Reproducibility Auditor — Research agent for Claude Code
Reviews research workflows for reproducibility gaps — hidden dependencies,\.
How to install Reproducibility Auditor
Installs to ~/.claude/agents/flonat-claude-research-reproducibility-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/flonat/claude-research/HEAD/.claude/agents/reproducibility-auditor.md -o ~/.claude/agents/flonat-claude-research-reproducibility-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Reproducibility Auditor does
name: reproducibility-auditor
fidelity: high
oversight: high
description: "Reviews research workflows for reproducibility gaps — hidden dependencies,\
\ absolute paths, undocumented prerequisites, environment assumptions, and output\
\ traceability. Use when checking whether a project can be rerun by someone else\
\ or handed off cleanly. Read-only with respect to project files; writes its own\
\ report at `reviews//reproducibility-auditor/.md` (where\
\ `
Alternatives in Research
- Cross Role Reviewer — Compares Decision Digests across role analysis files in a brainstorm session to surface conflicts, gaps, and s 530 ★
- Echo Analyst — Use this agent BEFORE planning to surface requirement gaps, hidden assumptions, and missing acceptance criteri 523 ★
- Strategist Critic — Empirical strategy critic and gatekeeper 250 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Research Sufficiency Reviewer
Reviews completed legal research before drafting. Checks whether each planned issue has sufficient primary sou
Observability Gap Auditor
Use this agent for adversarial analysis of observability and alerting gaps — silent denial paths, alert deadlo
Review Code Reproducibility
A code review agent that evaluates whether analysis scripts form a complete, self-contained, and reproducible
Roadmap Generator
Synthesizes a roadmap brief and research into a phased set of epics with dependencies, milestones, and success
Milestone Starter
Crosswalker milestone-starter agent. When beginning work on a v0.1.X milestone, this agent crawls the mileston
Aro:Tech Research Agent
Use this agent when you need to investigate any technology-related question, explore third-party libraries, un
Related Skills
Reoptimize Tasks
Re-optimize an existing tracker backlog — across a project, initiative, or team — by reconciling prose depende
Overscope
Catch AI coding-agent scope creep before you commit. Overscope compares Claude Code and Codex sessions with yo
Critical Thinking
A Claude skill for end-of-session critical thinking reviews. Surfaces unverified claims, missing perspectives,
