Back to directory

ECC

A plugin that adds agents, skills, hooks, rules and memory to AI coding tools such as Claude Code and Codex, so they plan, test, review and verify changes.

ECC

ECC gives an AI coding agent a structured engineering process: plan, test, implement, review, verify, remember and improve. It works best with Claude Code, has a sync path for Codex, and provides limited adapters for Cursor, OpenCode, Gemini, Zed, GitHub Copilot and other harnesses.

It includes 68 agents for planning, review, build repair, security and architecture, 292 skills, command shims, hooks, selectable rules, session memory and continuous learning. Its AgentShield component scans prompts, hooks, MCP configuration, permissions, secrets and agent files.

ECC is MIT licensed, with a paid hosted GitHub App for private repositories.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.