CEO Decision Loop — the ORBIT execution protocol (OBSERVE → REASON → BUILD → INSPECT → TURN) for one iteration of NXTG-Forge autonomous product governance. Preloaded into the nxtg-ceo-loop agent and started by the /forge:ceo-loop command; the ceo-loop-stop.sh Stop hook re-invokes it each iteration until the queue empties or limits hit. Use when running or resuming a CEO-LOOP: classify pending decisions by depth, apply the impact×reversibility matrix, write the append-only decision journal + progress file, run retrograde verification, update trust calibration, and decide continue-or-stop.
$npx -y skills add nxtg-ai/forge-plugin --skill ceo-loopInstalls into the current project.
Run `npx skills use "https://github.com/nxtg-ai/forge-plugin" --skill "nxtg-ai/forge-plugin/ceo-loop"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/nxtg-ai/forge-plugin" that are relevant to the current task. Run `npx skills add "https://github.com/nxtg-ai/forge-plugin"` and select the relevant skills, then follow their instructions.