Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.
JavaScript agentic-codingai-agentsai-governanceautonomous-agentsclaude-codeclicode-reviewcodexcoding-agentsdeveloper-toolsgit-hooksllmlocal-firstmulti-agentsoftware-factoryspec-driven-developmentverificationvibe-coding
feat(merge): seats report presence: live, idle [B3,I6,I11,A1,C7,N37,A7]
Corey Olsonb66f54c1938a
diff --cc src/help.jsindex 74ce9a84,c19e9ea8..3434f030--- a/src/help.js+++ b/src/help.js@@@ -72,11 -73,9 +73,11 @@@ Set uunread shouts, what to do next; run it to start any sessionpullboard badge write board-derived Shields endpoint JSON to docs/badges/pullboard hooks [uninstall] install Git hooks and agent nudges; uninstall removes only Pullboard's agent nudges- pullboard hook SessionStart|Stop native agent nudges; errors/timeouts warn and never block+ pullboard hook SessionStart|Stop|SessionEnd native agent nudges; errors/timeouts warn and never blockWork+ pullboard map [<module or function>] [--for <item>] [--budget <tokens>] source map for main, a card, or an item's one-hop slice+ slices default to 4k tokens and cap at 8k; effects the scan cannot see say "not detected"pullboard add <lane> <title> [--criterion "..."] [--specs G1.2,K3] [--after 3,4] [--parent <id>][--brief "..." | --brief-file <file>] [--route light|mid]--after: claiming waits until those items are verified