Brainstorm, plan, review, and ship with shared workflow contracts and principle-based reviewers.
Explore requirements and approaches before writing a requirement document.
Prepare branch state safely, create focused commits, and open a PR using shared workflow logic.
Transform a feature description or brainstorm into an executable requirement document.
Review and resolve pull request feedback with focused fixes and clear responses.
Run parallel principle reviews against local changes or a PR target.
Use before writing requirements when scope, intent, trade-offs, or success criteria are unclear.
Prepare branch state safely, create focused commits, and open a high-signal PR.
Transform a feature description or brainstorm output into an executable requirement document.
Process PR review comments end-to-end by implementing valid fixes and responding clearly to non-actioned feedback.
Claude adapter for the shared brainstorming workflow and skill.
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.
Workflows, principles, and review system for AI-native software teams. Distributed as a Claude Code marketplace plugin.
In Claude Code:
/plugin marketplace add travisfischer/agent-engineering
/plugin install agent-engineering@agent-engineering
That's it — the plugin lives in Claude Code's plugin cache, not in your project repo. Nothing is copied into your codebase as a side effect of install.
Five slash commands:
| Command | Purpose |
|---|---|
/project:brainstorm | Explore requirements and approaches before writing requirements. |
/project:plan | Turn a brainstorm into a structured plan. |
/project:review | Review staged changes against active principle reviewers. |
/project:pr-feedback | Process and apply PR feedback. |
/project:open-pr | Draft and open a PR with proper framing. |
Plus a principle-based review system with two principle sets:
principles/core/ — six core product/team principles (agent-native, autonomous-learning, llm-model-fluid, markdown-everything, universal-evals).principles/how-we-build/ — twelve "how we build" principles (quality-first, security-and-privacy, observability-and-incidents, sacred-schema, and more).Reviewers run from workflows/review/reviewers.md. To narrow the active set, copy a preset to review.local.md at your host repo root or write a custom one — see the inner README.
This repo is a Claude Code plugin marketplace:
.
├── .claude-plugin/
│ └── marketplace.json # marketplace manifest
└── plugins/
└── agent-engineering/ # the plugin
├── .claude-plugin/
│ └── plugin.json
├── .codex-plugin/ # Codex runtime support
├── skills/ # canonical + adapter skills
├── commands/ # slash command definitions
├── workflows/ # workflow contracts
├── principles/ # principle docs (the review source-of-truth)
├── review.presets/ # ready-made reviewer configurations
├── README.md
├── CHANGELOG.md
└── LICENSE
See the inner README for the plugin-internal layout and configuration details.
Workflows write outputs into your host repo:
plans/brainstorms/plans/requirements/plans/reviews/These are most useful when committed and accumulate as durable team context.
plugins/agent-engineering/principles/core/ or principles/how-we-build/.plugins/agent-engineering/workflows/review/reviewers.md using reviewer_type: principle and pointing principle_doc to the new file (relative to ${CLAUDE_PLUGIN_ROOT}).Codex adapters are under plugins/agent-engineering/.codex-plugin/. Codex marketplace install is not yet wired up; for now Codex users can clone and reference these directly.
npx claudepluginhub travisfischer/agent-engineering --plugin agent-engineeringHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.