dialectic

Run a dialectic check on: $ARGUMENTS

The goal is to reduce confirmation bias, not to generate debate theater.

Workflow

1. Restate the claim in one precise sentence. If the claim is vague, narrow it before launching agents.
2. Launch two read-only reviewers in parallel, in a single message. Prefer one reviewer from a different model/tool for independence, e.g. codex:codex-rescue when available, usually as Antithesis. If no independent reviewer is available, use two separate subagents with opposing prompts:
   • Thesis: find the strongest evidence that the claim is true.
   • Antithesis: find the strongest evidence that the claim is false, risky, or incomplete.
3. Require concrete evidence: file paths, line numbers, failing/passing command output, data, logs, or docs. Agents must say when evidence is missing.
4. Verify the important cited evidence yourself by reading the referenced code or output. Do not trust agent summaries blindly.
5. Synthesize the result as one of: true, false, mixed, or unknown.
6. If the result affects implementation, state the smallest next action: proceed, change design, add a test/experiment, or ask the user.

Output

Use this structure: