원클릭으로
council
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.
메뉴
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.
| name | council |
| description | Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing. |
| origin | ECC |
Convene four advisors for ambiguous decisions:
This is for decision-making under ambiguity, not code review, implementation planning, or architecture design.
Use council when:
Examples:
| Instead of council | Use |
|---|---|
| Verifying whether output is correct | santa-method |
| Breaking a feature into implementation steps | planner |
| Designing system architecture | architect |
| Reviewing code for bugs or security | code-reviewer or santa-method |
| Straight factual questions | just answer directly |
| Obvious execution tasks | just do the task |
| Voice | Lens |
|---|---|
| Architect | correctness, maintainability, long-term implications |
| Skeptic | premise challenge, simplification, assumption breaking |
| Pragmatist | shipping speed, user impact, operational reality |
| Critic | edge cases, downside risk, failure modes |
The three external voices should be launched as fresh subagents with only the question and relevant context, not the full ongoing conversation. That is the anti-anchoring mechanism.
Reduce the decision to one explicit prompt:
If the question is vague, ask one clarifying question before convening the council.
If the decision is codebase-specific:
If the decision is strategic/general:
Before reading other voices, write down:
Do this first so the synthesis does not simply mirror the external voices.
Each subagent gets:
Prompt shape:
You are the [ROLE] on a four-voice decision council.
Question:
[decision question]
Context:
[only the relevant snippets or constraints]
Respond with:
1. Position — 1-2 sentences
2. Reasoning — 3 concise bullets
3. Risk — biggest risk in your recommendation
4. Surprise — one thing the other voices may miss
Be direct. No hedging. Keep it under 300 words.
Role emphasis:
You are both a participant and the synthesizer, so use these rules:
Use this output shape:
## Council: [short decision title]
**Architect:** [1-2 sentence position]
[1 line on why]
**Skeptic:** [1-2 sentence position]
[1 line on why]
**Pragmatist:** [1-2 sentence position]
[1 line on why]
**Critic:** [1-2 sentence position]
[1 line on why]
### Verdict
- **Consensus:** [where they align]
- **Strongest dissent:** [most important disagreement]
- **Premise check:** [did the Skeptic challenge the question itself?]
- **Recommendation:** [the synthesized path]
Keep it scannable on a phone screen.
Do not write ad-hoc notes to ~/.claude/notes or other shadow paths from this skill.
If the council materially changes the recommendation:
knowledge-ops to store the lesson in the right durable location/save-session if the outcome belongs in session memoryOnly persist a decision when it changes something real.
Default is one round.
If the user wants another round:
santa-method — adversarial verificationknowledge-ops — persist durable decision deltas correctlysearch-first — gather external reference material before the council if neededarchitecture-decision-records — formalize the outcome when the decision becomes long-lived system policyQuestion:
Should we ship ECC 2.0 as alpha now, or hold until the control-plane UI is more complete?
Likely council shape:
The value is not unanimity. The value is making the disagreement legible before choosing.
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
在回答之前先读取仓库的实时状态,引导用户了解 ECC 当前的 agents、skills、命令、hooks、规则、安装配置档案以及项目接入流程。
当用户希望通过并行工作、并发 agents、批量工具调用、隔离 worktree 或多条独立验证通道来大幅加速任务、同时不损失正确性时使用。
Garbage collection for your Claude Code configuration. Periodically scans ~/.claude (skills, memory, hooks, permissions, MCP servers, caches) for redundant, stale, orphaned, or low-value items, then walks the user through a confirm-each-deletion cleanup. Use when the user says "clean up my config", "config GC", "too many skills", "audit my setup", "my .claude is bloated", or asks for a periodic config review.
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.