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
{
"blueprint": 1,
"name": "pullboard",
"title": "Pullboard, built on Pullboard",
"version": 1,
"kind": "practice",
"by": "Pullboard",
"summary": "The rules we build Pullboard with: a frozen bar on every item, a second agent on every change, and a landing gate that runs every test.",
"prefix": "PB",
"rules": [
{ "key": "PB1", "text": "A builder never verifies their own work.", "why": "the agent that wrote a change is the one least likely to see what it missed." },
{ "key": "PB2", "text": "Every item's check fails before the change and passes after it.", "why": "a check that passes either way proves nothing." },
{ "key": "PB3", "text": "Main only moves when the whole test suite passes.", "why": "two changes can each pass alone and still break each other." }
],
"items": [
{ "key": "1", "title": "The gate runs every test in the project", "cites": ["PB3"], "criterion": "pullboard.json names a gate, and that gate runs every test file in the project. test/gate.test.js lists the test files, checks the gate reaches each one, and fails before the change.", "brief": "Files:\n- pullboard.json (its gate)\n- test/gate.test.js\nTest:\n- test/gate.test.js lists every test file and fails on one the gate command does not run", "check": "node --test test/gate.test.js" }
]
}