CodeAlive Context Engine
/install codealive-context-engine
CodeAlive Context Engine
Semantic code intelligence across your entire code ecosystem — current project, organizational repos, dependencies, and any indexed codebase.
Authentication
All scripts require a CodeAlive API key. If any script fails with "API key not configured", help the user set it up:
Option 1 (recommended): Run the interactive setup and wait for the user to complete it:
python setup.py
Option 2 (not recommended — key visible in chat history): If the user pastes their API key directly in chat, save it via:
python setup.py --key THE_KEY
Do NOT retry the failed script until setup completes successfully.
Table of Contents
Tools Overview
| Tool | Script | Speed | Cost | Best For |
|---|---|---|---|---|
| List Data Sources | datasources.py |
Instant | Free | Discovering indexed repos and workspaces |
| Search | search.py |
Fast | Low | Finding code locations, descriptions, identifiers |
| Fetch Artifacts | fetch.py |
Fast | Low | Retrieving full content for search results |
| Chat with Codebase | chat.py |
Slow | High | Synthesized answers, architectural explanations |
| Explore | explore.py |
Slow | High | Multi-step discovery workflows |
Cost guidance: Search is lightweight and should be the default starting point. Chat with Codebase invokes an LLM on the server side, making it significantly more expensive per call — use it when you need a synthesized, ready-to-use answer rather than raw search results.
Three-step workflow:
- Search — find relevant code locations with descriptions and identifiers
- Review — examine the descriptions to understand what each result contains
- Get content — use
fetch.pyfor external repos orRead()for local files
When to Use
Use this skill for semantic understanding:
- "How is authentication implemented?"
- "Show me error handling patterns across services"
- "How does this library work internally?"
- "Find similar features to guide my implementation"
Use local file tools instead for:
- Finding specific files by name or pattern
- Exact keyword search in the current directory
- Reading known file paths
- Searching uncommitted changes
Quick Start
1. Discover what's indexed
python scripts/datasources.py
2. Search for code (fast, cheap)
python scripts/search.py "JWT token validation" my-backend
python scripts/search.py "error handling patterns" workspace:platform-team --mode deep
python scripts/search.py "authentication flow" my-repo --description-detail full
3. Fetch full content (for external repos)
python scripts/fetch.py "my-org/backend::src/auth.py::AuthService.login()"
4. Chat with codebase (slower, richer answers)
python scripts/chat.py "Explain the authentication flow" my-backend
python scripts/chat.py "What about security considerations?" --continue CONV_ID
5. Multi-step exploration
python scripts/explore.py "understand:user authentication" my-backend
python scripts/explore.py "debug:slow database queries" my-service
Tool Reference
datasources.py — List Data Sources
python scripts/datasources.py # Ready-to-use sources
python scripts/datasources.py --all # All (including processing)
python scripts/datasources.py --json # JSON output
search.py — Semantic Code Search
Returns file paths, line numbers, descriptions, identifiers, and content sizes. Fast and cheap.
python scripts/search.py \x3Cquery> \x3Cdata_sources...> [options]
| Option | Description |
|---|---|
--mode auto |
Default. Intelligent semantic search — use 80% of the time |
--mode fast |
Quick lexical search for known terms |
--mode deep |
Exhaustive search for complex cross-cutting queries. Resource-intensive |
--description-detail short |
Default. Brief description of each result |
--description-detail full |
More detailed description of each result |
Getting content: Search returns descriptions and identifiers. For the current repo, use Read() on the file paths. For external repos, use fetch.py with the identifiers.
fetch.py — Fetch Artifact Content
Retrieves the full source code content for artifacts found via search. Use this for external repositories you cannot access locally.
python scripts/fetch.py \x3Cidentifier1> [identifier2...]
| Constraint | Value |
|---|---|
| Max identifiers per request | 20 |
| Identifiers source | identifier field from search results |
| Identifier format | {owner/repo}::{path}::{symbol} (symbols), {owner/repo}::{path} (files) |
chat.py — Chat with Codebase
Sends your question to an AI consultant that has full context of the indexed codebase. Returns synthesized, ready-to-use answers. Supports conversation continuity for follow-ups.
