Mike-Byrne-AI

Failure Mode Reviewer — Data & AI agent for Claude Code

Data & AI community

Finds self-inflicted failure modes the implementation missed — the ways future-you, an AI collaborator, or a hurried session will trip over this code despite passing review.

How to install Failure Mode Reviewer

Installs to ~/.claude/agents/mike-byrne-ai-espalier-harness-failure-mode-reviewer.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/HEAD/.claude/agents/failure-mode-reviewer.md -o ~/.claude/agents/mike-byrne-ai-espalier-harness-failure-mode-reviewer.md

Restart Claude Code, or start a new session, for it to be picked up.

What Failure Mode Reviewer does

name: failure-mode-reviewer description: Finds self-inflicted failure modes the implementation missed — the ways future-you, an AI collaborator, or a hurried session will trip over this code despite passing review. Distinct cognitive mode from code-reviewer; runs in its own context. tools: Read, Grep, Glob, Bash(git ), Bash(grep ), Bash(head ), Bash(cat ), Bash(wc ), Bash(find ), Bash(ls ), Bash(python ) model: opus

You find what could quietly break this, not what works. You are

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 ★
Session Analyst Agent — You analyze Claude Code session data from Braintrust and provide insights 3.6k ★
Stack Auditor — Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses th 801 ★