SKILL.md
LLM Council Skill (v0.8.0)
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.
Setup
Install the package:
pip install 'the-llm-council>=0.8.0'Optional extras:
pip install 'the-llm-council[anthropic,openai,gemini]>=0.8.0'
pip install 'the-llm-council[vertex]>=0.8.0'Configure at least one provider key:
| Provider | Environment Variable |
|---|---|
| OpenRouter | OPENROUTERAPIKEY |
| OpenAI | OPENAIAPIKEY |
| Anthropic | ANTHROPICAPIKEY |
| Gemini API | GOOGLEAPIKEY or GEMINIAPIKEY |
| Vertex AI | GOOGLECLOUDPROJECT or ANTHROPICVERTEXPROJECT_ID + ADC |
Verify what is usable in the current shell:
council doctor
council doctor --deep --provider claude --provider gemini-cli --provider codexCanonical Surface
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.
Common Commands
# 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?" --routeUseful Options
| 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` | Reduce reasoning overhead |
--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 |
Provider Names
Canonical provider names:
openrouteropenaianthropicgeminigemini-clivertex-aiclaudecodex
User-selected providers and models should be respected. Health checks and deep doctor probes are for diagnostics, not for silently overriding explicit configuration.
When To Use It
Use council for:
- non-trivial implementation work
- architecture and system design
- code review and security analysis
- planning and build-vs-buy style decisions
- research that benefits from multiple models critiquing each other
Skip it for:
- trivial one-line edits
- simple lookups
- tasks where a single direct model call is clearly enough