context-loader — how to use context-loader how to use context-loader, context-loader setup guide, what is context-loader, context-loader alternative, context-loader vs Claude Code, context-loader install, loading project context with context-loader

v1.0.0
GitHub

About this Skill

Perfect for Codex CLI Agents needing consistent project context and knowledge synchronization with Claude Code. context-loader is a skill that loads shared project context from the .claude/ directory to ensure consistency between Codex CLI and Claude Code

Features

Loads coding rules from .claude/rules/ directory
Reads files such as coding-principles.md and dev-environment.md
Ensures Codex CLI has the same knowledge as Claude Code
Activates at the beginning of every task to load project context
Supports files in markdown format, such as .md

# Core Topics

gyumaruya gyumaruya
[0]
[0]
Updated: 3/9/2026

Quality Score

Top 5%
51
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add gyumaruya/minions/context-loader

Agent Capability Analysis

The context-loader MCP Server by gyumaruya is an open-source Community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use context-loader, context-loader setup guide, what is context-loader.

Ideal Agent Persona

Perfect for Codex CLI Agents needing consistent project context and knowledge synchronization with Claude Code.

Core Value

Empowers agents to load shared project context from the .claude/ directory, ensuring consistency with Claude Code through files like coding-principles.md and dev-environment.md, and providing a unified knowledge base for tasks.

Capabilities Granted for context-loader MCP Server

Loading coding rules for project consistency
Ensuring dev environment requirements are met
Synchronizing knowledge with Claude Code for tasks

! Prerequisites & Limits

  • Requires access to the .claude/ directory
  • Must run at the beginning of every task
  • Specific to Codex CLI and Claude Code integration
Project
SKILL.md
2.0 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Context Loader Skill

Purpose

Load shared project context from .claude/ directory to ensure Codex CLI has the same knowledge as Claude Code.

When to Activate

ALWAYS - This skill must run at the beginning of every task to load project context.

Workflow

Step 1: Load Coding Rules

Read all files in .claude/rules/:

.claude/rules/
├── coding-principles.md   # Simplicity, single responsibility, early return
├── dev-environment.md     # uv, ruff, ty, pytest requirements
├── language.md            # Think in English, respond in Japanese
├── security.md            # Secrets, validation, SQLi/XSS prevention
├── testing.md             # TDD, AAA pattern, 80% coverage
└── codex-delegation.md    # (skip - not relevant for Codex itself)

Step 2: Load Design Documentation

Read .claude/docs/DESIGN.md for:

  • Architecture decisions
  • Implementation patterns
  • Library choices and constraints
  • TODO items and open questions

Step 3: Check Library Documentation

If the task involves specific libraries, read relevant files from:

.claude/docs/libraries/

Step 4: Execute Task

With the loaded context, execute the requested task following:

  • Coding principles from rules
  • Design decisions from DESIGN.md
  • Library constraints from docs

Key Rules to Remember

After loading, always follow these principles:

  1. Simplicity first - Choose readable code over complex
  2. Single responsibility - One function/class does one thing
  3. Type hints required - All functions need annotations
  4. Use uv - Never use pip directly
  5. Security - No hardcoded secrets, validate input, parameterize SQL

Language Protocol

  • Thinking/Reasoning: English
  • Code: English (variables, functions, comments)
  • User communication: Japanese (when reporting back through Claude Code)

Output

After loading context, briefly confirm:

  • Rules loaded
  • Design document status
  • Ready to execute task

Related Skills

Looking for an alternative to context-loader or building a Community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

testing

Logo of lobehub
lobehub

Testing is a process for verifying AI agent functionality using commands like bunx vitest run and optimizing workflows with targeted test runs.

73.3k
0
Communication

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication