skills.rest
kstawiski
kstawiskiCOMMUNITY
Explore all skills by this author →
Website𝕏@KonradStawiskiGitHub

claude-codex-gemini-consensus

Coordinate blinded cross-model consensus among Claude, Codex, and Gemini for code reviews.

Updated Aug 23, 2026
Search Tags:#automation#analysis#consensus#code-review#publication#blinded
One-click install
npx skills add https://github.com/kstawiski/claude-skills --skill claude-codex-gemini-consensus
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-codex-gemini-consensus
Source: https://github.com/kstawiski/claude-skills/tree/main/claude-codex-gemini-consensus
Command: npx skills add https://github.com/kstawiski/claude-skills --skill claude-codex-gemini-consensus

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires codex, gemini, claude, timeout, perl, bash, and includes scripts (resource) and references (resource) components.

What problem does it solve?

The Claude-Codex-Gemini Consensus skill orchestrates a blinded, cross-model review workflow that ensures rigorous validation of plans, code changes, and analyses by three leading AI agents.

Core Features & Use Cases

  • Blinded multi-model reviews to prevent anchoring and promote independent verification.
  • SOP-based workflows covering Code Review, Analysis Planning/Execution, and Publication-ready Reporting.
  • Consensus-building orchestration with round-based discussions and mandatory sign-off from all three models.
  • Audit-ready logs and artifacts for traceability, reproducibility, and governance.

Quick Start

Use the skill to orchestrate a blinded consensus on a target project. Examples:

  • Run independent reviews: ./scripts/review.sh codex path/to/target
  • Start blinded discussion for a plan: ./scripts/blinded-consensus.sh plan analysis/plan.md --cd /path/to/project --rounds 3
  • Synthesize final consensus and generate a report: ./scripts/consensus-review.sh codepath --blinded --rounds 3 This section uses plain text prompts and commands (no code blocks).

Note: The actual execution relies on locally installed Claude, Codex, and Gemini CLIs.

Quick Start

  • Run a full blinded consensus on a codebase: ./scripts/blinded-consensus.sh code /path/to/project --rounds 3
  • Validate an analysis plan: ./scripts/blinded-consensus.sh plan analysis/plan.md --cd /path/to/project --rounds 2
  • Generate the final publishable report: ./scripts/consensus-review.sh code /path/to/project --blinded --rounds 3

Frequently Asked Questions about claude-codex-gemini-consensus

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How does blinded consensus improve AI code review validation?▼

Blinded consensus improves AI code review validation by preventing anchoring bias, ensuring Claude, Codex, and Gemini independently verify plans and code changes before reaching a unanimous sign-off.

How do I run a blinded multi-model code review across different AI agents?▼

To run a blinded multi-model code review, execute the blinded-consensus shell script with your target project path and specify the number of discussion rounds to orchestrate the cross-model validation.

Do I need local CLI installations to use multi-model consensus workflows?▼

Yes, you need the Claude, Codex, and Gemini CLIs locally installed to execute the blinded cross-model review workflow and generate audit-ready logs and reproducible artifacts.

What is the best way to validate an analysis plan using multiple AI models?▼

The best way to validate an analysis plan is using a round-based discussion script that enforces tri-model validation, requiring unanimous sign-off from all participating agents for robust governance.

Can I generate publication-ready reports after reaching a tri-model consensus?▼

Yes, you can generate publication-ready reports by running the consensus-review script after the blinded discussion, which synthesizes the final validated outputs into a reproducible artifact.

Why does the cross-model consensus workflow enforce round-based discussions?▼

The cross-model consensus workflow enforces round-based discussions to build agreement iteratively, ensuring all three models rigorously validate the target code or analysis before issuing a mandatory unanimous sign-off.

Related Skills

Explore More Software Engineering Skills→
kozyszookozyszoo
1

plan-review

Validate implementation plans via parallel Codex, Gemini, and Claude reviews.

Community
Advanced
lookatitudelookatitude
6

guild-wiki-ingest

Ingest URLs, files, or pasted text into categorized wiki pages with provenance metadata.

Community
Advanced
burgebjburgebj

ship

Automate testing, code review, pull request creation, and deployment workflows.

Community
Advanced
evolution-foundationevolution-foundation
520

dev-ccg

Orchestrate tri-model execution across Claude, Codex, and Gemini to synthesize consensus answers.

Official
Advanced