council · git:20260505.8ddeaf8 · 2026-05-05 · sha256 8f4bb58be5950adf
council git:20260505.8ddeaf8A
Immutable. This exact content never changes and is served at /api/v1/blob/8f4bb58be5950adf.
No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_nhecxazgxrif2bhs/8f4bb58be5950adfa411cf40673699bfbd6928fd3a684a8b68f0de0364c14d26.json
Then /plugin install council@markdownregistry-nhecxazgxrif2bhs in Claude Code. It installs this exact version, the one graded A here, pinned to the commit it was graded at, and leaves it there.
---
name: council
description: "Use when facing ambiguous decisions with significant trade-offs — triggers on architecture choices, technology selection, and design decisions with no clear right answer."
---
# Council — Structured Multi-Voice Decision Making
## Iron Law
NO MAJOR DECISION WITHOUT AT LEAST TWO OPPOSING VIEWPOINTS.
## When to Trigger
- Architecture choices (monolith vs microservice, SQL vs NoSQL)
- Technology selection (framework, library, language)
- Design decisions with no clear right answer
- Trade-offs between competing requirements (speed vs quality, security vs usability)
- User explicitly requests deliberation
## Process
### 1. Identify the Decision
State the decision in one clear question. Example: "Should we use WebSockets or SSE for real-time updates?"
### 2. Summon 4 Voices (Parallel)
Launch 4 independent subagents using the Agent tool, each with ONLY the question and relevant context (NOT the full conversation history — this prevents anchoring bias):
| Voice | Role | Focus |
|-------|------|-------|
| **Architect** | Long-term correctness | Maintainability, extensibility, architectural alignment |
| **Skeptic** | Challenge assumptions | Simpler alternatives, hidden costs, "what if we don't?" |
| **Pragmatist** | Ship it now | Timeline, user impact, operational complexity, team skills |
| **Critic** | Find the cracks | Edge cases, failure modes, migration risks, rollback difficulty |
**Anti-Anchoring Rule**: Each voice receives only:
- The decision question
- Relevant codebase context (file paths, current architecture)
- Their role and focus area
They do NOT receive: the full conversation, other voices' opinions, or the user's leaning.
### 3. Synthesize
After all 4 voices report back:
1. List areas of **agreement** (strong signal)
2. List areas of **disagreement** (where trade-offs live)
3. Present the user with:
- **Recommended option** (based on agreement weight)
- **Key trade-off** (the real decision to make)
- **Reversibility** (how hard to undo each option)
### 4. Record Decision
Save the decision to harness-mem:
```
mem_add(
title: "Decision: {question}",
type: "decision",
importance: 0.9,
body: "Context: ...\nOptions: ...\nChosen: ...\nRationale: ...\nTrade-off accepted: ..."
)
```
## Anti-Rationalization
| Excuse | Rebuttal |
|--------|----------|
| "I already know the answer" | Your gut feeling is not analysis. Council surfaces blind spots. |
| "This is too slow for a simple decision" | 5 minutes of council prevents weeks of regret. |
| "The team already agreed" | Groupthink is not consensus. Diverse perspectives prevent disasters. |
| "I don't need 4 voices for this" | Even simple decisions benefit from the Skeptic and Critic. |
## Red Flags
- Skipping the Council for "obvious" decisions
- Only summoning voices that agree with you
- Reading the full conversation to all voices (anchoring)
- Not recording the decision and rationale