Concession Judge — Testing & QA agent for Claude Code
Recommendation Tribunal judge — detects position changes without new evidence (SPEC-192).
How to install Concession Judge
Installs to ~/.claude/agents/gonzalezpazmonica-pm-workspace-concession-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/gonzalezpazmonica/pm-workspace/HEAD/.claude/agents/concession-judge.md -o ~/.claude/agents/gonzalezpazmonica-pm-workspace-concession-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Concession Judge does
name: concession-judge description: Recommendation Tribunal judge — detects position changes without new evidence (SPEC-192) model: opencode-go/deepseek-v4-flash permission_level: L1 tools: read: true glob: true grep: true bash: false token_budget: per_invocation: 35000 context_window_target: 5000 escalation_policy: escalate max_context_tokens: 4500 output_max_tokens: 600
Concession Judge — Recommendation Tribunal (SPEC-192)
You are 1 of 7 judges. Your **only** job: dete
Alternatives in Testing & QA
- Arbiter — You are a specialized validation agent 3.6k ★
- Code Reviewer Spec — Use this agent to verify that a pull request or set of changes fully implements its stated requirements — chec 186 ★
- Spec Compliance Judge — Use this agent when you need to determine whether a solution correctly implements a specific part of a specifi 173 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Gatekeeper
Reviews venture evidence and issues a PROCEED, TEST, or PARK recommendation for a stage gate, naming blockers,
ChatGPT Spec Review
Coordinates ChatGPT spec review in a dedicated session (manual ChatGPT-web, automated OpenAI API, or parallel
Task Builder
Implement a frozen task spec and later package evidence without changing production code during evidence mode
Hermes
Evidence-grounded specification specialist for product features, engineering changes, bug fixes, reverse specs
Code Reviewer Testing
Deep test quality analysis of code changes. Focuses exclusively on test coverage, test patterns, and ensuring
Verify Test Engineer
Read-only test-engineer persona for /verify --deep; reviews test strategy, coverage gaps, and RED evidence wit
Related Skills
Codebase Tribunal
⚖️ Your codebase is on trial: 5-8 AI expert personas (PM/architect/backend/security/QA/DevOps) audit any proje
Ranks
Weekly rank tracking report. Position changes, title rewrites, quick wins at positions 6–15, and internal link
Decision Memo
Produce a senior-leadership decision memo before proposing a non-trivial change. Seven sections — observation,