~ / leaderboard / skill / agent-architecture-audit
Skill · #882
agent-architecture-audit
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.
8rigs use it
0%of all rigs
26.3kavg rig context tax
Get it
$ npx degit affaan-m/ECC/docs/ja-JP/skills/agent-architecture-audit .claude/skills/agent-architecture-audit From the most-starred rig that ships it: affaan-m/ECC. Same-named skills in different rigs may differ — review before use.
Often used together with
accessibility · 8backend-patterns · 7coding-standards · 7architecture-decision-records · 7content-engine · 7article-writing · 7agent-introspection-debugging · 7crosspost · 7agentic-engineering · 7deployment-patterns · 7
Rigs using agent-architecture-audit (8)
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.
MCP Hoarder 58.4k tok ·
mturac/everything-openai-codex
EOC: open-source operating system for OpenAI Codex workflows with agents, skills, hooks, rules, memory, safety gates, and cross-harness adapters.
MCP Hoarder 47.1k tok ·
ysyecust/everything-claude-code
Complete collection of Claude Code configs for C++20 HPC development - agents, skills, hooks, commands, and rules
MCP Hoarder 56.9k tok ·
shipshitdev/skills
Claude, Cursor, Codex skills and commands
Skill Collector 10.4k tok ·
socialadsmentor/sam-agentic-harness
A working Claude Code harness scrubbed from a production agency setup: always-on rules, on-demand skills, hooks, model-scored subagents, three-tier memory, and a self-improvement loop gated by human approval. The installer checks fit and wa
Skill Collector 5.9k tok ·
baselane-sh/baselane
Git-native package manager for AI coding-agent configs — audit a repo, apply workflow packs, and keep CLAUDE.md/AGENTS.md in sync.
Orchestrator 13.1k tok ·
goharabbas321/zeoel-framework
A production-grade multi-agent orchestration framework for building enterprise-grade products. Powered by **22 highly specialized AI agents**, isolated Git Worktrees, strict Red-Green-Refactor TDD, and rigorous multi-stage verification.
Orchestrator 10.2k tok ·
chefcurry30the-boop/claude-dotfiles
Portable Claude Code + Cursor config: skills, agents, settings — sync across machines
Skill Collector 8.0k tok ·