Compare Models — Development skill for Claude Code
Compare outputs of two models in parallel using tmux.
How to install Compare Models
Installs to ~/.claude/commands/zieka-cpm-public-registry-compare-models.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/zieka/cpm-public-registry/HEAD/.claude/commands/compare-models.md -o ~/.claude/commands/zieka-cpm-public-registry-compare-models.md Restart Claude Code, or start a new session, for it to be picked up.
What Compare Models does
name: compare-models description: Compare outputs of two models in parallel using tmux args: required
Arguments
- the user should specify in the arguments two models to compare and a task to perform
- example:
opus vs sonnet "make a function to reverse a linked list"
Model Comparison Workflow
Add .worktrees/ to .gitignore if they are not there and commit this change separately.
Notes:
- use single quotes instead of double quotes in the git commit command
Run Two Worke
Alternatives in Development
- Claude Context Mode — An MCP server that sits between Claude Code and these outputs 5.3k ★
- Haft — Engineering decisions engine that know when they're stale 1.4k ★
- Setup Context — Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you 1.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Mulmoterminal
Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs
Gw Iss Run Parallel
Create multiple parallel implementations with tmux for trying different approaches.
Claude Yolo
Run parallel Claude Code agents in tmux with automatic permission approval. Auto-approves Bash, WebFetch, and
Claude Maestro
Run multiple Claude Code agents in parallel via tmux. One script. No frameworks.
Conduct
Multi-agent conductor — orchestrate multiple Claude Code instances working on issues in parallel via tmux
PARL
PARL (Parallel-Agent Reinforcement Learning) is a training paradigm that teaches models to decompose complex t
Related Agents
Evolve Behavior Compare
Behavior comparison agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on refactor
Claude Comparator
Blind-compares two outputs for the same task (labeled A and B) and says which is better and why. Use to compar
Gsd Research Synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd-new-project afte