Config Reviewer — Data & AI agent for Claude Code
Adversarial reviewer that audits .claude/ configurations for bloat, redundancy, LLM capability duplication, and missing Anthropic features.
How to install Config Reviewer
Installs to ~/.claude/agents/dialpad-dialtone-config-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dialpad/dialtone/HEAD/.claude/agents/config-reviewer.md -o ~/.claude/agents/dialpad-dialtone-config-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Config Reviewer does
description: "Adversarial reviewer that audits .claude/ configurations for bloat, redundancy, LLM capability duplication, and missing Anthropic features. Run to get a health score and actionable recommendations." tools:
- Bash
- Read
- Glob
- Grep memory: scope: project
Config Reviewer Agent
Audits `.claude/` configurations with a devil's advocate mindset. Identifies bloat, redundancy, and missed opportunities before they accumulate into the anti-patterns seen in over-engin
Alternatives in Data & AI
- Info Disclosure — Information Disclosure specialist (H1 #18, CWE-200/209/215/538/668/798) 812 ★
- LLM Expert — Use this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling 434 ★
- Review Code Robustness — A code review agent that checks analysis scripts for fragile patterns, missing error handling at data boundari 134 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Edc Skill Defender
EDC sub-agent. Defends the FlatRedBall2 skill files as curated AI playbooks. Argues for lean, generalizable sk
Agent Capability Analyst
Advanced specialist in AI agent capability analysis with enhanced scoring algorithms, semantic matching for na
Gap Finder
Analyzes a venture's AI usage across 10 production functions and identifies high-value gaps where AI could cre
Duplication Detector
Detects stories with overlapping implementation concerns using hybrid keyword pre-filter and LLM semantic veri
Scaffold Inspect
Sets up inspect-ai evaluation configurations for all runs in a designed experiment. Reads experiment_summary.y
Modularity Reviewer
Inferential modularity review grounded in the deterministic coupling data. Reads specs/brownfield/modularity-p
Related Skills
Ad Creative Evaluator
Score any video ad with an AI expert panel. Get structured feedback across 8 dimensions with actionable improv
Context Health Check
Run a structured health check on the current conversation context and report its quality score with actionable
DB Health
Supabase / Postgres health audit: missing indexes, slow queries via pg_stat_statements, unused indexes, table