martingarramon/claude-code-starter-kit
Production-extracted architecture for Claude Code CLI. 3-layer system: CLAUDE.md constitution + specialist Skills + persistent Memory. Rules from mistakes, not pre-optimization.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit martingarramon/claude-code-starter-kit/.claude ./rig-claude-code-starter-kit # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit martingarramon/claude-code-starter-kit/skills/architecture-decision .claude/skills/architecture-decision $ npx degit martingarramon/claude-code-starter-kit/skills/code-review .claude/skills/code-review $ npx degit martingarramon/claude-code-starter-kit/skills/context-management .claude/skills/context-management $ npx degit martingarramon/claude-code-starter-kit/skills/debugging .claude/skills/debugging $ npx degit martingarramon/claude-code-starter-kit/skills/deployment .claude/skills/deployment $ npx degit martingarramon/claude-code-starter-kit/skills/migration .claude/skills/migration $ npx degit martingarramon/claude-code-starter-kit/skills/performance .claude/skills/performance $ npx degit martingarramon/claude-code-starter-kit/skills/proposal-writing .claude/skills/proposal-writing $ npx degit martingarramon/claude-code-starter-kit/skills/research .claude/skills/research $ npx degit martingarramon/claude-code-starter-kit/skills/security-audit .claude/skills/security-audit $ npx degit martingarramon/claude-code-starter-kit/skills/testing .claude/skills/testing $ npx degit martingarramon/claude-code-starter-kit/skills/tool-integration .claude/skills/tool-integration
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(rm -rf *)",
"Bash(git push --force)"
]
}
} Skills (12)
architecture-decisioncode-reviewcontext-managementdebuggingdeploymentmigrationperformanceproposal-writingresearchsecurity-audittestingtool-integration
Permissions
deny (2)
Bash(rm -rf *)
Bash(git push --force)
ask (0)
—
allow (6)
Read
Write
Edit
Bash(git status)
Bash(git diff)
Bash(git log)
Similar rigs
pravindurgani/claude-code-multipane-iterm2
Stop your AI agent from reviewing its own code — 4-pane iTerm2 setup with role-locked Claude Code sessions. Step-by-step guide included.
Minimalist 1.0k tok ·
thixpin/claude-config
A reusable Claude Code configuration for agentic coding and software engineering workflows. It provides global engineering guidelines, debugging and bug-fixing workflows, code review, security auditing, testing skills, and reusable develope
Pragmatist 1.5k tok ·
bchox/agent-practices
Portable, practical repository guidance for AI-assisted software development.
Skill Collector 978 tok ·
byronxlg/skillfold
Declarative skill manager for Claude Code and Codex. Declare skills in YAML, pin exact revisions in a lockfile, install them reproducibly into .claude/skills.
Skill Collector 2.2k tok ·