This is more expensive than search because it runs an LLM inference on the server side. Prefer search when you just need to locate code. Use chat when you need explanations, comparisons, or architectural analysis.
python scripts/chat.py \x3Cquestion> \x3Cdata_sources...> [options]
| Option | Description |
|---|---|
--continue \x3Cid> |
Continue a previous conversation (saves context and cost) |
Conversation continuity: Every response includes a conversation_id. Pass it with --continue for follow-up questions — this preserves context and is cheaper than starting fresh.
explore.py — Smart Exploration
Combines search and chat-with-codebase in multi-step workflows. Useful for complex investigations.
python scripts/explore.py \x3Cmode:query> \x3Cdata_sources...>
| Mode | Purpose |
|---|---|
understand:\x3Ctopic> |
Search + explanation |
dependency:\x3Clibrary> |
Library usage and internals |
pattern:\x3Cpattern> |
Cross-project pattern discovery |
implement:\x3Cfeature> |
Find similar features for guidance |
debug:\x3Cissue> |
Trace symptom to root cause |
Data Sources
Repository — single codebase, for targeted searches:
python scripts/search.py "query" my-backend-api
Workspace — multiple repos, for cross-project patterns:
python scripts/search.py "query" workspace:backend-team
Multiple repositories:
python scripts/search.py "query" repo-a repo-b repo-c
Configuration
Prerequisites
- Python 3.8+ (no third-party packages required — uses only stdlib)
API Key Setup
The skill needs a CodeAlive API key. Resolution order:
CODEALIVE_API_KEYenvironment variable- OS credential store (macOS Keychain / Linux secret-tool / Windows Credential Manager)
Environment variable (all platforms):
export CODEALIVE_API_KEY="your_key_here"
macOS Keychain:
security add-generic-password -a "$USER" -s "codealive-api-key" -w "YOUR_API_KEY"
Linux (freedesktop secret-tool):
secret-tool store --label="CodeAlive API Key" service codealive-api-key
Windows Credential Manager:
cmdkey /generic:codealive-api-key /user:codealive /pass:"YOUR_API_KEY"
Base URL (optional, defaults to https://app.codealive.ai):
export CODEALIVE_BASE_URL="https://your-instance.example.com"
Get API keys at: https://app.codealive.ai/settings/api-keys
Using with CodeAlive MCP Server
This skill works standalone, but delivers the best experience when combined with the CodeAlive MCP server. The MCP server provides direct tool access via the Model Context Protocol, while this skill provides the workflow knowledge and query patterns to use those tools effectively.
| Component | What it provides |
|---|---|
| This skill | Query patterns, workflow guidance, cost-aware tool selection |
| MCP server | Direct codebase_search, fetch_artifacts, codebase_consultant, get_data_sources tools |
When both are installed, prefer the MCP server's tools for direct operations and this skill's scripts for guided multi-step workflows like explore.py.
Detailed Guides
For advanced usage, see reference files:
- Query Patterns — effective query writing, anti-patterns, language-specific examples
- Workflows — step-by-step workflows for onboarding, debugging, feature planning, and more
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install codealive-context-engine - 安装完成后,直接呼叫该 Skill 的名称或使用
/codealive-context-engine触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
CodeAlive Context Engine 是什么?
Semantic code search and AI-powered codebase Q&A across indexed repositories. Use when understanding code beyond local files, exploring dependencies, discove... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 219 次。
如何安装 CodeAlive Context Engine?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install codealive-context-engine」即可一键安装,无需额外配置。
CodeAlive Context Engine 是免费的吗?
是的,CodeAlive Context Engine 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
CodeAlive Context Engine 支持哪些平台?
CodeAlive Context Engine 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 CodeAlive Context Engine?
由 Rodion Mostovoi(@rodion-m)开发并维护,当前版本 v1.0.0。