agentrigs
+ submit rig
~ / rigs / tatarco / claude-code-starter

tatarco/claude-code-starter

Cache-friendly Claude Code configuration: environment caps, read-deny rules, and Token Optimizer hook wiring. Generic settings only.

↗ GitHub ★ 6 MIT updated 2mo ago project Claude Code
share on X
ARCHETYPE
Automator
Hooks on every lifecycle event: format, lint, notify, log.
CONTEXT TAX · EVERY TURN
~86 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Protects secrets · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit tatarco/claude-code-starter/skills ./rig-claude-code-starter/skills

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 tatarco/claude-code-starter/skills/usage-report .claude/skills/usage-report

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Read(**/.env)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "Read(**/*.pem)",
      "Read(**/node_modules/**)",
      "Read(**/dist/**)",
      "Read(**/build/**)",
      "Read(**/.next/**)",
      "Read(**/coverage/**)",
      "Read(**/*.log)",
      "Read(**/.git/objects/**)"
    ]
  }
}

Skills (1)

usage-report

Hooks (6)

eventmatcherruns
SessionStartcompactpython3 __TOKEN_OPTIMIZER__ compact-restore
SessionStart*python3 __TOKEN_OPTIMIZER__ compact-restore --new-session-only
PreCompact*python3 __TOKEN_OPTIMIZER__ compact-capture --trigger auto
Stop*python3 __TOKEN_OPTIMIZER__ compact-capture --trigger stop
Stop*bash '__KIT_SCRIPTS__/usage-guard.sh'
SessionEnd*python3 __TOKEN_OPTIMIZER__ collect --quiet && python3 __TOKEN_OPTIMIZER__ dashboard --quiet

Permissions

deny (11)
Read(**/.env)
Read(**/.env.*)
Read(**/*.key)
Read(**/*.pem)
Read(**/node_modules/**)
Read(**/dist/**)
Read(**/build/**)
Read(**/.next/**)
Read(**/coverage/**)
Read(**/*.log)
Read(**/.git/objects/**)
ask (0)
—
allow (0)
—

Similar rigs

agentic-community/mcp-gateway-registry
Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding assistants. Transform scattered MCP serve
★ 954 project Claude CodeCodex 18 skills 1 agents 7d ago
Skill Collector 17.2k tok ·
cocoindex-io/cocoindex
Incremental engine for long horizon agents 🌟 Star if you like it!
★ 11.6k project Claude CodeCodex 1 skills 4 hooks 6d ago
Automator 7.3k tok ·
FailproofAI/failproofai
Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.
★ 5,234 project Claude CodeCodex 1 skills 25 hooks 9d ago
Automator 22.9k tok ·
caliber-ai-org/ai-setup
Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex.
★ 1,295 setup Claude CodeCodexCursor 8 skills 8 hooks 15d ago
Automator 3.2k tok ·
copied ✓