Skip to content
Agentmart
Submit a tool

council

Pressure-tests meaningful decisions through a five-advisor Council using Contrarian, First Principles, Expansionist, Outsider, and Executor perspectives, peer…

Skill by bvts

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/bvts-council

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Pressure-tests meaningful decisions through a five-advisor Council using Contrarian, First Principles, Expansionist, Outsider, and Executor perspectives, peer review, and chairman synthesis. Use when the user asks to council, debate, pressure-test, stress-test, validate, or resolve a genuine multi-option decision.

Use cases: testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/council

What's inside

Skill name
council
Description
Pressure-tests meaningful decisions through a five-advisor Council using Contrarian, First Principles, Expansionist, Outsider, and Executor perspectives, peer review, and chairman synthesis. Use when the user asks to council, debate, pressure-test, stress-test, validate, or resolve a genuine multi-option decision.
License
MIT
Instructions
91 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# /council — COUNCIL OF FIVE

This skill implements the Council-of-5 methodology supplied for this pack and is compatible with Ole Lehmann's `llm-council` concept.

## Trigger

Strong triggers:
- council this
- run the council
- war room this
- pressure-test this
- stress-test this
- debate this

Strong decision triggers when a real tradeoff exists:
- should I X or Y
- which option
- what would you do
- is this the right move
- validate this
- get multiple perspectives
- I can't decide
- I'm torn between

Do not use for trivial facts or obvious yes/no questions.

## Advisors

1. Contrarian — seek failure modes, missing assumptions, hidden costs.
2. First Principles Thinker — reconstruct the problem from fundamentals.
3. Expansionist — find upside, scale, adjacent opportunity, compounding effects.
4. Outsider — challenge jargon and expert blind spots from fresh context.
5. Executor — test feasibility, sequencing, dependencies, and first action.

## Process

### 1. Enrich context

Inspect only relevant workspace context:
- project instructions
- product/business docs
- constraints
- referenced files
- existing implementation
- prior council artifacts

### 2. Frame the question

Produce a neutral frame containing:
- core decision
- context
- options
- constraints
- stakes
- success criteria
- known unknowns

Do not insert your own conclusion.

### 3. Independent advisors

Use five parallel subagents when available. Each receives only the framed decision and its own perspective. Encourage direct, specific analysis and explicit assumptions.

### 4. Blind peer review

Anonymize outputs as A–E and randomize advisor mapping. Use parallel reviewers when available. Each reviewer identifies:
- strongest response and why
- biggest blind spot
- what all responses missed

### 5. Chairman synthesis

Synthesize:
- Where the Council Agrees
- Where the Council Clashes
- Blind Spots the Council Caught
- The Recommendation
- The One Thing to Do First

For political/electoral matters, keep the synthesis neutral and factual; do not rank candidates, endorse political choices, predict outcomes, or otherwise steer political decisions.

### 6. Artifacts

For full sessions, save:
- `council-report-[timestamp].html`
- `council-transcript-[timestamp].md`

The HTML must be self-contained and easy to scan, with collapsible advisor/review sections and a concise chairman synthesis.

If an installed `llm-council` skill is available, delegate to it instead of duplicating the same workflow.

From bvts/max-the-prompter, MIT.

More from bvts/max-the-prompter

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Sep 23, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from bvts

Cite this page

council skill. Agent Mart. https://agentmart.dev/skills/bvts-council (last updated 2026-10-24)