compound-engineering-plugin: AI coding-agent skills that structure engineering work into a repeating loop of planning, execution, review, and reusable learning.
What problem it solves
Traditional development accumulates technical debt and leaves important knowledge scattered, forcing later changes to rediscover context. The plugin addresses this by turning each engineering cycle into a structured workflow and writing durable learnings into artifacts that subsequent cycles can use as grounding.
Key features
Structured engineering loop — A six-step cycle moves from requirements and planning through implementation, simplification, review, and learning capture. The resulting context can inform the next cycle.
Source: README
Reusable knowledge capture — The compound step records durable learnings so later brainstorming and planning can read and apply them. Artifact folders can also be relocated under a configurable repository-relative root.
Source: README
Planning and review workflow — Interactive brainstorming produces a requirements-only plan, planning turns it into an implementation-ready artifact, and review checks the result against the plan. A simplification step is included before review.
Source: README
Autonomous delivery pipeline — The `/lfg` command can run the full pipeline hands-off, including work, simplification, review fixes, learning capture, browser tests, and commits. With a configured remote, it can push, open a pull request, and monitor CI without merging unless permission is granted.
Source: README
Broad agent-host support — The plugin provides installation and invocation guidance for Claude Code, Cursor, Codex, and other supported coding-agent hosts. Its skills are grouped into core, on-demand, Git workflow, autonomous, testing, collaboration, and utility categories.
Source: README, skills
Quick start
Copied verbatim from the project's README.
/plugin marketplace add EveryInc/compound-engineering-plugin
/plugin install compound-engineering/ce-brainstorm make background job retries safer
/ce-plan
/ce-work
/ce-simplify-code
/ce-code-review
/ce-compoundWho it may suit
This may suit engineering teams and individual developers who use AI coding agents and want a repeatable way to plan, review, ship, and preserve project knowledge.
Topics to discuss
How should durable learnings be structured so they remain useful without adding excessive project noise?
Which boundaries between autonomous execution and explicit human review work best for different repositories?
How can shared Compound Packs encode organizational rules while remaining practical for day-to-day planning and review?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/EveryInc/compound-engineering-plugin#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…