alanshurafa/co-evolution

Structured refinement of any document between AI agents. Two agent roles bounce a file back and forth using disagreement markers until it converges. Open source, agent-agnostic, runs from any terminal.

3Stars on the repository
5Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

co-evolution

01

alanshurafa/co-evolution

Skill Claude CodeCodex

General-purpose co-evolution for questions, ideas, drafts, plans, specs, arguments, and markdown documents. Composes or bounces content between agents using [CONTESTED]/[CLARIFY] markers until it converges. Triggers on "co-evolution", "co-evolve", "co evolve", "bounce", "bounce document", "agent bouncer", "refine with…

3 2d ago A 118 tokens original MIT

codex-build

02

alanshurafa/co-evolution

Skill Claude CodeCodex

Orchestrate Codex to BUILD code in the background while this Claude Code session (typically Opus) plans and reviews — never babysitting. The session composes the implementation plan, kicks the dev-review runner detached via a background Bash task with --preset codex-build, ENDS ITS TURN, and is woken on exit to run a…

3 2d ago A 181 tokens original MIT

dev-review

03

alanshurafa/co-evolution

Skill Claude CodeCodex

Code-focused plan-bounce-execute workflow between Claude Code (Opus) and Codex CLI. Use when the user wants repo files changed, a bug fixed, a feature implemented, or a code plan verified before execution. One AI composes a plan, it bounces between agents with [CONTESTED]/[CLARIFY] markers until refined, then the…

3 2d ago B 176 tokens original MIT