Back to list
tobyhede

verifying-by-consensus

by tobyhede

Turn skills into executable workflows with rundown runbooks

0🍴 0📅 Jan 14, 2026

SKILL.md


name: verifying-by-consensus description: Dispatch N independent review agents, collate by consensus ratio, cross-check exclusive findings workflow: verify.runbook.md

Verifying by Consensus

Overview

Dispatch N agents to independently review the same subject. Collate findings:

  • Common (N/N): All agents found → act immediately
  • Exclusive (<N/N): Some agents found → cross-check validates

Agent Count Heuristics

ScopeDefault NRationale
Single file change2Focused review, two perspectives sufficient
Multi-file feature2-3More surface area benefits from diversity
Architecture change3Different perspectives valuable
Security-sensitive3+Higher stakes warrant more eyes

Override via args: --count 3 or --agents "Explore,Plan,code-agent"

Agent Selection

  1. Explicit args: If user provides --agents, use those
  2. Available plugins: Check for specialized agents (cipherpowers code-review-agent, etc.)
  3. Built-in agents: Use Claude's Explore, Plan agents with review prompts
  4. Fallback: N instances of same agent with different perspective prompts

Process

Announce: "I'm using the verifying-by-consensus skill to verify [subject]."

Phase 1: Dispatch

  1. Determine N (default 2, or from args)
  2. Select agents (from args, plugins, or built-ins)
  3. Start workflow: tsv run runbooks/verify.runbook.md
  4. Dispatch agents with StepId prefix in description:
    Step(description="1.1 - Review [subject]", prompt="...", subagent_type="...")
    Step(description="1.2 - Review [subject]", prompt="...", subagent_type="...")
    

Hooks automate step binding:

Manual commandHook triggerWhen
tsv run --step 1.1PostToolUse (Step)StepId detected in description
tsv run --agent {id}SubagentStartAgent spawns

Subagent protocol:

  • Write findings to .work/{date}-verify-{agentId}.md
  • End response with STATUS: PASS or STATUS: FAIL

Phase 2: Collate

After all agents complete, dispatch collation:

  • Read all N review files
  • Compare findings across agents
  • Categorize by consensus:
    • Common (N/N): All agents found this issue
    • Exclusive: Subcategorize by ratio (e.g., 2/3, 1/3)
  • Write collation to .work/{date}-verify-collated.md

Present immediately:

Collation complete.

## Common (N/N)
[Issues all agents found - can implement now]

## Exclusive
### (N-1)/N
[Issues most agents found]
### 1/N
[Issues one agent found]

Cross-check starting for exclusive findings...

Phase 3: Cross-Check

Dispatch cross-check agent to validate ALL exclusive findings:

  • For each exclusive issue, verify against ground truth
  • Mark as: VALIDATED | INVALIDATED | UNCERTAIN
  • Write to .work/{date}-verify-crosscheck.md

Present when complete:

Cross-check complete.

VALIDATED: X issues (should address)
INVALIDATED: X issues (can skip)
UNCERTAIN: X issues (user decides)

Phase 4: Complete

tsv complete

Output Files

All files saved to .work/:

  • {date}-verify-{agentId}.md - Individual reviews
  • {date}-verify-collated.md - Collation report
  • {date}-verify-crosscheck.md - Cross-check results

Templates

Review template: ${CLAUDE_PLUGIN_ROOT}templates/verify-review.md Collation template: ${CLAUDE_PLUGIN_ROOT}templates/verify-collation.md

Score

Total Score

55/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

0/10
説明文

100文字以上の説明がある

0/10
人気

GitHub Stars 100以上

0/15
最近の活動

1ヶ月以内に更新

+10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

+5

Reviews

💬

Reviews coming soon