Crucible

A council of specialized personas debates one idea under structured conflict. The chair synthesizes into a verdict. Transcripts are saved to disk for second-brain reuse.

Use this when the cost of being wrong is high enough to justify convening 5-10 subagents. For one-lens exploration without a debate, use Solo mode. For tactical questions under five minutes of normal thinking, don't use Crucible at all.

When to trigger

Trigger on explicit user invocation only. Examples:

/crucible <idea> (Decision mode default)
/crucible --council <idea> or /crucible --quick <idea> (Council mode)
/crucible --pm <idea> (PM Daily mode)
/crucible --solo <persona> <idea> or natural language ("give me the First Principles read on X")
/crucible --existential <idea>
"Run this through the crucible: ..."
"Convene the crucible on ..."

Do not auto-trigger. This is an expensive skill and the user decides when it runs.

Five modes

The chair selects mode at intake based on the user's phrasing OR an explicit flag. Most daily use belongs in Council or Solo. Decision and Existential are for real decisions with real stakes.

Mode 1: Solo (single-persona lens, ~10-15 seconds)

Triggers: /crucible --solo <persona>, or natural language ("give me the First Principles read on X", "what does the Expansionist think about Y", "Track Record this for me").

Persona count: 1. No duels. No chair verdict. The chair's only job is persona-matching and returning the rubric output unchanged.

Use for: Exploration, not decisions. When you want one specific lens, not a debate.

Honesty check: If you find yourself reaching for Solo to avoid hearing the Contrarian, that's a signal to run Council mode instead.

Mode 2: Council (daily reflex, ~30-45 seconds)

Triggers: "council", "quick crucible", "gut check", "throw rocks at this", "poke holes", "sanity check", /crucible --council, /crucible --quick.

Bench: 5 personas, parallel openings only. No duels. No verdict beyond a one-liner.

Contrarian (Sonnet, NOT Opus at this tier to keep cost down)
First Principles (Sonnet at this tier)
Expansionist (Sonnet)
Outsider (Haiku)
Operator (Haiku)

Output: Five short challenges (80-120 words each) plus a one-line "proceed / shelve / reframe" call from the chair. No transcript file unless the user asks.

Use for: Daily PM ideation, "I just thought of X, is it dumb?", quick sanity checks between meetings.

Mode 3: PM Daily (bounded ideation, ~60-90 seconds)

Triggers: "pm brainstorm", "pm daily crucible", /crucible --pm.

Bench: 4 personas, parallel openings, no duels, short verdict.

Contrarian (Sonnet)
Operator (Haiku)
First Principles (Sonnet at this tier)
Expansionist (Sonnet)

Output: Four one-paragraph challenges plus a chair verdict (proceed / shelve / reframe + one concrete next action if proceed). Transcript optional.

Use for: PM-specific work ideation, feature direction, user research design, anything that deserves more than "throw rocks" but less than a full decision council.

Mode 4: Decision (current default, 9-11 personas)

Triggers: /crucible, "convene the crucible", "run this through the crucible", or the skill's default when the user's phrasing implies a real decision.

Bench: Core 6 plus bench-specific specialty per benches.md, typically 9-11 personas. Full duels. Full verdict. Transcript written.

Use for: Real decisions with multi-week time at stake, or money, or reputation.

Mode 5: Existential (Heavy Custom, all 17 personas)

Triggers: User explicitly flags "existential", "life decision", "full crucible", or chair detects the question framing implies existential scope.

Bench: All 17 personas. Full duels. Extended verdict.

Use guardrail: If invoked more than once per quarter, chair warns: "You've convened the Existential tier N times in M days. These questions usually move slower than that. Proceed anyway?"

Motivated-convening guardrail (added 2026-04-19)

Before firing any Decision or Existential mode council, the chair asks three questions at intake:

Has a structurally similar question been convened in the last 30 days? (Chair should glob ~/Documents/VibeCoding/_scratch/crucible/ for recent transcripts and compare topic proximity. If a near-duplicate exists, show its verdict and ask: "Is this a re-run of that, or genuinely new?")
What decision does a verdict produce that you will act on in the next 14 days? If the user cannot name a concrete action, the chair should say: "This looks like a discussion, not a decision. Use Council mode instead."
What new information has arrived since you last thought seriously about this? If the honest answer is "none, just renewed energy," the chair should say: "Run 2 on 2026-04-19 named this pattern 'appetite disguised as governance.' Proceed anyway, or reframe?"

The chair never REFUSES to run. It names what it is seeing and lets the user decide. This is the skill's main defence against becoming a procrastination ritual.

Core design

17 personas, 1 chair. The chair selects 1-17 personas per run based on mode and problem type (see benches.md). The Core 6 are always convened in Decision and Existential modes. The rest are activated by bench.

Four phases. Intake, opening takes, pair duels, verdict.

Model routing per persona. Haiku for rubric-driven checks, Sonnet for judgment, Opus for Contrarian, First Principles, Consequences, and Chair.

Transcripts persist. Full debate writes to ~/Documents/VibeCoding/_scratch/crucible/YYYY-MM-DD-{slug}.md. Main thread sees only the verdict and a link. Thinking is preserved, context stays clean.

Rubrics prevent theater. Each persona has concrete deliverables (cite an analog, estimate a number, name a mechanism), not just "give your take". See personas.md.

Phase 1: Intake

The chair (main thread, Opus) does three things:

Classify the input. Is this a problem statement ("should I do X?") or a proposed solution ("here's my plan, tear it apart")? Frame the persona prompts differently for each.
Select the bench. In Decision and Existential modes, always convene the Core 6: Contrarian, Advocate, Pre-mortem, Operator, First Principles, Expansionist. Add specialty personas based on problem type per benches.md.
Restate and confirm. Before spinning up subagents, restate the question in one sentence and ask the user to confirm or correct the framing. Do not skip this. Mis-framed questions produce sharp answers to the wrong thing.

Phase 2: Opening takes (parallel subagents)

Spawn one subagent per selected persona in parallel (single message, multiple Agent tool calls). Each subagent:

Uses general-purpose subagent_type
Uses the model tier specified in personas.md
Receives a self-contained prompt containing: the persona's full rubric, the user's idea, the framing mode (problem vs solution), and the output length constraint
Writes a direct response back; no file writes at this phase

Personas cannot see each other's openings. This is deliberate; it prevents contamination and produces honest independent takes.

Collect all opening takes before moving to Phase 3. Store them internally as labeled blocks ({persona_name}_opening).

Phase 3: Pair duels (serial subagents, anonymized rebuttals)

Central duel (MANDATORY in Decision and Existential modes):

First Principles vs Expansionist is the spine of Crucible. Strip-to-bedrock vs scale-to-100x is the highest-value tension this council generates. It always fires when both personas are in the bench (always true in Decision and Existential modes). The chair must address its resolution in the verdict.

Other duels (activated only if both personas are in the current bench):

Advocate vs Contrarian: is the premise valid?
Operator vs Historian: can we ship it, has anyone shipped it?
**Eco

crucible