context-loader

ALWAYS activate this skill at the start of every task. Load project context from .claude/ directory including coding rules, design decisions, and documentation before executing any task.

141 stars

Best use case

context-loader is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

ALWAYS activate this skill at the start of every task. Load project context from .claude/ directory including coding rules, design decisions, and documentation before executing any task.

Teams using context-loader should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/context-loader/SKILL.md --create-dirs "https://raw.githubusercontent.com/DeL-TaiseiOzaki/claude-code-orchestra/main/.codex/skills/context-loader/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/context-loader/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How context-loader Compares

Feature / Agentcontext-loaderStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

ALWAYS activate this skill at the start of every task. Load project context from .claude/ directory including coding rules, design decisions, and documentation before executing any task.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 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

update-lib-docs

141
from DeL-TaiseiOzaki/claude-code-orchestra

Update library documentation in .claude/docs/libraries/ with latest information from web search.

update-design

141
from DeL-TaiseiOzaki/claude-code-orchestra

Explicitly update DESIGN.md with decisions from the current conversation. Use when you want to force a design document update.

troubleshoot

141
from DeL-TaiseiOzaki/claude-code-orchestra

Diagnose and plan fixes for errors/bugs with Codex-first multi-agent collaboration (Codex + Opus 4.6 + Agent Teams). Codex CLI is consulted in EVERY phase for deep code reasoning, hypothesis evaluation, and fix validation. Phase 1: Error reproduction & context gathering (Opus subagent 1M context + Codex initial analysis + Claude user interaction). Phase 2: Parallel diagnosis (Agent Teams: Root Cause Analyst [Codex-driven] + Impact Investigator [Opus + Codex risk analysis]). Phase 3: Fix plan synthesis, Codex validation & user approval. Fix implementation is handled separately by /team-implement.

team-review

141
from DeL-TaiseiOzaki/claude-code-orchestra

Parallel code review using Agent Teams. Spawns specialized reviewers (security, quality, test coverage) to review implementation from different perspectives simultaneously. Run after implementation.

team-implement

141
from DeL-TaiseiOzaki/claude-code-orchestra

Parallel implementation using Agent Teams. Spawns teammates per module/layer, each owning separate files to avoid conflicts. Uses shared task list with dependencies for autonomous coordination. Run after /start-feature plan approval.

tdd

141
from DeL-TaiseiOzaki/claude-code-orchestra

Implement features using Test-Driven Development (TDD) with Red-Green-Refactor cycle.

start-feature

141
from DeL-TaiseiOzaki/claude-code-orchestra

Start a new feature with multi-agent collaboration (Opus 4.6 + Agent Teams). Phase 1: Codebase understanding (Opus subagent 1M context + Claude user interaction). Phase 2: Parallel research & design (Agent Teams: Researcher + Architect). Phase 3: Plan synthesis & user approval. Implementation is handled separately by /team-implement.

spike

141
from DeL-TaiseiOzaki/claude-code-orchestra

Time-boxed technical investigation/feasibility study with Codex-first multi-agent collaboration (Codex + Opus 4.6 + Agent Teams). Codex CLI is consulted in EVERY phase for question framing, feasibility analysis, and final evaluation. Phase 1: Frame the investigation question & constraints (Claude user interaction + Codex question decomposition). Phase 2: Parallel investigation (Agent Teams: Researcher [Opus external research] + Feasibility Analyst [Codex deep analysis] + optional prototype). Phase 3: Codex synthesis into go/no-go recommendation & research report. Produces a DECISION DOCUMENT, NOT an implementation plan. Use /add-feature or /start-feature after a GO decision.

simplify

141
from DeL-TaiseiOzaki/claude-code-orchestra

Simplify and refactor code while preserving functionality and library constraints.

research-lib

141
from DeL-TaiseiOzaki/claude-code-orchestra

Research a library and create comprehensive documentation in .claude/docs/libraries/.

plan

141
from DeL-TaiseiOzaki/claude-code-orchestra

Create a detailed implementation plan for a feature or task. Use when user wants to plan before coding.

init

141
from DeL-TaiseiOzaki/claude-code-orchestra

Analyze project structure and populate the "Repository Identity" section of CLAUDE.md (Zone B) plus AGENTS.md.