ase
ASE automates routine development tasks and code generation workflows, reducing manual effort and allowing teams to focus on architecture and critical logic …
Dr. Ralf S. Engelschall's opinionated toolkit for fusing agentic AI coding with traditional software engineering in Claude Code (reduced support for GitHub Copilot CLI and OpenAI Codex CLI). Ships agent hooks, skills, an MCP service, and a CLI for plan-driven, human-in-the-loop development: named persisted plans, plan stress-testing, implementation preflights, and cost-reducing personas.
- Ask Claude to generate boilerplate code for a new microservice with standard patterns
- Automate creation of API endpoint scaffolding with request validation and error handling
- Generate unit test suites for existing functions to improve code coverage quickly
ASE automates routine development tasks and code generation workflows, reducing manual effort and allowing teams to focus on architecture and critical logic rather than boilerplate.
Development teams adopting AI-assisted workflows seeking to accelerate delivery cycles while maintaining code quality standards.
By rse
How to Get It
npm install -g @rse/ase && ase setup install --tool claude
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Generate boilerplate code for a new microservice with standard patterns
Trust Signals Auto-scanned
Community Pulse Growing
Discussed on Hacker News
- Agentic Software Engineering (ASE): Agentic AI Coding Meets Software Engineering — Hacker News · 2 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 36 GitHub stars; contributors unknown; last commit 1d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 36 GitHub stars; contributors unknown; last commit 1d ago; license Apache-2.0.