npx claudepluginhub boshu2/agentops --plugin agentopsThis skill uses the workspace's default tool permissions.
Spawn parallel judges with different perspectives, consolidate into consensus. Works for any task — validation, research, brainstorming.
references/agent-prompts.mdreferences/architecture-flow.mdreferences/backend-background-tasks.mdreferences/backend-claude-teams.mdreferences/backend-codex-subagents.mdreferences/backend-inline.mdreferences/brainstorm-techniques.mdreferences/caching-guidance.mdreferences/claude-code-latest-features.mdreferences/cli-spawning.mdreferences/consensus-and-output.mdreferences/debate-protocol.mdreferences/evidence-mode.mdreferences/examples-extended.mdreferences/explorers.mdreferences/finding-extraction.mdreferences/flags-reference.mdreferences/model-profiles.mdreferences/model-routing.mdreferences/multi-agent-architecture.mdCreates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Spawn parallel judges with different perspectives, consolidate into consensus. Works for any task — validation, research, brainstorming.
/council --quick validate recent # fast inline check
/council validate this plan # validation (2 agents)
/council brainstorm caching approaches # brainstorm
/council research kubernetes upgrade strategies # research
/council --preset=security-audit validate the auth system # preset personas
/council --deep --explorers=3 research upgrade automation # deep + explorers
/council --debate validate the auth system # adversarial 2-round review
/council # infers from context
Council works independently — no RPI workflow, no ratchet chain, no ao CLI required.
| Mode | Agents | Execution Backend | Use Case |
|---|---|---|---|
--quick | 0 (inline) | Self | Fast single-agent check, no spawning |
| default | 2 | Runtime-native (Codex sub-agents preferred; Claude teams fallback) | Independent judges (no perspective labels) |
--deep | 3 | Runtime-native | Thorough review |
--mixed | 3+3 | Runtime-native + Codex CLI | Cross-vendor consensus |
--debate | 2+ | Runtime-native | Adversarial refinement (2 rounds) |
Council requires a runtime that can spawn parallel subagents and (for --debate) send messages between agents. Use whatever multi-agent primitives your runtime provides. If no multi-agent capability is detected, fall back to --quick (inline single-agent).
Required capabilities:
--quick)--debate)Skills describe WHAT to do, not WHICH tool to call. See skills/shared/SKILL.md for the capability contract.
After detecting your backend, read the matching reference for concrete spawn/wait/message/cleanup examples:
skills/shared/references/claude-code-latest-features.mdreferences/claude-code-latest-features.mdreferences/backend-claude-teams.mdreferences/backend-codex-subagents.mdreferences/backend-background-tasks.md--quick) → references/backend-inline.mdSee also references/cli-spawning.md for council-specific spawning flow (phases, timeouts, output collection).
--debateUse --debate for high-stakes or ambiguous reviews where judges are likely to disagree:
Skip --debate for routine validation where consensus is expected. Debate adds R2 latency (judges stay alive and process a second round via backend messaging).
Incompatibilities:
--quick and --debate cannot be combined. --quick runs inline with no spawning; --debate requires multi-agent rounds. If both are passed, exit with error: "Error: --quick and --debate are incompatible."--debate is only supported with validate mode. Brainstorm and research do not produce PASS/WARN/FAIL verdicts. If combined, exit with error: "Error: --debate is only supported with validate mode."Council infers task type from natural language. Trigger words: validate (validate, check, review, assess, critique, feedback, improve), brainstorm (brainstorm, explore, options, approaches), research (research, investigate, deep dive, analyze, examine, evaluate, compare).
See references/task-type-rigor-gate.md for the trigger-word table, the MANDATORY first-pass rigor gate for plan/spec validation, and the full --quick single-agent inline mode contract.
See references/architecture-flow.md for the context-budget rule, full Phase 1→3 execution flow diagram, reviewer-config loading, graceful degradation table, effort levels, and pre-flight checks.
See references/packet-format.md for the full JSON packet schema (fields, output_schema, judge-prompt boundary rules) and the Empirical Evidence Rule for feasibility reviews.
Perspectives & Presets: Use
Readtool onskills/council/references/personas.mdfor persona definitions, preset configurations, and custom perspective details.
