claudecodex

consensus

Consensus create, decide, plan, refine, evaluate, review, panel, phone-a-friend, observer, and observer-collab skills for deliberation, bounded review, consultation, and observation.

0 on GitHubby Thomas Stangv0.2.8MITupdated 7 days agodevelopment
/

Plugin consensus from marketplace skills in tkstang/skills. Commands read from the repo's manifest — 6 days ago.

What it installs

Skills (10)

  • create

    Use when creating a new artifact from a brief with two AI peers, independent drafts, synthesis, and a readable audit trail.

  • decide

    Use when choosing between documented options with two AI peers, independent decision drafts, synthesis, and explicit unresolved dissent.

  • evaluate

    Use when evaluating an artifact against a rubric with two AI peers, unified findings, per-peer reasoning, and dissent preserved in the deliberation log.

  • observer-collab

    Use when two coding-agent sessions should observe each other and collaborate. Composes with the declared observer workflow for pinned review, bounded wake behavior, and explicit human-authority boundaries.

  • observer

    Use when checking what another coding agent (Claude Code, Codex, or Cursor) just did in this project, reviewing a peer session, reading exact own-session Codex evidence, or catching up on new messages. Locates the active transcript, renders a tool-free digest, and tracks runtime-specific read positi

  • panel

    Use when asking a multi-peer consensus panel for independent, attributed responses while the host stays a neutral moderator.

  • phone-a-friend

    Use for advisory peer consultation when the host wants a structured second opinion and remains responsible for dispositioning the take — one-shot by default, or a bounded follow-up exchange with the same peer when the user asks to deliberate, go back and forth, or collaborate with a named model unti

  • plan

    Use when turning a goal and inline constraints into a structured markdown plan with two AI peers and synthesis.

  • refine

    Use when refining a draft and you want two AI peers to deliberate to convergence with structured verdicts, a final artifact, and a readable audit trail.

  • review

    Use when an independent provider-backed reviewer should inspect an explicitly bounded branch, file set, or document without modifying it.

Subagents (1)

  • consensus-section-runner
View source on GitHub tkstang.github.io

More from tkstang/skills

All 2 plugins →

session

claudecodex

Session alignment, status, debriefs, option explanations, necessity checks, next steps, reorientation, handoffs, messaging, transcript workflows, retrospective review, and Session Toolkit CLI guidance.

14 skills

0

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

cli-anything

claude

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

agent-browser

claude

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Open Code Review

codex

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain consensus?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins