Agent Room

Two Entry Points

1. Standalone (user invokes directly)

/agent-room "Should we use a monorepo or polyrepo?"

2. Sub-routine (another skill invokes mid-flow)

discover

1. Frame the specific decision as a clear problem statement
2. Include relevant context gathered so far
3. Invoke agent-room with mode (debate/poll) and agent count
4. Receive the report: consensus, disagreements, recommendation
5. Integrate the recommendation into the ongoing conversation
6. The agent-room report is ephemeral — it lives in context, not necessarily on disk

Critical Gates

1. Choose the right mode — debate for trade-off decisions, poll for filtering hallucinations and finding consensus. Default to debate (richer output for fewer agents).
2. Problem must be specific — N agents on a fuzzy prompt wastes tokens. If vague, ask the user to sharpen before spawning.
3. Agents must produce structured output — freeform prose can't be aggregated.
4. Cost scales with agent count — 3 debate agents x 3 rounds ~ $0.30-0.50. 10 poll agents ~ $0.30-0.50. Default to sonnet unless user requests opus.

Mode Routing

Mode A: Debate

A1. Parse the Request

• Problem/question to debate
• Agent count N — default 3 (override: "have 5 agents debate")
• Round count R — default 3 (override: "debate for 5 rounds")
• Agent roles — user may specify. If not, assign diverse defaults.

A2. Assign Agent Roles

1. Architect — systems, interfaces, scalability, long-term maintainability
2. Pragmatist — shipping fast, minimal complexity, "good enough" solutions
3. Critic — edge cases, failure modes, security holes, unstated assumptions

1. User advocate — UX, simplicity, delight
2. Business strategist — revenue, growth, competitive advantage
3. Engineer — technical feasibility and cost

1. Optimist — opportunity, upside, reasons to act
2. Skeptic — risk, downside, reasons to wait
3. Synthesizer — middle path, integrates both perspectives

• Agent 1: "Minimize surface area — aim for the fewest possible methods/endpoints"
• Agent 2: "Maximize flexibility — support the widest range of use cases"
• Agent 3: "Optimize for the most common case — make the 80% path trivially simple"
• Agent 4 (if N > 3): "Take inspiration from [specific paradigm/library the user knows]"

A3. Run Debate Rounds

You are {role}: {role_description}

PROBLEM:
{problem}

CONTEXT:
{context}

This is Round 1 of a multi-agent debate. State your initial position.
Be specific — propose actual solutions, not vague principles. Take a clear stance.
Other agents will challenge you in subsequent rounds.

Communication discipline:
- No performative agreement: never open with "Great point" or "I appreciate X's perspective"
- State disagreements directly: "That approach fails because [X]" not "While that has merit..."
- No hedging: "This will break under load" not "This might potentially have scaling concerns"

Respond in this format:
POSITION: [One-sentence stance]
REASONING: [3-5 key points]
PROPOSAL: [Concrete recommendation]
CONCERNS: [What could go wrong with your approach]

Write your response directly — do not write to any files.

You are {role}: {role_description}

PROBLEM:
{problem}

PREVIOUS DISCUSSION:
{all previous round entries}

This is Round {N}. Read the previous discussion carefully.

1. Respond to the strongest counterargument against your position
2. Identify where you AGREE with other agents (concede good points)
3. Identify where you still DISAGREE and why
4. Refine your proposal based on the discussion

Do NOT repeat your previous position. Engage with what others said.
Change your mind if they made a better argument.
Do NOT soften disagreements with praise. "I appreciate Agent A's point, but..." is sycophancy disguised as discourse. State the disagreement directly.

Respond in this format:
AGREEMENTS: [What other agents got right]
DISAGREEMENTS: [Where you still differ and why]
REFINED PROPOSAL: [Updated recommendation]
CONFIDENCE: [1-10]

Write your response directly — do not write to any files.

1. Collect all agent responses
2. Check for convergence: if all agents agree (confidence 8+, proposals aligned), stop early
3. Otherwise continue to next round

A4. Synthesize

• Where did agents converge? — high-confidence conclusions
• Where did they remain split? — genuine trade-offs the user must decide
• What concerns were raised but unresolved? — risks to monitor
• Did any agent change their mind? — mind-changes are strong signals

Mode B: Poll

B1. Design Structured Output Schema

B2. Generate Framing Variations

1. Neutral baseline
2. Risk-averse analyst
3. Growth-oriented strategist
4. Contrarian (challenge conventional wisdom)
5. First-principles reasoner
6. User-empathy focus
7. Resource-constrained optimizer
8. Long-term (5-year) optimizer
9. Data-driven (measurable only)
10. Systems thinker (second/third-order effects)

B3. Spawn All N Agents in Parallel

B4. Aggregate Results

Report

.agents/meta/agent-room-report.md

---
skill: agent-room
version: 1
date: {YYYY-MM-DD}
status: final
---

# Agent Room Report

**Problem**: {problem}
**Mode**: {debate | poll}
**Agents**: {N} | **Rounds**: {R, debate only}

Configuration

Edge Cases

• Vague problem: Ask user to sharpen before spawning. Don't burn tokens on vagueness.
• N < 2 (debate) or N < 3 (poll): Warn user — debate needs 2+, poll needs 3+.
• Unanimous agreement round 1: Stop early. Report consensus. Valid and cheap.
• Deadlock after R rounds: Report honestly. The finding IS that no dominant answer exists.
• Even poll split: Report the split. No forced tiebreaker.
• Agent goes off-topic: Exclude from synthesis, note effective N.
• Existing report: Overwrite — these are ephemeral analysis artifacts.

Cost Considerations

• 3 sonnet agents x 3 rounds (debate): ~$0.30-0.50
• 10 sonnet agents (poll): ~$0.30-0.50
• Opus multiplies ~10x — only use when explicitly requested
• Early convergence saves cost
• For binary decisions, 5 poll agents usually suffices

Chain Position

solution-design

system-architecture

discover