affaan-m avatar

Agent Architecture Audit

This is a diagnostic workflow that systematically checks the 12-layer stack of agent applications for common failure patterns like wrapper regression, memory pollution, and hidden repair loops. You run it when your agent worked fine in the playground but breaks in production, or when users report degrading behavior after you've added prompt layers or memory systems. It searches your codebase for anti-patterns (tool requirements only in prompts, not code), maps failures to specific layers, and gives you severity-ranked findings with code-first fixes. The core insight is that most agent failures happen in the wrapper layers between the model and the user, not in the model itself. Worth running before any production release with tool calling or multi-step workflows.

skills.sh installs
5.8K
GitHub stars
300.3K
last updated
Aug 21, 2026

Install

$ npx -y skills add affaan-m/ecc --skill agent-architecture-audit --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent Architecture Audit

A diagnostic workflow for agent systems that hide failures behind wrapper layers, stale memory, retry loops, or transport/rendering mutations.

When to Activate

MANDATORY for:

  • Releasing any agent or LLM-powered application to production
  • Shipping features with tool calling, memory, or multi-step workflows
  • Agent behavior degrades after adding wrapper layers
  • User reports "the agent is getting worse" or "tools are flaky"
  • Same model works in playground but breaks inside your wrapper
  • Debugging agent behavior for more than 15 minutes without finding root cause

Especially critical when:

  • You've added new prompt layers, tool definitions, or memory systems
  • Different agents in your system behave inconsistently
  • The model was fine yesterday but is hallucinating today
  • You suspect hidden repair/retry loops silently mutating responses

Sponsors

Details

Repository
github.com/affaan-m/ecc
Categories
Code Review & Quality, AI & Agent Building
First seen
Jul 14, 2026

More from affaan-m/ecc

All 263
1claude-office-skills avatarcontract-reviewclaude-office-skills/skillsAnalyze contracts for risks, check completeness, and provide actionable recommendations. Supports employment contracts, NDAs, service agreements, and more.5.6Kskills.sh installs
2wshobson avatarreview-agent-setupwshobson/agentsConfigure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merge5.6Kskills.sh installs
3affaan-m avatarquality-nonconformanceaffaan-m/eccCodified expertise for quality control, non-conformance investigation, root cause analysis, corrective action, and supplier quality management in regulated manu5.4Kskills.sh installs
4affaan-m avatarrecsys-pipeline-architectaffaan-m/eccDesign composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI5.4Kskills.sh installs
5aaron-he-zhu avatarcontent-quality-auditoraaron-he-zhu/seo-geo-claude-skillscontent quality auditor5.1Kskills.sh installs
6jeffallan avatarangular-architectjeffallan/claude-skillsGenerates Angular 17+ standalone components, configures advanced routing with lazy loading and guards, implements NgRx state management, applies RxJS patterns, 5.1Kskills.sh installs