agentrigs
+ submit rig
~ / rigs / stavrespasov / claude-code-os-lite

stavrespasov/claude-code-os-lite

A free, installable starter setup for Claude Code: 10 workflow commands, 2 agents, and the hook that ends --no-verify commits. MIT.

↗ GitHub ★ 2 MIT updated 4mo ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~101 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit stavrespasov/claude-code-os-lite/agents ./rig-claude-code-os-lite/agents
$ npx degit stavrespasov/claude-code-os-lite/commands ./rig-claude-code-os-lite/commands
$ npx degit stavrespasov/claude-code-os-lite/hooks ./rig-claude-code-os-lite/hooks

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.

$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/stavrespasov/claude-code-os-lite/main/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/stavrespasov/claude-code-os-lite/main/agents/planner.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Subagents (2)

code-reviewer
model: sonnet
Code review specialist. Use proactively after writing or modifying any non-trivial code, and before every commit or PR.
planner
model: opus
Implementation planner. Use proactively before any feature touching 3+ files, any architecture decision, or any ambiguous requirement. Produces a phased plan and waits for confirmation — writes no cod

Slash commands (10)

/research/docs/session/resume-session/session/save-session/workflow/build-fix/workflow/checkpoint/workflow/code-review/workflow/plan/workflow/tdd/workflow/test-coverage/workflow/verify

Similar rigs

CreatmanCEO/claude-code-antiregression-setup
Stop Claude Code from breaking your projects. Ready-to-use CLAUDE.md templates, subagents, hooks, and anti-regression configs.
★ 11 setup Claude Code 3 agents 2 hooks 5mo ago
Pragmatist 96 tok ·
Joan266/claude-dotfiles
—
★ 0 setup Claude Code 4 agents 3mo ago
Pragmatist 831 tok ·
tylerjkells/claude-dotfiles
—
★ 0 setup Claude Code 4 agents 8mo ago
Pragmatist 579 tok ·
AizenvoltPrime/claude-setup
—
★ 269 setup Claude Code 1 mcp 1 agents 1 hooks 9mo ago
Pragmatist 1.2k tok ·
copied ✓