affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
About the project
A performance optimization system for coding agents: a set of agents, skills, memory, and rules that adds a plan-test-review-remember workflow to Claude Code, Codex, Cursor, and other harnesses.
Useful for
- Install the agent and skill pack into Claude Code via npx ecc-universal setup
- Configure ECC for Claude Code, Codex, and Kimi Code at once with the guided wizard
- Run AgentShield scanning over prompts, MCP configs, and secrets in agent files
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 511 stars today.
- Interest is fading: the two-day pace is 55% of the previous week and a half.
- GitHub Trending this week: #2, +8,086 stars.
- About 81 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 257,737
- Stars in a day
- 517
- Forks
- 38,547
- Issues and pull requests
- 2,967
- Watchers
- 1,307
- Language
- JavaScript
- License
- MIT
- Latest release
- v2.2.1 · September 8, 2026
- Created
- January 18, 2026
- Last push
- September 12, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 13, 2026GitHub Trending this week: #2, +8,086 stars
Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.