con un clic
council
Convenes multiple agents to debate an important decision
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Convenes multiple agents to debate an important decision
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Full pipeline: evaluation -> spec -> implementation -> review -> QA
Full pipeline: evaluation -> spec -> implementation -> review -> QA
Convenes multiple agents to debate an important decision
Enriches CLAUDE.md by exploring the project and specializes agents to the real stack
QA + bugfix cycle until it passes
Enriches CLAUDE.md by exploring the project and specializes agents to the real stack
Basado en la clasificación ocupacional SOC
| name | council |
| description | Convenes multiple agents to debate an important decision |
| user-invocable | true |
| workflow | {"version":1,"steps":[{"id":"identify-type","role":"system","intent":"Analyze the question and determine council type: architecture, feature-scope, or tech-debt.","requires":["user-question"],"produces":["council-type","participant-roles"],"gate":true},{"id":"agent-1","role":"dynamic","intent":"Analyze the question from specialized perspective. State position with concrete arguments. Spawn via Agent tool IN PARALLEL with agent-2 and agent-3.","requires":["user-question","council-type"],"produces":["perspective-1"],"model-tier":"reasoning"},{"id":"agent-2","role":"dynamic","intent":"Analyze the question from specialized perspective. State position with concrete arguments.","requires":["user-question","council-type"],"produces":["perspective-2"],"model-tier":"reasoning"},{"id":"agent-3","role":"dynamic","intent":"Analyze the question from specialized perspective. State position with concrete arguments.","requires":["user-question","council-type"],"produces":["perspective-3"],"model-tier":"reasoning"},{"id":"synthesize","role":"system","intent":"Synthesize debate: points of agreement, disagreement, risks. Present options to user.","requires":["perspective-1","perspective-2","perspective-3"],"produces":["synthesis","options"],"gate":true},{"id":"write-spec","role":"system","intent":"After user decides, write spec document to docs/specs/.","requires":["synthesis","user-decision"],"produces":["spec-document"],"gate":true}]} |
Convenes a council of specialized agents to debate an important decision. Each agent contributes their independent perspective and the result is a synthesis of the debate.
Agents are invoked IN PARALLEL using the Task tool to obtain independent perspectives without bias.
/council [question or decision to debate]
Optionally you can specify the type: /council architecture [question]
Participants: Tech Lead + Advisor + Developer When it applies: Decisions about architecture, patterns, large refactors, new technologies
Invokes all 3 agents IN PARALLEL using Task tool:
.claude/agents/tech-lead.md — architecture and technical coherence perspective.claude/agents/advisor.md — feasibility and business risk perspective.claude/agents/developer.md — implementability and pragmatism perspectiveParticipants: Advisor + Developer + Tech Lead When it applies: Defining feature scope, prioritizing functionality, evaluating product proposals
Invokes all 3 agents IN PARALLEL using Task tool:
.claude/agents/advisor.md — domain and strategic vision perspective.claude/agents/developer.md — implementability and pragmatism perspective.claude/agents/tech-lead.md — technical feasibility and effort perspectiveParticipants: Tech Lead + Developer + Code Reviewer When it applies: Deciding whether to address technical debt, planning refactors, evaluating codebase quality
Invokes all 3 agents IN PARALLEL using Task tool:
.claude/agents/tech-lead.md — architectural impact perspective.claude/agents/developer.md — implementation cost perspective.claude/agents/code-reviewer.md — quality and risk perspectiveAnalyze the user's question and determine which council type applies:
Workspace detection: Before invoking agents, check if the project is inside a workspace:
guild-workspace.json file by searching upward from the project rootInvoke the 3 corresponding agents IN PARALLEL using Task tool with model: "opus" (all council agents use reasoning tier). Each agent:
.claude/agents/[name].md file to assume their roleCLAUDE.md for project contextPresent the perspectives of all 3 agents in a structured format:
## Council: [type]
Question: [the user's question]
### [Agent 1] — [position]
[main arguments]
### [Agent 2] — [position]
[main arguments]
### [Agent 3] — [position]
[main arguments]
### Synthesis
- Points of agreement: [...]
- Points of disagreement: [...]
- Identified risks: [...]
Present clear options to the user based on the debate:
Ask the user to decide.
After the user makes their decision in Step 4, offer to write a spec document to docs/specs/.
docs/specs/graphql-migration-strategy.mddocs/specs/ if it does not already exist.src/templates/specs/SPEC_TEMPLATE.md (or the project's local copy) to use as the structural guide..md)draftYYYY-MM-DD format- [ ])docs/specs/<filename>.md.When spawning council agents via the Task tool, always use subagent_type: "general-purpose". Guild agent role names (advisor, developer, tech-lead, etc.) are NOT valid Claude Code subagent_types.
Example:
Task tool with:
subagent_type: "general-purpose"
model: "opus"
prompt: "Read .claude/agents/tech-lead.md and assume that role. Then: [debate question]
[If in workspace, append:]
## Workspace context
[workspace context block from Step 2]"
The model parameter is resolved from the step's model-tier: all council agents use reasoning→"opus".
User: /council Should we migrate from REST to GraphQL?
Council: Architecture
Tech Lead (opus) — Recommends GraphQL for complex queries, keep REST for simple CRUD.
Advisor (opus) — Risk is high mid-project. Suggests incremental adoption.
Developer (opus) — Prefers REST simplicity. GraphQL adds tooling overhead.
Consensus: Incremental adoption. New endpoints in GraphQL, existing stay REST.
docs/specs//council — it captures the debate, decision, and rationaleparallel execution is best-effort — the orchestrator may run parallel steps sequentially if concurrent agent execution is unavailable