damionrashford Verdict
Context: $ARGUMENTS
Deliver the final judgment. What survives, what doesn't, and the uncomfortable truth.
Workflow
1. Check for existing graph state
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" show
If a graph exists from prior /steelman or /crucible runs, use it. If empty, build one from scratch by identifying the idea's claims, assumptions, evidence, weaknesses, and counter-arguments:
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" reset
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" add "<claim-id>" claim --obs "<fact>" --agent judge
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" add "<assumption-id>" assumption --obs "<fact>" --agent judge
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" add "<weakness-id>" weakness --obs "<fact>" --agent judge
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" relate "<claim-id>" assumes "<assumption-id>" --agent judge
2. Gadfly sting
Read ${CLAUDE_PLUGIN_ROOT}/references/social-gadfly.md.
Name the ONE thing nobody wants to say about this idea. Not a weakness (those are tactical), the foundational uncomfortable truth that would remain even if everything else went right.
Ask yourself:
- What is everyone avoiding saying?
- What assumption is so foundational that questioning it feels rude?
- What would a persistent, unsilenceable critic keep coming back to?
If the gadfly sting reveals something that changes the structural picture, register it:
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" add "<counter-id>" counter --obs "<the uncomfortable truth>" --agent judge
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" relate "<counter-id>" undermines "<claim-id>" --agent judge
3. Structural verdict
Run the graph verdict:
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" verdict
The verdict is computed by grounded semantics, not by counting attacks. Each claim lands in exactly one bucket:
| Key | Means |
|---|---|
survives_scrutiny |
supported, and every attacker was itself defeated. survived_attacks says how many it withstood |
does_not_survive |
defeated by an attacker that still stands. reason names it |
needs_more_work |
attacks unresolved, or resting on something unestablished, or unsupported |
unmitigated_weaknesses |
weaknesses still standing — nothing countered or mitigated them |
circular_reasoning |
dependency cycles, if any |
open_reservations on a surviving claim lists minor attacks still standing — nitpicks that could not defeat it but belong in the ruling. Mention them. Report these as the script computed them. Do not re-derive a verdict from your own reading of the argument — the whole point is that the ruling comes from the record.
4. Present the verdict
Output format
The Uncomfortable Truth: One sentence. The gadfly sting.
Survives Scrutiny: Claims that were attacked and held, or that stand on unchallenged support. Say what defeated each attacker — "survives because X was countered by Y" is the citation.
Does Not Survive: Claims with a surviving attacker. Name the attacker. These need to be dropped or reworked.
Needs More Work: Three different situations, and they need different advice — say which applies. Unresolved attacks (the attackers are themselves contested), a dependency that was never established, or no supporting evidence at all. State what would settle it.
Unmitigated Weaknesses: Exposed risks nothing answered. What has to happen before this moves forward.
Circular Reasoning: If non-empty, name the cycle. A claim propped up by what it props up is not established.
Optionally export the full graph for the user:
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" export
Resources
${CLAUDE_PLUGIN_ROOT}/references/social-gadfly.md— load always. Socrates as the stinging fly, the cost of silencing uncomfortable questioners, the distinction between tactical weaknesses and foundational truths.${CLAUDE_PLUGIN_ROOT}/references/polemic.md— load when the gadfly sting needs rhetorical force or the user asks for a forceful take. Constructive polemic exposes genuine errors without demonizing.${CLAUDE_PLUGIN_ROOT}/references/argument-semantics.md— load always. How the verdict is computed: attacks from defeated nodes stop counting, so counters decide outcomes.${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts— runverdictfor structural analysis,exportfor full graph markdown.
Gotchas
- The gadfly sting is not another weakness. Weaknesses are tactical (the API might go down). The gadfly names a foundational truth (the team doesn't actually want this to succeed). If your gadfly sting could appear in a list of weaknesses, it's not stinging enough.
- If a graph exists from prior skills, use it. The verdict is strongest when it reads a graph built by
/steelmanand/crucible. Running verdict standalone works, but the graph will be thinner. - The verdict script's output is structural, not rhetorical. It tells you what survives based on graph topology. Your job is to synthesize that into a human-readable judgment.
- Don't soften the gadfly. Socrates was executed for it. The uncomfortable truth is uncomfortable. Name it plainly.