moai-foundation-cc

Author Claude Code Skills, sub-agents, plugins, slash commands, hooks, and settings.

Updated Aug 29, 2026
One-click install
npx skills add https://github.com/Seung-zedd/secure-file-upload --skill moai-foundation-cc-seung-zedd
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: moai-foundation-cc
Source: https://github.com/Seung-zedd/secure-file-upload/tree/main/.claude/skills/moai-foundation-cc
Command: npx skills add https://github.com/Seung-zedd/secure-file-upload --skill moai-foundation-cc-seung-zedd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Creating Claude Code extensions requires knowing many scattered rules: SKILL.md frontmatter formats, sub-agent tool lists, plugin manifests, hook events, settings hierarchy, and sandboxing options. This Skill consolidates the official authoring guidance into one reference so extensions are built correctly the first time. ## Core Features & Use Cases - Skill Authoring: Progressive disclosure structure, frontmatter rules, and the 500-line SKILL.md limit with validation checklists. - Extension Coverage: Reference docs for sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, dev containers, and CLI usage. - Agent Patterns: Orchestrator-worker architectures, two-agent long-task patterns, context engineering, and tool design best practices. - Use Case: When adding a new project Skill or configuring a PreToolUse hook in settings.json, consult this kit to get the exact frontmatter fields, file locations, and common pitfalls (rationalizations, red flags, verification steps). ## Quick Start Ask Claude to create a new Claude Code Skill or configure a hook using the moai-foundation-cc authoring guidance.

Frequently Asked Questions about moai-foundation-cc

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a Claude Code Skill?▼

Create a SKILL.md file with YAML frontmatter containing a kebab-case name and a third-person description with trigger terms. Keep the body under 500 lines, use progressive disclosure, and move detailed content into reference files loaded on demand.

How do I create a sub-agent in Claude Code?▼

Write a markdown file in .claude/agents/ with frontmatter for name, description, a CSV tools list, and model, followed by the system prompt. The /agents wizard was removed in CC 2.1.198, so ask Claude to create agents or edit the files directly.

What is the difference between allowed-tools and disallowed-tools in a Skill?▼

allowed-tools pre-approves those tools so they run without a permission prompt when the skill is invoked; it does not restrict the tool set. disallowed-tools is the field that actually removes tools from use.

Can Claude Code sub-agents spawn their own sub-agents?▼

Yes, nesting is allowed by default up to three layers below the main conversation, controlled by CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH. To prevent a specific agent from spawning, omit Agent from its tools list or add it to disallowedTools.

How do I run Claude Code in headless mode for CI/CD?▼

Use claude -p with your prompt for non-interactive execution, and always pass --allowedTools to restrict capabilities. Add --output-format json for parseable results and --json-schema when you need validated structured output.

What are the limits of CLAUDE.md memory files?▼

CLAUDE.md has a 40,000 character limit, so large rule sets should move into .claude/rules/*.md files that load conditionally. Memory follows an enterprise-to-project-to-user hierarchy and supports @import syntax.