Auto-Escalation: When --preset or --perspectives specifies more perspectives than the current judge count, automatically escalate judge count to match. The --count flag overrides auto-escalation.
See references/consensus-and-output.md for named-perspective usage (--perspectives, --perspectives-file, YAML format, flag priority), consensus verdict rules (PASS/WARN/FAIL combination table, DISAGREE resolution), and the finding-extraction flywheel protocol. See references/personas.md for built-in presets.
Explorer Details: Use
Readtool onskills/council/references/explorers.mdfor explorer architecture, prompts, sub-question generation, and timeout configuration.
Summary: Judges can spawn explorer sub-agents (--explorers=N, max 5) for parallel deep-dive research. Total agents = judges * (1 + explorers), capped at MAX_AGENTS=12.
--debate)Debate Protocol: Use
Readtool onskills/council/references/debate-protocol.mdfor full debate execution flow, R1-to-R2 verdict injection, timeout handling, and cost analysis.
Summary: Two-round adversarial review. R1 produces independent verdicts. R2 sends other judges' verdicts via backend messaging (send_input or SendMessage) for steel-manning and revision. Only supported with validate mode.
Agent Prompts: Use
Readtool onskills/council/references/agent-prompts.mdfor judge prompts (default and perspective-based), consolidation prompt, and debate R2 message template.
Consensus verdict combination rules, DISAGREE handling, and the finding-extraction flywheel protocol live in references/consensus-and-output.md. Full report templates (validate, brainstorm, research) and debate-report additions live in references/output-format.md. All reports write to .agents/council/YYYY-MM-DD-<type>-<target>.md. Findings extraction targets .agents/council/extraction-candidates.jsonl; see references/finding-extraction.md for schema and classification heuristics.
Core consensus rules: All PASS -> PASS; Any FAIL -> FAIL; Mixed PASS/WARN -> WARN; cross-vendor disagreement -> DISAGREE.
Minimum quorum: 1 agent. Recommended: 80% of judges. On timeout, proceed with remaining judges and note in report. On user cancellation, shutdown all judges and generate partial report with INCOMPLETE marker.
| Env var | Default |
|---|---|
COUNCIL_CLAUDE_MODEL | sonnet |
COUNCIL_EXPLORER_MODEL | sonnet |
COUNCIL_CODEX_MODEL | gpt-5.3-codex |
COUNCIL_TIMEOUT | 120 |
COUNCIL_EXPLORER_TIMEOUT | 60 |
COUNCIL_R2_TIMEOUT | 90 |
| Flag | Description |
|---|---|
--technique=<name> | Brainstorm technique (reverse, scamper, six-hats). See references/brainstorm-techniques.md. |
--profile=<name> | Model quality profile (balanced, budget, fast, inherit, quality, thorough). See references/model-profiles.md. |
See references/flags-reference.md for the full flag and environment variable reference (COUNCIL_TIMEOUT, COUNCIL_CODEX_MODEL, --deep, --mixed, --debate, --evidence, --commit-ready, --preset, --profile, and all other flags).
CLI Spawning: Use
Readtool onskills/council/references/cli-spawning.mdfor team setup, Claude/Codex agent spawning, parallel execution, debate R2 commands, cleanup, and model selection.
See references/examples-extended.md for the full example catalog and walkthroughs (fast single-agent validation, adversarial debate, cross-vendor consensus with explorers).
See references/troubleshooting.md for common error messages, causes, and solutions, plus the judge→council migration table.
See references/multi-agent-architecture.md for the deliberation protocol, communication rules, Ralph Wiggum compliance, degradation behavior, and judge naming convention.
skills/vibe/SKILL.md — Complexity + council for code validation (uses --preset=code-review when spec found)skills/pre-mortem/SKILL.md — Plan validation (uses --preset=plan-review, always 3 judges)skills/post-mortem/SKILL.md — Work wrap-up (uses --preset=retrospective, always 3 judges + retro)skills/swarm/SKILL.md — Multi-agent orchestrationskills/standards/SKILL.md — Language-specific coding standardsskills/research/SKILL.md — Codebase exploration (complementary to council research mode)