Skip to content
Agentmart
Submit a tool

council

Run a multi-model council with independent opinions, anonymized peer review, and a chairman.

Skill by Kshintak

IndexedMIT
Write a review

Chalk Labs

Need help deploying council?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/kshintak-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

Run a multi-model council with independent opinions, anonymized peer review, and a chairman. Use when STATUS phase is council or the human says council, other AIs, or pressure-test this.

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 and code. Checked Nov 1, 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
Run a multi-model council with independent opinions, anonymized peer review, and a chairman. Use when STATUS phase is council or the human says council, other AIs, or pressure-test this.
License
MIT
Instructions
38 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# council

Karpathy-style three-stage deliberation, run on real, different-vendor lanes. Read the harvest scorecard + assumptions first. Do not re-research.

The graph gives each seat its own card on its own vendor's lane. A seat with no available lane is written as `Verdict: ABSENT` by hbs. **Never impersonate a seat.** Your card's `Args` tell you the stage and your seat.

## Stage 1 — independent opinion (`stage: 1`, one card per seat)

- Do not read other seats' files.
- Write `build/06-council/<seat>.md` from `~/.build-framework/templates/build/06-council/vote.md`:
  Verdict (Approve / Concern / Block), three bullets, and "would change my vote if".

## Stage 2 — anonymized peer review (`stage: 2`, one card per seat)

1. `hbs council anonymize --repo <repo>` (idempotent; the first reviewer creates it).
2. Read only `build/06-council/anon/Response-*.md`. Skip the one that is yours.
3. Write `build/06-council/review-<seat>.md`: rank the others by letter for accuracy and insight, and "what others got wrong".

## Stage 3 — chairman (`stage: 3`)

1. `hbs council unmask --repo <repo>` → writes `peer-review.md` with the label map in its footer.
2. Write `build/06-council/chairman.md`:
   - Agreements
   - Tensions
   - Blocks (a single seat's Block is carried, not outvoted)
   - Recommended path
   - What would reopen the decision
   - ABSENT seats, named
   - `- Verdict: Approve | Concern | Block` (merged)
3. The chairman merges; the chairman does not campaign for its own seat's view.
4. Merged verdict **Block** → `kanban_block(reason="COUNCIL BLOCK: <what would reopen it>")`. hbs re-harvests once (the decision loop), then leaves it to the human.
   Otherwise complete the card.

## Manual council (no harness lanes yet)

You are the router: paste the scorecard into each vendor's app, save each answer as `build/06-council/<seat>.md`, then run stages 2 and 3 above in any tool.

From Kshintak/new-build-framework, MIT.

More from Kshintak/new-build-framework

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 29, 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 Kshintak

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get council running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying council?

CallGet help
Cite this page

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