebase intelligence grows more comprehensive with every interaction, making it an essential addition to your Openclaw Skills library.
Atris Use Cases
- Onboarding to a complex, unfamiliar codebase with hundreds of files.
- Reducing token costs and latency during long-running development sessions.
- Mapping out specific feature flows or cross-cutting concerns like authentication.
- Providing immediate "where is X?" answers without re-triggering expensive search operations.
How Atris Works
- Initialize the atris directory and check for an existing MAP.md file within the project root.
- Execute ripgrep (rg) commands to extract key definitions, route handlers, and entry points while ignoring dependencies and build artifacts.
- Parse the extracted data to build a structured Markdown index organized by feature, concern, and critical impact.
- Consult the map for every subsequent navigation request to find direct file and line references immediately.
- Surgically update the map as files are modified, moved, or deleted to maintain technical accuracy without full regeneration.
Atris Setup
First, ensure ripgrep (rg) is installed on your system. To initialize this skill within your Openclaw Skills environment, create the directory and generate the initial map using the following commands:
mkdir -p atris
# Extract key definitions to seed the map
rg "^(export|function|class|const|def |async def |router\.|app\.|@app\.)" --line-number -g "!node_modules" -g "!.git" > atris/MAP.md
Once the file is created, use it as the primary source of truth for all codebase navigation tasks.
Atris Data Schema & Taxonomy
The skill organizes codebase intelligence into a specific hierarchy within the atris/MAP.md file:
| Section | Content Type | Purpose |
|---|---|---|
| Quick Reference | Symbol definitions | Provides immediate file:line access for common functions and classes. |
| By-Feature Map | Grouped logic | Maps files and line ranges to specific business features like Auth or UI. |
| By-Concern Map | Cross-cutting patterns | Identifies common patterns like error handling, logging, and middleware. |
| Entry Points | Execution flow | Documents server initialization, request lifecycles, and build pipelines. |
| Critical Files | High-impact assets | Flags essential configuration, schemas, and model files with usage notes. |
Atris Advanced Features
- Surgical map updates that prevent full regeneration and preserve manual annotations.
- Automated detection of stale references or missing files based on codebase drift.
- Integration with ripgrep for lightning-fast structure extraction across thousands of files.
- Token-optimized context management designed specifically for advanced Openclaw Skills workflows.
- Multi-level grouping that maps code by feature, concern, and execution flow.
SKILL.md
Loading
Related Openclaw Skills
Web Automation Service
A comprehensive browser automation tool for form filling, data extraction, and scheduled monitoring.
AI Research Scraper
A specialized automation tool for extracting, summarizing, and tracking the latest AI product developments and research from premier technical sources.
AI News Pusher v2.2
An advanced AI news aggregator that utilizes LLMs to score, filter, and push high-value industry updates automatically to team channels.
RouteMesh RPC (JSON-RPC)
A streamlined interface for calling RouteMesh's unified JSON-RPC endpoint across multiple EVM chains using a Python-based helper.
Academic Deep Research
A methodical AI research agent providing exhaustive, multi-cycle investigations with APA-compliant documentation.
ActiveCampaign Skill
Integrate ActiveCampaign CRM functionality into your AI agent workflows for seamless lead management and automated sales pipelines.
METADATA
Featured*
