affaan-m/ECC

This page introduces an external open-source repository. It is not an HDATF product.

What it does

ECC adds skills, memory and security checks to coding agents such as Claude Code, Codex, Opencode and Cursor. It makes the agent plan before building, verify changes with tests and review its own work in a fresh context.

How it helps ATF

Worth comparing with Harness, which hands work to executors like Claude Code and Codex and checks the result. ECC's test-based verification and fresh-context review could be a reference for Harness's evidence checks.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• blader/humanizer
  An agent skill written in Markdown that rewrites AI-sounding text so it reads like a person wrote it, without changing its meaning. It can follow a writing sample to match the user's voice.
• coreyhaines31/marketingskills
  A collection of AI agent skills for marketing tasks such as conversion optimization, copywriting, SEO, analytics and growth engineering. It works with Claude Code, OpenAI Codex, Cursor, Windsurf and other agents that support the Agent Skills spec.
• VoltAgent/awesome-openclaw-skills
  A curated list of OpenClaw skills. It gathers more than 5,400 skills filtered and sorted into categories from the official OpenClaw Skills Registry.
• sickn33/agentic-awesome-skills
  A catalog of more than 2,100 agent skills with AAS Core, a local CLI and read-only MCP server. Codex or Claude picks exact skills from the catalog, and AAS Core validates the selection and previews a plan before changes.
• multica-ai/andrej-karpathy-skills
  A single CLAUDE.md file, based on Andrej Karpathy's observations on LLM coding pitfalls, that gives Claude Code four principles: think before coding, simplicity first, surgical changes and goal-driven execution.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.