confront-codex
Skill4 starsChanged 26 days agoNo licenceView on GitHub
Confronte un plan technique avec un second agent indépendant (Codex depuis Claude, Claude depuis Codex, ou Fable avec --fable) par débats itératifs jusqu'au consensus. Plan final dans docs/, rounds archivés. Option --model pour choisir le modèle. Trigger /confront-codex, "confronter codex", "valider le plan avec codex", "challenger l'approche", "second avis sur le plan".
In this repository9 other files it gives its agents.
- audit-secuSkill
- doc-syncSkill
- humanizeSkill
- impressionSkill
- rename-sessionsSkill
- roastSkill
- save-stateSkill
- tidySkill
- timelogSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.