Baseline Auditor — Development agent for Claude Code
Use this agent to judge whether a captured baseline is trustworthy before it gets frozen and committed for verification-gate to compare against.
How to install Baseline Auditor
Installs to ~/.claude/agents/toxiccoder777-agentic-claude-baseline-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/toxiccoder777/agentic-claude/HEAD/agents/baseline-auditor.md -o ~/.claude/agents/toxiccoder777-agentic-claude-baseline-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Baseline Auditor does
name: baseline-auditor description: Use this agent to judge whether a captured baseline is trustworthy before it gets frozen and committed for verification-gate to compare against. Invoke it right after running a capture script and before committing the resulting baseline files, whenever a validity-report.json needs a human-quality second opinion rather than just the mechanical checks the gate itself runs, or when a gate chain's PASS results feel suspiciously easy and the baseline itself is
Alternatives in Development
- Robin — Read-only, skeptical evidence auditor for a Superloopy criterion 109 ★
- Code Review Manager — Use this agent when the user has recently written, modified, or committed code and needs comprehensive code re 59 ★
- Uxaudit L3 Judge — L3-vision Judge for the uxaudit pipeline 52 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Tz Altitude Reviewer
Judge whether a diff's work sits at the right layer, and name the root causes worth their own ticket. Reports
Evolve Behavior Compare
Behavior comparison agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on refactor
Brainswarm Judge
brainswarm judge role. Compares anonymised finalist pairs against the frozen rubric and rules on disputed crit
Sim Verifier Sonnet
Drives the iOS/watchOS simulator to check that a change actually looks and behaves right — launch, tap through
Akinator Product Owner
Use at plan and verify stations when work adds, changes or removes user-facing behavior. Reviews whether the f
Plan Guardian
Drift check for the active cc-memory plan. Read memory/PLAN.md + memory/PROGRESS.md, compare against recent ac
Related Skills
Paydown
Pay down the frozen code-quality baseline and run a full QA sweep
Autodev
Stop letting your agent grade its own homework. An Agent Skill that writes the test first, then optimizes agai
Persona Portability Benchmark
One persona, one frozen memory, N models: how much of an agent's character survives a model swap? Harness + bl