From llm-council
Runs multi-LLM council for adversarial debate, critique, and synthesis on implementation, architecture, review, security, research, and planning tasks via llm-council CLI.
npx claudepluginhub sherifkozman/the-llm-council --plugin llm-councilThis skill uses the workspace's default tool permissions.
Multi-model council: parallel drafts, adversarial critique, validated synthesis.
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
Multi-model council: parallel drafts, adversarial critique, validated synthesis.
This skill requires the
the-llm-councilpackage to be installed. The skill provides the agent-side interface; actual runs happen through the installedcouncilCLI.
Install the package:
pip install 'the-llm-council>=0.7.16'
Optional extras:
pip install 'the-llm-council[anthropic,openai,gemini]>=0.7.16'
pip install 'the-llm-council[vertex]>=0.7.16'
Configure at least one provider key:
| Provider | Environment Variable |
|---|---|
| OpenRouter | OPENROUTER_API_KEY |
| OpenAI | OPENAI_API_KEY |
| Anthropic | ANTHROPIC_API_KEY |
| Gemini API | GOOGLE_API_KEY or GEMINI_API_KEY |
| Vertex AI | GOOGLE_CLOUD_PROJECT or ANTHROPIC_VERTEX_PROJECT_ID + ADC |
Verify what is usable in the current shell:
council doctor
council doctor --deep --provider claude --provider gemini-cli --provider codex
council run <subagent> [--mode <mode>] "<task>" [options]
Primary subagents:
| Subagent | Modes | Use for |
|---|---|---|
drafter | impl, arch, test | implementation, architecture, tests |
critic | review, security | code review and security analysis |
planner | plan, assess | execution plans and decision assessments |
researcher | — | research with sources and evidence |
router | — | task classification and routed handoff |
synthesizer | — | final merged output |
Legacy aliases such as implementer, architect, reviewer, red-team,
assessor, test-designer, and shipper still work, but they are no longer
the preferred interface.
# Implementation
council run drafter --mode impl "Add pagination to users API"
# Architecture
council run drafter --mode arch "Design a caching layer"
# Tests
council run drafter --mode test "Design tests for cursor pagination"
# Review
council run critic --mode review "Review auth changes"
# Security
council run critic --mode security "Analyze auth system vulnerabilities"
# Planning
council run planner --mode plan "Plan MongoDB to PostgreSQL migration"
# Assessment
council run planner --mode assess "Redis vs Memcached for sessions"
# Research
council run researcher "Research WebSocket libraries for Node.js"
# Router handoff
council run router "Should we buy or build auth?" --route
| Option | Purpose |
|---|---|
--mode <mode> | Select a runtime mode for drafter, critic, or planner |
--json | Return structured JSON |
--verbose | Show resolved execution details and council phases |
--providers | Explicit provider list. Omit to use config defaults |
--models | Explicit model list |
--runtime-profile bounded | Lower latency and token budgets |
| `--reasoning-profile off | light` |
--route | Follow a router decision into the chosen subagent/mode |
--files | Add file context to the task |
--dry-run | Show the resolved plan without executing |
--schema | Use a custom output schema |
Canonical provider names:
openrouteropenaianthropicgeminigemini-clivertex-aiclaudecodexUser-selected providers and models should be respected. Health checks and deep doctor probes are for diagnostics, not for silently overriding explicit configuration.
Use council for:
Skip it for: