AI Decision Auditor — Data & AI agent for Claude Code
Use this agent when you need to review and refactor code that contains hard-coded deterministic logic that should instead use AI-based decision making with transparency.
How to install AI Decision Auditor
Installs to ~/.claude/agents/kody-w-ai-agent-templates-ai-decision-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/kody-w/AI-Agent-Templates/HEAD/.claude/agents/ai-decision-auditor.md -o ~/.claude/agents/kody-w-ai-agent-templates-ai-decision-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What AI Decision Auditor does
name: ai-decision-auditor description: Use this agent when you need to review and refactor code that contains hard-coded deterministic logic that should instead use AI-based decision making with transparency. This agent identifies rigid conditional statements, business rules, or threshold-based logic that would benefit from probabilistic reasoning, and replaces them with AI-powered decisions that include confidence scores and detailed explanations. Context: The user wants to review
Alternatives in Data & AI
- Svelte Correctness Review — Reviews a feature segment in any SvelteKit app (apps/moderator, apps/auth, apps/creator-studio) for correctnes 7.2k ★
- Credential Hunter — Autonomous credential-attack pipeline runner 4.5k ★
- Specialized AI Agents — This directory contains specialized AI agent definitions used by Claude Code to handle complex, domain-specifi 357 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
GPT Advisor
Obtains an independent GPT opinion on a disputed technical decision and provides an honest synthesis of the tw
ADR Indexer
Use to generate a readable, navigable index page of all Architecture Decision Records (ADRs) in a repository m
Setup Auditor
Read-only diagnostic agent that audits the project's AI setup (CLAUDE.md, skills, docs, rules). Use when you w
Agent Architect
Use this agent when you need to design, optimize, or refactor AI agent systems. Specifically:\n\n \nContext: U
Aeo AI Scorer
Use only for an explicitly requested experimental content-quality review alongside the deterministic aeoptimiz
Analyse
Use for deep analysis tasks — break down problems, evaluate options, find root causes, surface insights from d
Related Skills
Stop Protocol
STOP — Skill Transparency & Observability Protocol. Making Agent Skills transparent, debuggable, and trustwort
Architecture Compose Resource Limit Env Substitution
Planning pattern for exposing hard-coded docker-compose deploy.resources limits/reservations (cpus, memory) as
Hyperliquid Trading Agent
LLM-driven crypto trading agent for Hyperliquid paper-trading. 3-layer architecture: research + quant signals