By jvishnefske
Verified Rust development with 4 layers (Requirements, TDD, Implementation, Verify) and maximum parallelism. Combines defense-in-depth verification with parallel task orchestration.
Analyze requirements and produce TOML task specification
Gate to run: requirements, tdd, implementation, verify
Generate Swiss Cheese validation report by running all layer gates
Begin TDD implementation from task specification
Run all verification gates (requirements, tdd, implementation, verify)
Layer 4: Implement safe Rust code to pass tests
Layer 1: Formalize requirements with Rust-specific constraints
4-layer verified development with maximum parallelism. Use for multi-module Rust development with requirements, TDD, implementation, and verification.
Layer 3: Write comprehensive tests BEFORE implementation
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin providing iterative Rust software development lifecycle tooling with multi-layer defect escape reduction methodology.
# Add Anthropic marketplace
/plugin marketplace add anthropics/claude-code
# Install plugin
/plugin install swiss-cheese
# Start with design review
/swiss-cheese "CAN-based motor controller"
# Answer all design review questions...
# Orchestrator runs 9-layer verification automatically
# Gates validate each layer by exit code
# Loop continues until ALL_GATES_PASS
| Command | Description |
|---|---|
/swiss-cheese | Start new verification with design review |
/swiss-cheese:gate N | Run gate N validation (exit 0=pass) |
/swiss-cheese:loop | Start iterative loop until completion |
/swiss-cheese:status | Show verification status |
/swiss-cheese:skip-layer N | Request layer skip (requires proof) |
/swiss-cheese:cancel | Cancel active loop |
┌─────────────────────────────────────────────────────────┐
│ Layer 9: Release Analysis → Gate 9 (exit 0/1) │
├─────────────────────────────────────────────────────────┤
│ Layer 8: Independent Review → Gate 8 (exit 0/1) │
├─────────────────────────────────────────────────────────┤
│ Layer 7: Dynamic Analysis → Gate 7 (exit 0/1) │
│ Miri, Fuzz, Coverage, Timing │
├─────────────────────────────────────────────────────────┤
│ Layer 6: Formal Verification → Gate 6 (exit 0/1/3) │
│ Kani, Prusti, Creusot │
├─────────────────────────────────────────────────────────┤
│ Layer 5: Static Analysis → Gate 5 (exit 0/1) │
│ Clippy, audit, deny, geiger │
├─────────────────────────────────────────────────────────┤
│ Layer 4: Implementation → Gate 4 (exit 0/1) │
│ Safe Rust, all tests pass │
├─────────────────────────────────────────────────────────┤
│ Layer 3: TDD Tests → Gate 3 (exit 0/1) │
│ Tests MUST FAIL (Red phase) │
├─────────────────────────────────────────────────────────┤
│ Layer 2: Architecture → Gate 2 (exit 0/1) │
│ Type-state, newtypes, ownership │
├─────────────────────────────────────────────────────────┤
│ Layer 1: Requirements → Gate 1 (exit 0/1) │
│ Formalized FR/SR/RC/TR │
└─────────────────────────────────────────────────────────┘
| Code | Meaning | Action |
|---|---|---|
| 0 | PASS | Advance to next layer |
| 1 | FAIL | Route to root cause layer |
| 2 | BLOCKED | Resolve prerequisites |
| 3 | SKIP | Approved skip |
The Orchestrator asks ALL questions upfront:
Using ralph-wiggum pattern:
/swiss-cheese:loop
→ Execute Layer N
→ Run Gate N
→ If PASS: advance
→ If FAIL: route to root cause
→ Stop hook blocks exit
→ Re-inject prompt
→ Continue until ALL_GATES_PASS
Convenience is NOT a valid reason.
Valid: "Pure lookup table with no arithmetic" Invalid: "We don't have time"
.swiss-cheese/
├── design-spec.yaml # Complete design specification
├── state.json # Verification state
├── loop-state.json # Loop iteration state
├── gates/ # Gate validation results
├── artifacts/
│ ├── layer-1/ # Requirements
│ ├── layer-2/ # Architecture
│ ├── layer-3/ # Tests
│ ├── layer-4/ # Implementation (src/)
│ ├── layer-5/ # Static analysis reports
│ ├── layer-6/ # Formal verification
│ ├── layer-7/ # Dynamic analysis
│ ├── layer-8/ # Review findings
│ └── layer-9/ # Release case
└── release/ # Release package
design-review: Upfront question methodologygate-validation: Exit code gate implementationswiss-cheese-patterns: Type-state, newtypes, no-panicnpx claudepluginhub jvishnefske/swiss-cheese --plugin swiss-cheeseRust development skill with strict coding standards, FAIL FAST error handling, and build/review agents
Comprehensive collection of specialized Rust development agents with Claude Code best practices. Includes rust-modern-apis skill for proactive suggestions of stable Rust APIs added in 1.89–1.97, loaded explicitly at session startup by rust-developer and rust-code-reviewer. team-develop skill for multi-agent collaborative development and team-debug skill for multi-agent root cause investigation (stops at consolidated review, awaits user decision on issues/epic/team-develop handoff), both via Claude Code experimental agent teams. continuous-improvement orchestrator spawns read-only rust-live-tester, rust-researcher, rust-arch-analyst, and rust-security-analyst agents for automated CI cycles; the arch-inspect and security-audit skills back the code-quality and vulnerability audits. Full-cycle SDD orchestrator with BRD/SRS/NFR pipeline (spec-from-stream skill). Autonomous tech-writer agent for user-facing documentation with progressive disclosure. rust-analyzer LSP integration for real-time code intelligence. Handoff protocol via rust-agent-handoff skill for context sharing. Adversarial critic agent for stress-testing designs. Updated for Rust Edition 2024 and modern tooling.
Rust development - cargo, clippy, testing, memory safety
Rust code review and development skills covering ownership, lifetimes, error handling, async/tokio, serde, sqlx, axum, macros, FFI, unsafe, concurrency, and testing patterns.
Comprehensive Rust development assistant with meta-question routing, coding guidelines, version queries, and ecosystem support
52 agent skills for systematic software development. Covers design, planning, TDD, code review, debugging, quality gates, and adversarial testing. 12 core skills are eval-tested with measured A/B deltas using Anthropic's skill evaluation framework.