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
chore(map): compose accepted map with landed main [C7,H16]
Corey Olson5f8dfee4ec77
diff --cc src/help.jsindex 1b56ce13,695a5c71..88abd9c9--- a/src/help.js+++ b/src/help.js@@@ -71,11 -71,10 +71,12 @@@ Set upullboard resume [--diagnostics] where you are: your claim, branch, what came back,unread shouts, what to do next; run it to start any sessionpullboard badge write board-derived Shields endpoint JSON to docs/badges/- pullboard hooks reinstall the git hooks (e.g. after a fresh clone)+ 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 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 verifieddiff --cc src/templates.jsindex 808ce1b6,0b604a86..b6d55719--- a/src/templates.js+++ b/src/templates.js@@@ -144,9 -144,9 +144,11 @@@ When a reject names a structured cause6. A reject reopens the item. Fix it, commit, claim, submit again; the same head is refused. If you cannot get an item green, do not force it: \`pullboard escalate <id> --note "what you tried and how it failed"\` hands it one tier up.7. Your lane is done when its items are verified, not when they are submitted. After your last submit, keep running \`pullboard next --wait 9\`: a rejected item comes back to your lane.+**Read the source map.** \`pullboard map\` shows committed \`main\`; use \`pullboard map <module or function>\` for a card or \`pullboard map --for <item>\` for its one-hop source and test slice. Item slices default to 4k tokens and cap at 8k with \`--budget\`. The map is static: \`not detected\` means the scan could not see an effect or edge, so treat it as unknown.+- The coordinator merges verified items into the main line; builders never merge. When a release ships, the coordinator runs \`pullboard milestone ship <name>\`: it records main's commit and moves the items that have not landed into the next milestone. \`pullboard health\` lists every stuck item: a lapsed claim, a review nobody took, accepted work that never landed, an old hold, an unanswered decision. Each line says why, since when, the next step and who takes it; run it at the start of a session and take the steps that name you.+ The coordinator merges verified items into the main line; builders never merge. When a release ships, the coordinator runs \`pullboard milestone ship <name>\`: it records main's commit and moves the items that have not landed into the next milestone. The queue orders itself by what each item unblocks and what it costs; the coordinator holds an item above that order with \`pullboard milestone pin <name> <ids> --reason "<why>"\`, below it with \`pullboard milestone sink <name> <ids> --reason "<why>"\`, and returns it with \`pullboard milestone lift <name> <ids>\`. \`pullboard health\` lists every stuck item: a lapsed claim, a review nobody took, accepted work that never landed, an old hold, an unanswered decision. Each line says why, since when, the next step and who takes it; run it at the start of a session and take the steps that name you.++ **Replay flow.** Run \`pullboard flow replay --json\` to reproduce recorded landing order and stage quartiles from text-free lifecycle history. To compare a hypothetical order and board line settings, run \`pullboard flow replay --history history.json --policy policy.json --json\` with the exported version-1 history and a JSON policy containing \`order\` and \`settings\`. Recorded work durations stay fixed; alternate queue times are deterministic predictions, not measured speedups.For recurring checks, \`pullboard sentinels\` lists this board's watches, their approvals and their latest results. Propose one with \`pullboard sentinel propose <name> --check "<command>" --every hourly --owner coordinator\`; a proposal does not run until the person approves its exact command, directory and schedule. Only the person runs \`pullboard sentinel approve <name>\` or \`pullboard sentinel decline <name> --reason "<why>"\` from their own terminal or Pullboard View. Agents never approve their own proposals; send the decision to the coordinator.