Skip to content
Agentmart
Submit a tool

consensus-gated-grilling

Resolve decisions through dependency-ordered questions with bounded subagent consensus.

Skill by wufei-png

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying consensus-gated-grilling?

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/wufei-png-consensus-gated-grilling

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

Resolve decisions through dependency-ordered questions with bounded subagent consensus.

Use cases: productivity, agent-building

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/consensus-gated-grilling

What's inside

Skill name
consensus-gated-grilling
Description
Resolve decisions through dependency-ordered questions with bounded subagent consensus.
License
MIT
Instructions
24 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Consensus-Gated Grilling

Interview me relentlessly, working through the decision tree in dependency order.

Resolve factual questions from available context or tools. Choose an option directly when the established constraints clearly favor it. Ask only about genuine tradeoffs: present viable options and compare when each fits. Recommend one only when established priorities support it; otherwise explain which scenarios favor each option and let the user choose.

Ask one question at a time and wait for feedback. Treat a user-provided per-turn maximum as a ceiling; batch only tightly related questions whose prerequisites are settled and whose answers do not depend on one another.

Reopen a settled decision when new information invalidates its assumptions.

Before each candidate question or permitted batch:

1. Draft its options, tradeoffs, and any supported recommendation.
2. Start one fresh, read-only subagent with the conversation context, or the positive number the user requested. Give multiple reviewers distinct, non-leading perspectives. They must not edit or question the user.
3. Have each independently challenge the question's necessity, option completeness, tradeoffs, and recommendation using evidence, the strongest countercase, and what would change the conclusion.
4. Synthesize evidence rather than votes. For a material disagreement, state the provisional position and evidence to the original reviewer.
5. Allow at most two exchange rounds. Each response must maintain, revise, or withdraw the challenge with supporting evidence.
6. If disagreement remains, start one fresh, read-only tie-breaker with neutral context and both positions. If it still remains unresolved, ask the user to adjudicate before showing the question. Do not silently reject a disputed correction or force consensus.

Use accepted reviewer corrections to revise the candidate. If the requested reviewers are unavailable, disclose that and ask whether to retry or continue without the gate. Never silently self-review or reduce their number.

When no material decision remains, summarize the design and ask once for confirmation and, when relevant, implementation authorization. Do not modify code before approval.

From wufei-png/skills, MIT.

More from wufei-png/skills

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Sep 6, 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 wufei-png

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 consensus-gated-grilling 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 consensus-gated-grilling?

CallGet help
Cite this page

consensus-gated-grilling skill. Agent Mart. https://agentmart.dev/skills/wufei-png-consensus-gated-grilling (last updated 2026-10-24)