Independent auditor that checks whether the agent's stated verdict — claims like "the fix works", "tests pass", "root cause is X", "deploy is healthy", "found N issues" / "no issues", "<thing> is removed/unused", "done" — is backed by concrete, re-runnable proof rather than…
How to install verdict-auditor?
boxlite-ai/boxlite/verdict-auditor
$curl -o .claude/agents/verdict-auditor.md https://raw.githubusercontent.com/boxlite-ai/boxlite/HEAD/.claude/agents/verdict-auditor.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install verdict-auditor by running `curl -o .claude/agents/verdict-auditor.md https://raw.githubusercontent.com/boxlite-ai/boxlite/HEAD/.claude/agents/verdict-auditor.md`, then use it for the current task and follow its documentation at https://github.com/boxlite-ai/boxlite.
Related
6 picksType
- debuggerRoot-cause analysis, regression isolation, stack trace analysis, build/compilation error resolutionJul 2026
- exploreCodebase search specialist for finding files and code patternsJul 2026
- tracerEvidence-driven causal tracing with competing hypotheses, evidence for/against, uncertainty tracking, and next-probe recommendationsJul 2026
- performance-analystThe Performance Analyst profiles game performance, identifies bottlenecks, recommends optimizations, and tracks performance metrics over time. Use this agent for performance profiling, memory…May 2026
- debuggerUse this agent when encountering errors, test failures, unexpected behavior, or any issues that require root cause analysis. The agent should be invoked proactively whenever debugging is needed.Jul 2026
- explorerRead-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.Jul 2026
