Add claude-code-dual-build to Multi-Agent Swarms - #42
Open
cjcsecurity wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adding
claude-code-dual-build— a Claude Code skill that orchestrates symmetric Claude+Codex builds with mandatory bidirectional cross-review.Why I think it fits Multi-Agent Swarms specifically: the skill coordinates specialized roles (claude-builder, codex-builder, claude-reviewer, codex-reviewer), runs them in parallel in isolated git worktrees, and has each model review the opposite model's diff before consolidation. The cross-review is the load-bearing piece — different model families catch different bug classes (e.g., on a real
mission-controlrun, Claude reviewing Codex's stop-button code caught a SIGKILL→ESRCH race + ansspermission-model UX bug that the implementing model missed). This shape feels closer to coordinated specialists than a parallel runner per se.Repo: https://github.com/cjcsecurity/claude-code-dual-build
The README has worked examples + a comparison vs. existing patterns in this exact space (asymmetric, single-model parallel, sequential pipeline, consensus drafting, multi-reviewer fan-out, communication bridge) — happy to revise placement if you'd prefer it land elsewhere.