ICM-style numbered-stage scaffold + 22 vendored lifecycle skills. Master plugin for building software products with Claude Code.
Advance to the next stage (or roll back via --back NN-stage). Validates exit criteria + writes state.
Scaffold a new Enhanced Agentic Flow project — numbered stages + lifecycle skills.
Enter a stage. Loads L0 + L1 + the stage's L2 CONTEXT.md and resolves its Inputs table.
Print current EAF state — stage, exit-criteria progress, handoff history.
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
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.
Master plugin for building software products with Claude Code. Fuses two ideas:
EAF gives you the stages (workspace). The vendored skills give you the playbook. Stage CONTEXT.md files dispatch the right skills at the right phase.
When you scaffold a project (/eaf-init my-app or npx create-eaf-app my-app), you get:
my-app/
├── CLAUDE.md # L0 — always-loaded invariants
├── CONTEXT.md # L1 — workspace routing
├── shared/_config/ # L3 — cross-cutting config (tech stack, style, cross-cutting skills)
├── stages/
│ ├── 00-define/ (interview-me, idea-refine)
│ ├── 01-plan/ (spec, planning, api-design)
│ ├── 02-build/ (incremental, TDD, source-driven, frontend)
│ ├── 03-verify/ (browser-testing, debugging)
│ ├── 04-review/ (quality, simplify, security, perf)
│ ├── 05-ship/ (git, ci/cd, launch, ADRs)
│ └── 06-operate/ (deprecation-and-migration — steady state)
└── .eaf/state.json # stage pointer + handoff history
Each stage has its own CONTEXT.md (the dispatcher), references/ (inputs), and output/ (formal handoff artifacts for the next stage).
/plugin marketplace add liam-ai-reality/enhanced-agentic-flow
/plugin install enhanced-agentic-flow@enhanced-agentic-flow
Then in any new directory:
/eaf-init my-app
npx create-eaf-app my-app
# or
npx --prefix /path/to/enhanced-agentic-flow create-eaf-app my-app
This works without Claude Code; the resulting directory is meant to be opened in Claude Code afterward.
| Command | What it does |
|---|---|
/eaf-init <name> | Scaffold a new project tree. |
/eaf-stage [N] | Enter stage N (or current). Loads L0+L1+L2 context and lists skills. |
/eaf-handoff [--back NN] | Advance to the next stage (or roll back). Validates exit criteria + outputs. |
/eaf-status | Show current stage, exit-criteria progress, recent handoffs. |
npx create-eaf-app my-app && cd my-app/eaf-stage 0. Agent loads CLAUDE.md + CONTEXT.md + stages/00-define/CONTEXT.md, then invokes interview-me.stages/00-define/output/CONCEPT.md. Tick exit-criteria. /eaf-handoff.01-plan. stages/01-plan/references/00-define-output is symlinked to ../00-define/output/.06-operate. Use /eaf-handoff --back 01-plan if you need to revisit.Some skills aren't stage-bound — they auto-fire when triggers match:
context-engineering (always, via L0)doubt-driven-development (confidence checks)code-simplification (post-edit in stages 02, 04)security-and-hardening (auth/crypto/secrets file globs)debugging-and-error-recovery (first test failure)See skills/eaf-scaffold-project/templates/shared/_config/cross-cutting.md and hooks/stage-transition.json.
22 lifecycle skills + 1 meta (using-agent-skills) are vendored from addyosmani/agent-skills (MIT). The 24th skill, eaf-scaffold-project, is EAF-native. See references/skills-provenance.md for the upstream commit SHA and re-sync procedure.
npm test
Runs tests/scaffold.spec.js, which scaffolds into a temp dir and asserts the tree shape matches references/scaffolded-tree.md.
MIT.
npx claudepluginhub liam-ai-reality/enhanced-agentic-flow --plugin enhanced-agentic-flowComprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.