By quangphu1912
Codebase analysis, reverse engineering, and development orchestration — 32 skills covering reconnaissance, deep investigation, TDD, debugging, planning, and code review
Multi-scenario reasoning agent that tests how system behavior changes under different gate combinations, feature flag states, and configuration values
Deep multi-step codebase exploration — traces call chains, maps execution paths, follows imports across files, and builds comprehensive understanding of specific subsystems
Production readiness code review — reviews implementation against plan, checks quality, architecture, testing, and security
Use when tracing turn loops, tool continuations, state transitions, or understanding how an AI agent or complex system actually processes requests through its execution cycle
Use when understanding how source transforms to runtime, what gets filtered/compiled/generated, or tracing build-time shaping that affects what code actually runs
Use when separating prompt-driven behavior from code-driven behavior, understanding what system prompts actually control vs what's hardcoded, or testing how behavior changes under different prompt configurations
Use when evaluating code health, finding bug hotspots, identifying anti-patterns, preparing a quality improvement plan, or assessing technical debt
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design 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.
Progressive-depth codebase analysis and reverse engineering plugin for Claude Code, OpenCode, and Codex.
/plugin marketplace add quangphu1912/ai-plugins
/plugin install codebase-analyzer@ai-plugins
/reload-plugins
Add codebase-analyzer to the plugin array in your opencode.json (global or project-level):
{
"plugin": ["codebase-analyzer@git+https://github.com/quangphu1912/codebase-analyzer.git"]
}
Restart OpenCode. The plugin auto-installs and registers all 32 skills.
Verify installation by checking that ~/.cache/opencode/node_modules/codebase-analyzer/ exists, or ask OpenCode: "What analysis skills do you have?"
See .opencode/INSTALL.md for pinning versions and troubleshooting.
/plugin marketplace update ai-plugins
/plugin update codebase-analyzer
/reload-plugins
| Skill | Purpose |
|---|---|
/codebase-analyzer:using-codebase-analyzer | Auto-loaded entry point — routes to the right skills |
/codebase-analyzer:classify-analysis-target | Determine what we're analyzing (runs first) |
| Skill | Purpose |
|---|---|
/codebase-analyzer:identifying-tech-stack | Framework/library/version detection |
/codebase-analyzer:mapping-architecture | Component relationships, layers |
/codebase-analyzer:tracing-dependencies | Coupling, circular deps |
/codebase-analyzer:detecting-dead-code | Unused code, orphaned files |
/codebase-analyzer:inventorying-api-surface | Public interfaces, endpoints |
/codebase-analyzer:analyzing-code-quality | Anti-patterns, hotspots |
| Phase | Skills | Purpose |
|---|---|---|
| 1. Establish Truth | trace-codebase-provenance, analyze-build-pipeline | Git archaeology, build reality |
| 2. Map Runtime | classify-repo-artifacts, analyze-agent-loop, trace-data-flows | Artifact classification, loops, data flows |
| 3. Gates & Behavior | extract-tool-graph, map-feature-gates, simulate-behavior, analyze-prompt-influence | Tool maps, feature gates, scenario testing |
| 4. System Intent | reconstruct-system-intent | What the system was built to do |
| Skill | Purpose |
|---|---|
/codebase-analyzer:detect-hidden-contracts | Find implicit APIs and undocumented contracts |
/codebase-analyzer:test-hypothesis | Hypothesis-driven targeted analysis |
| Skill | Purpose |
|---|---|
/codebase-analyzer:brainstorming | Design-first approach before implementation |
/codebase-analyzer:writing-plans | Break specs into bite-sized tasks |
/codebase-analyzer:subagent-driven-development | Fresh subagent per task, review between |
/codebase-analyzer:executing-plans | Batch execution with checkpoints |
/codebase-analyzer:dispatching-parallel-agents | Concurrent subagent dispatch |
/codebase-analyzer:test-driven-development | RED-GREEN-REFACTOR cycle |
/codebase-analyzer:systematic-debugging | Root cause investigation process |
/codebase-analyzer:verification-before-completion | Verify commands pass before finishing |
/codebase-analyzer:using-git-worktrees | Isolated parallel workspace management |
/codebase-analyzer:finishing-a-development-branch | Merge/PR workflow |
/codebase-analyzer:requesting-code-review | Dispatch code-reviewer agent |
/codebase-analyzer:receiving-code-review | Process and apply review feedback |
Analysis workflow: Track A scans the surface. When it finds signals worth investigating deeper (with confidence scores), it offers to trigger Track B's phased deep dive. You can also jump straight to any skill or start a hypothesis test.
Development workflow: The bootstrap skill also routes development triggers ("build", "plan", "debug", "test", "review") to orchestration skills cloned from the superpowers plugin. These skills provide structured development lifecycles — brainstorming, planning, implementation, testing, and review.
npx claudepluginhub quangphu1912/codebase-analyzer --plugin codebase-analyzerSmart codebase exploration with dependency mapping and structure analysis
Codebase exploration, refactoring, and quality analysis
AI-powered codebase understanding assistant. Learn design patterns, analyze impact, trace code flows, and understand any codebase through information theory principles. Includes 6 Agent Skills for automatic analysis triggering.
Generate comprehensive analysis and documentation of entire codebase
Live codebase visualization and structural quality gate — 14 health dimensions graded A-F, dependency analysis, and architecture governance via MCP
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.