council
Run a multi-model council with independent opinions, anonymized peer review, and a chairman.
Skill by Kshintak
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.
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.
About
Use cases: testing
Reviews
Write a reviewNo 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
- 0.570score
vibeproof
Kshintak
Builds or fixes a website so it doesn't look vibe coded.
SkillAFreshness: AClaude Code +9 - 0.565score
verify
Kshintak
Independently verify the full-build worktree — run the real build/test commands, check for test tampering, write build/11-verify.md, and pass or fail the cycle.
SkillAFreshness: AClaude Code +9 - 0.565score
scout
Kshintak
Screen newly discovered skills, MCP servers, repos, harness releases, and companies that could make the build system better; score them, quarantine-check the…
SkillAFreshness: AClaude Code +9 - 0.565score
box-it-up
Kshintak
Plan, build, and compare isolated spikes — the smallest falsifiable demo, built in parallel git worktrees by different vendors.
SkillAFreshness: AClaude Code +9 - 0.565score
conductor
Kshintak
Claude Code only (Hermes uses hermes-conductor).
SkillAFreshness: AClaude Code +9 - 0.565score
distill
Kshintak
Turn a finished run into reusable learning — ACE-style lesson bullets merged by code, and skill proposals that must pass an eval before promotion.
SkillAFreshness: AClaude Code +9 - 0.565score
full-build
Kshintak
Implement the product in a worktree from the winning spike, one feature at a time, test-first, until the verify command passes — or, when the human says…
SkillAFreshness: AClaude Code +9 - 0.565score
review
Kshintak
Cross-vendor code review of the full-build worktree before verify — findings P0–P3 with file:line; P0–P2 sends the build back for another cycle.
SkillAFreshness: AClaude Code +9 - 0.565score
optimize
Kshintak
Explain and steer the build system's self-improvement — the cheaper / faster / more accurate / less-hallucinating scorecard, running A/B experiments, accepted…
SkillAFreshness: AClaude Code +9 - 0.565score
retro
Kshintak
Measure a finished (or capped) run — metrics from the hbs ledger and board, vote on the lessons that were injected, find weak spots for the scout.
SkillAFreshness: AClaude Code +9 - 0.565score
grill
Kshintak
Interview the operator until build/01-assumptions.md has no OPEN rows.
SkillAFreshness: AClaude Code +9 - 0.565score
harvest
Kshintak
Find similar builds, repos, and companies and score them.
SkillAFreshness: AClaude Code +9
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
- Repository
- github.com/Kshintak/new-build-framework
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Kshintak
- 0.570score
vibeproof
Kshintak
Builds or fixes a website so it doesn't look vibe coded.
SkillAFreshness: AClaude Code +9 - 0.565score
grill
Kshintak
Interview the operator until build/01-assumptions.md has no OPEN rows.
SkillAFreshness: AClaude Code +9 - 0.565score
harvest
Kshintak
Find similar builds, repos, and companies and score them.
SkillAFreshness: AClaude Code +9 - 0.565score
verify
Kshintak
Independently verify the full-build worktree — run the real build/test commands, check for test tampering, write build/11-verify.md, and pass or fail the cycle.
SkillAFreshness: AClaude Code +9 - 0.565score
box-it-up
Kshintak
Plan, build, and compare isolated spikes — the smallest falsifiable demo, built in parallel git worktrees by different vendors.
SkillAFreshness: AClaude Code +9 - 0.565score
conductor
Kshintak
Claude Code only (Hermes uses hermes-conductor).
SkillAFreshness: AClaude Code +9
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.
Cite this page
council skill. Agent Mart. https://agentmart.dev/skills/kshintak-council (last updated 2026-10-24)