ASE turns Claude Code into a structured engineering workflow

Agentic Software Engineering (ASE) is now publicly available. ASE is an Apache-2.0 open-source toolkit by Dr. Ralf S.

Engelschall, built to run as a plugin for Anthropic’s . Its goal is to connect AI coding with normal software engineering habits, so an agent does more than quickly produce code. The toolkit includes agent hooks, configurable agent skills, a (MCP) service, and a companion .

Its scope covers idea generation, web search, asking other LLMs, comparing answers, finding components, weighing options, checking claims, finding root causes, managing tasks, reviewing plans, analyzing code, fixing code, refactoring code, writing new code, reviewing changes, and creating changelog entries. The wider reaction around similar tools points to the same pattern: coding agents such as Claude Code, Codex, Gemini, and Cursor can save time, but loose use can also create weaker code, bigger-than-planned work, and repeated explanation of the same . Related local tools for shared MCP memory and outcome-based show a growing push to make coding agents more disciplined and reusable, not just faster.

Key points

  • ASE is an open-source toolkit for .
  • It packages software engineering tasks into agent-driven workflows.
  • It includes agent hooks, agent skills, a (MCP) service, and a .
  • The broader trend is discipline around coding agents, not just faster .
  • s should test it on one repeated workflow before adopting the whole toolkit.

Sources covering this story (11)

Read original