Verdict Writer — Development agent for Claude Code
Writes structured PASS/FAIL verdicts based on evidence review.
How to install Verdict Writer
Installs to ~/.claude/agents/krzemienski-validationforge-verdict-writer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/krzemienski/validationforge/HEAD/agents/verdict-writer.md -o ~/.claude/agents/krzemienski-validationforge-verdict-writer.md Restart Claude Code, or start a new session, for it to be picked up.
What Verdict Writer does
name: verdict-writer description: Writes structured PASS/FAIL verdicts based on evidence review capabilities: ["evidence-review", "verdict-writing", "root-cause-analysis", "report-generation", "ai-analysis-integration"]
Verdict Writer Agent
You write structured PASS/FAIL verdicts based on evidence review. You are a skeptical reviewer. You do NOT trust claims, only evidence. You do NOT trust descriptions of evidence — you READ the evidence files yourself.
Identity
- Role: Evi
Alternatives in Development
- Gitnexus Synthesis Critic — GitNexus final review synthesis critic 45.8k ★
- Executioner — Optional Sanhedrin fallback verifier 632 ★
- Dashclaw Gate Runner — Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa 297 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Adversarial Judge.Agent
Use to adversarially evaluate a proposal or implementation against its repository profile and specs, returning
Compound Skeptic
Skeptical second-pass reviewer of a compound proposal; emits per-item IMPLEMENT / DONT_IMPLEMENT verdicts with
Loop Evaluator
Evaluate artifact strictly against active loop criteria and return structured pass/fail output. Use proactivel
Sigma Step Judge
Fresh-context cross-family judge for Sigma step artifacts. Runs via fusion: a cross-family panel analyzes the
Uxaudit L3 Judge
L3-vision Judge for the uxaudit pipeline. Reads ONE captured screenshot plus a check-specific prompt.md (and o
Uxaudit L4 Judge
L4-journey Judge for the uxaudit pipeline. Reads the per-journey capture directory (screenshots + steps.json +
Related Skills
Dsh Auto Review
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns stru
Warden Receipt
Show token-warden rule receipts — the per-rule verdict card with token savings vs. rent, per-task pass/fail, t
Squad Review
Run only the reviewer agent against the current run's code and tests. Produces a PASS/FAIL verdict and routes