Reliability Analyst — Development agent for Claude Code
Use this agent when the user explicitly requests interpretation of an existing agent-evals report.
How to install Reliability Analyst
Installs to ~/.claude/agents/beibeihk-claude-code-agent-evals-reliability-analyst.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/beibeihk/claude-code-agent-evals/HEAD/agents/reliability-analyst.md -o ~/.claude/agents/beibeihk-claude-code-agent-evals-reliability-analyst.md Restart Claude Code, or start a new session, for it to be picked up.
What Reliability Analyst does
name: reliability-analyst description: Use this agent when the user explicitly requests interpretation of an existing agent-evals report. Never launch automatically. Context: user has a local report. user: "Interpret this reliability report." assistant: "I will ask the reliability analyst to distinguish evidence from hypotheses." User explicitly requested interpretation. model: inherit color: cyan tools: Read
You are a reliability analyst. You
Alternatives in Development
- Codebase Scout — Explores codebase structure, affected files, blast radius, related tests, and local conventions for a focused 548 ★
- Claude Context Local — Code search MCP for Claude Code 201 ★
- Discovery Agent — Expert in Phase 1 discovery and context gathering for the plan workflow 85 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
n8n Workflow Validator
Use this agent to validate an existing n8n workflow (either by ID in the user's n8n instance or a local JSON f
Aichor Experiment Launcher
Use this agent when the user explicitly requests to launch a run/experiment on aichor, or when another agent h
Sanitizer Expert
Use when analyzing an existing sanitizer report (ASan, TSan, UBSan, MSan output) and you want a focused interp
Bounded Executor
Use for one coherent local implementation only when explicitly assigned isolated edit custody and the parent s
Harness Optimizer
Analyze and improve the local agent harness configuration for reliability, cost, and throughput.
Packaging Engineer
Build and verify a local Windows Electron package, including inference runtime, model assets and offline launc
Related Skills
Agent Reliability Harness
Evals, tracing and CI regression gates for tool-using agents: tool-selection, final-state, cost, latency and s
Bar Interpret
Generate BAR Observatory's optional self-improvement report (engineering or executive audience)
Vf Check
Run a vibe-force check (format, lint, analyzer, jest, static, local, apex, smoke, verify, all), interpret the