Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
安装
npx skills add affaan-m/ECC --skill agent-architecture-auditnpx skills add affaan-m/ECC --skill agent-architecture-audit -a claude-code -gnpx skills add affaan-m/ECC --skill agent-architecture-audit -a codex -ggemini skills install https://github.com/affaan-m/ECC.git --path docs/ja-JP/skills/agent-architecture-auditgh skill install affaan-m/ECC agent-architecture-auditgit clone --depth 1 https://github.com/affaan-m/ECC /tmp/affaan-m__ECC
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/affaan-m__ECC/docs/ja-JP/skills/agent-architecture-audit ~/.claude/skills/agent-architecture-audit # Claude Code
cp -R /tmp/affaan-m__ECC/docs/ja-JP/skills/agent-architecture-audit ~/.agents/skills/agent-architecture-audit # Codex, Cursor, Gemini CLI, Copilot, OpenCode