LogoAwesome Skills
  • Search
  • Category
  • Tag
  • Blog
LogoAwesome Skills
LogoAwesome Skills

Discover Open-Source Agent Skills for AI Coding Assistants

Product

  • Search
  • Category
  • Tag
  • Blog

Resources

  • Claude Skill Docs
  • Antigravity Skills Docs

Tools

  • Claude Code
  • OpenCode
  • Cursor
  • Codex
  • Antigravity

Company

  • Privacy Policy
  • Terms of Service
  • Sitemap

©2026 Awesome Skills. All rights reserved.

Privacy PolicyTerms
Back to Skills

council

Run multi-judge consensus.

376stars40forksUpdated 6/2/2026
Developer Tools#decision-making#judgment#consensus#evaluation#multi-agent#review

Security Assessment

High Risk(40/100)

Detected risks:

Destructive Operations([references/backend-claude-teams.md] rm -rf)
Security Score40/100

About council

The council skill provides a multi-model consensus process that convenes multiple independent reasoners around a shared briefing and produces a synthesized outcome. It is designed to support judgment-intensive decisions where a single evaluation may not be sufficient. Rather than owning a workflow step itself, the skill acts as a cross-cutting judgment layer that other processes can consume. Its primary purpose is to improve confidence in plans, artifacts, proposals, and acceptance decisions by gathering independent assessments and consolidating them into a single result.

The skill supports three deliberation patterns through its mode system: brainstorm, debate, and verdict. Brainstorm mode focuses on generating diverse ideas, perspectives, and risks without issuing a pass/fail judgment. Debate mode enables competing positions to be evaluated and ranked while preserving dissenting viewpoints. Verdict mode, which is the default behavior, independently evaluates an artifact against defined standards and produces a consolidated PASS, WARN, or FAIL outcome. Additional controls such as focus, depth, runtime, roster selection, and adversarial evaluation rounds allow users to tailor the deliberation process without changing the underlying lifecycle of convene, brief, deliberate, synthesize, and record.

Typical use cases include validating plans before execution, reviewing non-mechanical correctness during implementation, evaluating product or design decisions, assessing security-sensitive systems, and performing adversarial reviews when consumer-facing behavior requires deeper scrutiny. The skill is intended for teams, reviewers, architects, researchers, and decision-makers who need structured multi-agent judgment and consensus rather than a single-model opinion. It operates independently and does not require specific workflow tooling or external command chains to be used.

FAQ

What modes does the council skill support?

The skill supports exactly three modes: brainstorm, debate, and verdict. Verdict is the default mode when no mode is specified.

What output does verdict mode produce?

Verdict mode produces a single consolidated PASS, WARN, or FAIL result along with consolidated findings from the independent evaluations.

Can I customize how the council evaluates a topic?

Yes. You can adjust focus, depth, runtime, roster selection, and adversarial evaluation settings. These are configuration knobs and do not change the underlying deliberation mode.

Does the skill require a specific workflow or external toolchain?

No. The documentation states that the skill works independently and does not require an RPI workflow, ratchet chain, or ao CLI.

Are there any runtime requirements?

Yes. The skill requires a runtime capable of spawning parallel subagents, and certain deliberation patterns such as debate and adversarial evaluation have additional runtime requirements related to agent interaction.

All Files

39 files
references/claude-code-latest-features.md4.3 KB
View
references/caching-guidance.md1.4 KB
View
references/flags-reference.md4.5 KB
View
references/model-routing.md3.2 KB
View
references/backend-codex-subagents.md4.4 KB
View
references/brainstorm-techniques.md2.7 KB
View
references/dueling-route.md5.2 KB
View
references/finding-extraction.md2.5 KB
View
references/reviewer-config-example.md1.0 KB
View
references/adversarial-protocol.md5.7 KB
View
references/backend-background-tasks.md3.9 KB
View
references/consensus-and-output.md3.3 KB
View
references/cli-spawning.md8.0 KB
View
references/multi-agent-architecture.md2.4 KB
View
references/packet-format.md3.1 KB
View
references/strategic-doc-validation.md12.3 KB
View
references/architecture-flow.md7.2 KB
View
references/cross-vendor-duel-when-to-use.md5.6 KB
View
references/explorers.md3.8 KB
View
references/presets.md0.5 KB
View
SKILL.md15.5 KB
View
references/backend-claude-teams.md9.5 KB
View
references/backend-inline.md2.2 KB
View
references/council-modes.feature3.1 KB
View
references/modes.md4.3 KB
View
references/quick-mode.md2.3 KB
View
schemas/verdict.json1.9 KB
View
scripts/validate.sh3.7 KB
View
references/agent-prompts.md15.5 KB
View
references/examples-extended.md3.3 KB
View
references/evidence-mode.md6.0 KB
View
references/ralph-loop-contract.md2.0 KB
View
references/personas.md14.0 KB
View
scripts/validate-council.sh10.9 KB
View
references/model-profiles.md2.9 KB
View
references/output-format.md4.7 KB
View
references/task-type-rigor-gate.md2.7 KB
View
scripts/validate-mixed-artifacts.sh6.8 KB
View
references/troubleshooting.md1.7 KB
View

Install council

Download and extract the skill files to your .claude/skills/ directory.

Quick Setup:

  1. Copy the skill folder to .claude/skills/
  2. Claude will automatically detect and use the skill

Repository

boshu2/agentops

Related Skills

dbt-sf-to-bq-translator

21,076

build-models

102

html-prototype

3,588

doc

448