Open-source plugins for Claude Code — AI-powered developer tools that extend Claude's capabilities with specialized workflows.
- Claude Code CLI installed and authenticated
- For mutation-guard: Go 1.21+ (other languages coming soon)
| Plugin | What It Does | Languages | Status |
|---|---|---|---|
| mutation-guard | Test quality analysis via mutation testing — detects false confidence where high coverage hides weak assertions | Go (PHP, Node.js, Java, Rust planned) | ✅ Active |
claude plugins add github:rezafarzaneh7/claude-code-plugins/plugins/mutation-guardcd ~/projects/my-go-service
claude# See where your tests have gaps
/mutation-guard ./services
# Auto-write tests that close those gaps
/mutation-guard-fix ./services# Install the plugin (one-time)
$ claude plugins add github:rezafarzaneh7/claude-code-plugins/plugins/mutation-guard
# Navigate to your Go project
$ cd ~/projects/my-api
# Start Claude Code
$ claude
# Inside Claude Code — analyze your handlers package
> /mutation-guard ./internal/handlers
# Claude will:
# 1. Detect Go from go.mod
# 2. Install go-mutesting if missing
# 3. Run coverage analysis
# 4. Run mutation testing
# 5. Produce a quality report with impact analysis
# Now fix the gaps it found
> /mutation-guard-fix ./internal/handlers
# Claude will:
# 1. Read your existing test patterns
# 2. Write tests that kill survived mutants
# 3. Verify all new tests pass
# 4. Show a before/after comparison## Mutation Guard — Quality Report
**Project**: my-service | **Language**: Go | **Scope**: ./services
### TL;DR
| Metric | Score | Trend |
|-----------------|--------|-------|
| Coverage | 72.4% | 🆕 |
| Mutation Score | 58.3% | 🆕 |
| Quality Verdict | ⚠️ False Confidence | ⚠️ |
High coverage masks weak assertions — 5 critical gaps found.
### Quality Matrix
| # | File | Coverage | Mutation | Verdict |
|---|-----------------|----------|----------|---------------------|
| 1 | handler.go | 89.2% | 42.1% | ⚠️ False Confidence |
| 2 | service.go | 76.5% | 71.4% | 🟡 Partial |
| 3 | repository.go | 45.0% | 33.3% | 🔴 Critical |
### TL;DR
> 7 tests written | 5 mutants killed
> Coverage: 72.4% → 84.1% (↑ +11.7%)
> Mutation Score: 58.3% → 78.9% (↑ +20.6%)
- Detect — auto-identifies project language from build files (
go.mod,package.json, etc.) - Coverage — runs language-native coverage tools to measure what code tests execute
- Mutate — injects small bugs (mutants) and checks if tests catch them
- Impact — classifies survived mutants by production risk (Critical → High → Medium)
- Fix — writes missing tests that kill survived mutants, matching your existing test patterns
The key insight: coverage measures what tests touch, mutation score measures what tests catch. A file with 90% coverage and 40% mutation score has tests that run the code without actually verifying behavior.
| Language | Coverage Tool | Mutation Tool | Status |
|---|---|---|---|
| Go | go test -cover |
go-mutesting | ✅ Active |
| PHP | phpunit --coverage |
Infection | 🔜 Planned |
| Node.js | jest --coverage / nyc |
Stryker | 🔜 Planned |
| Java | jacoco |
PIT | 🔜 Planned |
| Rust | cargo tarpaulin |
cargo-mutants | 🔜 Planned |
See CONTRIBUTING.md for how to add a new plugin or improve an existing one.