alinaqi

Claude Bootstrap — Security skill for Claude Code

Security community intermediate

Opinionated project initialization with security-first guardrails, spec-driven atomic todos, LLM testing patterns, and CLI tool orchestration (gh, vercel, supabase).

How to install Claude Bootstrap

This entry records only its repository, not the path inside it, so there is no exact command to give. Open alinaqi/claude-bootstrap and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claude Bootstrap does

An opinionated project initialization system for Claude Code. **Agent teams by default, strict TDD pipeline, multi-engine code review, security-first.**

Alternatives in Security

Free Code — The free build of Claude Code 8.1k ★
Trail Of Bits Claude-code-config — Opinionated production defaults from a top security firm: sandboxing, permissions, hooks, skills, MCP server c 1.6k ★
Promptmap — Security scanner for custom LLM apps 1.2k ★

README

Claude Bootstrap

An opinionated project initialization system for Claude Code. **Agent teams by default, strict TDD pipeline, multi-engine code review, security-first.**

**The bottleneck has moved from code generation to code comprehension.** AI can generate infinite code, but humans still need to review, understand, and maintain it. Claude Bootstrap provides guardrails that keep AI-generated code simple, secure, and verifiable.

**New in v2.5.0:** Every project now runs as a coordinated team of AI agents. A Team Lead orchestrates, a Quality Agent enforces TDD, a Security Agent scans for vulnerabilities, a Code Review Agent runs multi-engine reviews, a Merger Agent creates PRs, and dedicated Feature Agents implement each feature in parallel - all following an immutable pipeline: **Spec > Tests > Fail > Implement > Pass > Review > Security > PR.**

Core Philosophy

┌────────────────────────────────────────────────────────────────┐
│  ITERATIVE LOOPS BY DEFAULT                                    │
│  ─────────────────────────────────────────────────────────────│
│  Every task runs in a self-referential loop until tests pass.  │
│  Claude iterates autonomously. You describe what, not how.     │
│  Powered by Ralph Wiggum - iteration > perfection.             │
├────────────────────────────────────────────────────────────────┤
│  TESTS FIRST, ALWAYS                                           │
│  ─────────────────────────────────────────────────────────────│
│  Features: Write tests → Watch them fail → Implement → Pass    │
│  Bugs: Find test gap → Write failing test → Fix → Pass         │
│  No code ships without a test that failed first.               │
├────────────────────────────────────────────────────────────────┤
│  SIMPLICITY IS NON-NEGOTIABLE                                  │
│  ─────────────────────────────────────────────────────────────│
│  20 lines per function │ 200 lines per file │ 3 params max     │

...