Balanced Verifier — Development agent for Claude Code
Round 2 verification — reviews brutalist decisions for false negatives and severity over-corrections.
How to install Balanced Verifier
Installs to ~/.claude/agents/vmihalis-hacker-bob-balanced-verifier.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vmihalis/hacker-bob/HEAD/.claude/agents/balanced-verifier.md -o ~/.claude/agents/vmihalis-hacker-bob-balanced-verifier.md Restart Claude Code, or start a new session, for it to be picked up.
What Balanced Verifier does
name: balanced-verifier description: Round 2 verification — reviews brutalist decisions for false negatives and severity over-corrections tools: Bash, Read, mcp__hacker-bob__bob_http_scan, mcp__hacker-bob__bob_http_confirm, mcp__hacker-bob__bob_read_http_audit, mcp__hacker-bob__bob_read_surface_routes, mcp__hacker-bob__bob_read_candidate_claims, mcp__hacker-bob__bob_read_chain_attempts, mcp__hacker-bob__bob_write_verification_round, mcp__hacker-bob__bob_stage_verification_round_partial, mcp_
Alternatives in Development
- Cold Verifier — Phase 11 cold verification agent that independently re-verifies CRITICAL and HIGH findings with zero prior con 125 ★
- Ac Evidence Verifier — Phase 3.4 evidence verifier 115 ★
- Fire Verifier — Combines must-haves verification with WARRIOR 70-point validation 77 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Brutalist Verifier
Round 1 verification — re-runs PoCs with maximum skepticism, checks severity inflation, filters non-bugs
Review Bug
Review: Bug/Logic Error Detection (coverage-first) — report all findings with confidence and severity tags; do
Verification Reviewer
Read-only adversarial verifier for Best Practices findings. Reopens cited evidence, challenges semantic conclu
Final Verifier
Round 3 verification — re-runs only REPORTABLE findings with fresh requests as final confirmation
Claim Auditor
Adversarial verifier for proposed genealogical matches. Tries to break each proposed match with evidence, kill
Fidelity Verifier
Adversarial verifier for outward-facing drafts (briefs, digests, packs) produced by /share. It tries to FAIL t
Related Skills
Claude Code Discipline Skills
Seven Claude Code skills that stop an LLM agent asserting what it has not measured. Each born from a dated pro
All Recommendations
Launch a team of implementation agents to apply ALL recommended changes from the most recent review — every se
Slice Review
Run a multi-agent code review over a local diff (no PR or remote required) and report findings by severity wit