Calibration Judge — Development agent for Claude Code
Truth Tribunal judge — confidence statements match evidence strength.
How to install Calibration Judge
Installs to ~/.claude/agents/gonzalezpazmonica-pm-workspace-calibration-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/gonzalezpazmonica/pm-workspace/HEAD/.claude/agents/calibration-judge.md -o ~/.claude/agents/gonzalezpazmonica-pm-workspace-calibration-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Calibration Judge does
name: calibration-judge description: Truth Tribunal judge — confidence statements match evidence strength model: opencode-go/deepseek-v4-flash permission_level: L1 tools: [Read, Glob, Grep] token_budget: per_invocation: 60000 context_window_target: 8500 escalation_policy: escalate max_context_tokens: 8000 output_max_tokens: 500
Calibration Judge — Truth Tribunal
You are one of 7 judges in Savia's Truth Tribunal (SPEC-106). Your focus: **calibration between stated confidence and
Alternatives in Development
- Review Agent — You are a specialized review agent 3.6k ★
- Eval Engineer — GAIA evaluation framework specialist 1.5k ★
- Librarian Critic — Literature quality critic 250 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Coherence Judge
Truth Tribunal judge — internal consistency (sums, dates, entities)
Completeness Judge
Truth Tribunal judge — report covers what its title/abstract promises
Debate Tribunal
Multi-agent structured debate protocol where 3-5 persona-driven debaters argue positions through claim-evidenc
Football Forecaster
Expert statistician for football (soccer) match & tournament forecasting. Knows the literature (Dixon-Coles, b
Sonmat Witness
External witness agent. Verifies intent-artifact match using user turn cascade and ground truth. Protocol-isol
Control Quality Adversary
Fresh-context judge of a FLAGGED calibration control — is the control genuinely clean, is its oracle fair, or
Related Skills
Codebase Tribunal
⚖️ Your codebase is on trial: 5-8 AI expert personas (PM/architect/backend/security/QA/DevOps) audit any proje
Decision Audit
Analyzes the decision journal to produce a PM Decision Profile. Extracts patterns across optimization bias, in
Claude Boot Stats
Per-component token cost analyzer for Claude Code first-turn context: HTTP intercept proxy + Qwen3 BPE + groun