~ / rigs / AI-BrandFactory / claude-code-starter-pack

AI-BrandFactory/claude-code-starter-pack

Working templates for Claude Code primitives: slash commands, skills, hooks, subagents, MCP configs, Agent SDK starters. Current to Opus 4.7, April 2026.

↗ GitHub ★ 1 NOASSERTION updated 6mo ago project Claude Code
share on X
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
CONTEXT TAX · EVERY TURN
~584 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
5/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · Sandbox or ask-first rules · details

Copy this rig

# review before running: this installs third-party code
$ npx degit AI-BrandFactory/claude-code-starter-pack/.claude ./rig-claude-code-starter-pack  # 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 AI-BrandFactory/claude-code-starter-pack/.claude/skills/commit .claude/skills/commit
$ npx degit AI-BrandFactory/claude-code-starter-pack/.claude/skills/deploy .claude/skills/deploy
$ npx degit AI-BrandFactory/claude-code-starter-pack/.claude/skills/review-code .claude/skills/review-code
$ npx degit AI-BrandFactory/claude-code-starter-pack/.claude/skills/tdd .claude/skills/tdd
$ curl -fsSL --create-dirs -o .claude/agents/refactor-agent.md https://raw.githubusercontent.com/AI-BrandFactory/claude-code-starter-pack/main/.claude/agents/refactor-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/AI-BrandFactory/claude-code-starter-pack/main/.claude/agents/security-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/AI-BrandFactory/claude-code-starter-pack/main/.claude/agents/test-writer.md

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(sudo *)",
      "Bash(curl * | bash)",
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(./secrets/**)",
      "Edit(./.env)",
      "Edit(./.env.*)"
    ],
    "ask": [
      "Bash(git push *)",
      "Bash(git reset --hard *)",
      "Bash(npm publish *)",
      "Bash(npm install *)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/block-rm.sh"
          }
        ]
      }
    ]
  }
}

Skills (4)

Subagents (3)

refactor-agent
model: sonnet
Handles large-scale refactoring across multiple files. Use for rename operations, API signature changes, pattern migrations.
security-reviewer
model: sonnet
Security-focused code review specialist. Use after code changes that touch authentication, authorization, input handling, or external integrations.
test-writer
model: sonnet
Writes unit and integration tests for existing code that lacks test coverage. Use when adding tests to legacy or untested modules.

Hooks (2)

eventmatcherruns
PreToolUseBash"$CLAUDE_PROJECT_DIR"/.claude/hooks/block-rm.sh
PostToolUseEdit"$CLAUDE_PROJECT_DIR"/.claude/hooks/lint-on-edit.sh

Slash commands (3)

/commit-staged/review-diff/ship

Permissions

deny (8)
Bash(rm -rf *)
Bash(sudo *)
Bash(curl * | bash)
Read(./.env)
Read(./.env.*)
Read(./secrets/**)
Edit(./.env)
Edit(./.env.*)
ask (4)
Bash(git push *)
Bash(git reset --hard *)
Bash(npm publish *)
Bash(npm install *)
allow (20)
Bash(npm test *)
Bash(npm run *)
Bash(git status)
Bash(git diff *)
Bash(git log *)
Bash(git add *)
Bash(git commit -m *)
Bash(git branch *)
Bash(git checkout *)
Bash(ls *)
Bash(cat *)
Bash(grep *)
Bash(find *)
Read(src/**)
Read(tests/**)
Read(docs/**)
Read(package.json)
Read(tsconfig.json)
Edit(src/**)
Edit(tests/**)

Similar rigs

copied ✓