Update to Hamster

{
  "description": "Ship a Hamster brief. Merge the base branch, implement in parallel waves, test, review, and create bisectable commits. Ask before opening a PR. Use when the user wants to execute or ship an existing brief.",
  "included_files": [
    {
      "relative_path": "references/agents/task-executor.md",
      "size_in_bytes": 10975
    },
    {
      "relative_path": "references/agents/wave-reviewer.md",
      "size_in_bytes": 6123
    },
    {
      "relative_path": "references/brief-selection.md",
      "size_in_bytes": 8970
    },
    {
      "relative_path": "references/execution-loop.md",
      "size_in_bytes": 10477
    },
    {
      "relative_path": "scripts/ensure-ready.ps1",
      "size_in_bytes": 929
    },
    {
      "relative_path": "scripts/ensure-ready.sh",
      "size_in_bytes": 666
    }
  ],
  "name": "ship",
  "skill_md_contents": "---\nname: ship\ndescription: Ship a Hamster brief. Merge the base branch, implement in parallel waves, test, review, and create bisectable commits. Ask before opening a PR. Use when the user wants to execute or ship an existing brief.\n---\n\n# Ship Brief\n\nExecutes a Hamster Studio brief. **Execution-only**: the plan — parent tasks, subtasks, context — was generated upstream in Hamster Studio and synced into `.hamster/`. This skill schedules those existing tasks into parallel waves and executes them. It never generates, splits, or replans tasks on its own initiative — but it doesn't execute blindly either. Executors adapt to mechanical drift (documented as deviations) and escalate genuine plan defects as **PLAN_ISSUE** instead of implementing something known to be wrong; the orchestrator (and for scope changes, the user) decides how to proceed.\n\nProject skills ARE loaded during execution: task-executors read `.claude/skills/hamster-project-context/SKILL.md` when it exists (generated by `hamster sync`; clients that discover `.claude/skills/` expose it as the `hamster-project-context` skill), relevant project skills, and `.hamster/` blueprints/methods. Execution-only restricts *planning*, not *context*.\n\n**Argument**: \"$ARGUMENTS\"\n\n---\n\n## Readiness\n\nBefore assuming a Hamster CLI, run this skill's bundled gate. Set `SKILL_DIR` to the absolute path of the directory holding the SKILL.md you just read — the shell's working directory is the user's project, not this skill — and keep the whole command on one line with its statements `;`-separated, because some clients flatten a fenced block before running it. The `else` branch is the same gate inline, for clients that expose no readable path to the installed package.\n\nUnix:\n\n```bash\nSKILL_DIR=\"<absolute path of the directory containing this SKILL.md>\"; if [ -f \"$SKILL_DIR/scripts/ensure-ready.sh\" ]; then bash \"$SKILL_DIR/scripts/ensure-ready.sh\"; else export PATH=\"$HOME/.hamster/bin:$PATH\"; if command -v hamster >/dev/null 2>&1 && { status_err=\"$(hamster --no-tui status 2>&1)\"; printf '%s' \"$status_err\" | grep -q \"Logged in\" || { printf '%s\\n' \"$status_err\" >&2; false; }; } && sync_err=\"$(hamster sync 2>&1)\"; then echo READY; else [ -n \"${sync_err:-}\" ] && printf '%s\\n' \"$sync_err\" >&2; echo SETUP_NEEDED; exit 1; fi; fi\n```\n\nWindows:\n\n```powershell\n$SkillDir = \"<absolute path of the directory containing this SKILL.md>\"; if (Test-Path \"$SkillDir\\scripts\\ensure-ready.ps1\") { pwsh \"$SkillDir\\scripts\\ensure-ready.ps1\" } else { $env:PATH = \"$env:USERPROFILE\\.hamster\\bin;\" + $env:PATH; if (Get-Command hamster -ErrorAction SilentlyContinue) { $status = & hamster --no-tui status 2>&1 | Out-String; if ($LASTEXITCODE -eq 0 -and $status -cmatch \"Logged in\") { $syncOut = & hamster sync 2>&1; if ($LASTEXITCODE -eq 0) { \"READY\" } else { [Console]::Error.WriteLine(($syncOut | Out-String).TrimEnd()); \"SETUP_NEEDED\"; exit 1 } } else { [Console]::Error.WriteLine($status.TrimEnd()); \"SETUP_NEEDED\"; exit 1 } } else { \"SETUP_NEEDED\"; exit 1 } }\n```\n\nIf it prints `SETUP_NEEDED` in Codex on macOS and `hamster` is already on `PATH`, re-run only this readiness command with elevated permission. The default workspace sandbox cannot read Keychain credentials, and an extra directory grant does not change that. If the elevated check prints `READY`, continue. Only if it still prints `SETUP_NEEDED`, run this plugin's `setup` skill, then re-run the check. Do not continue until it prints `READY`.\n\n## Setup\n\nRead [brief-selection](references/brief-selection.md) and run **Account Resolution** first. On `ACCOUNT_UNRESOLVED`, follow its team-selection/re-sync guidance and stop. Then run prerequisites and live sync in ONE bash call, assigning `account` to the resolved filesystem slug (shell-quoted), not `HAMSTER_ACCOUNT_ID`:\n\n```bash\nexport PATH=\"$HOME/.hamster/bin:$PATH\"\nerrors=\"\"\ncommand -v hamster >/dev/null 2>&1 || errors=\"${errors}hamster CLI not found. Run this plugin's setup skill.\\n\"\n[ -d \".hamster\" ] || errors=\"${errors}.hamster/ directory not found. Run 'hamster sync' first.\\n\"\ncommand -v gh >/dev/null 2>&1 || errors=\"${errors}gh CLI not found. Install from https://cli.github.com\\n\"\ndirty=$(git status --porcelain 2>/dev/null | head -5)\n[ -n \"$dirty\" ] && errors=\"${errors}Uncommitted changes:\\n${dirty}\\n\"\nif [ -n \"$errors\" ]; then printf \"PREREQ_FAIL:\\n$errors\"; exit 1; fi\naccount=\"<resolved filesystem account slug>\"\nrepo=$(git rev-parse --show-toplevel 2>/dev/null)\nwatch=\"\"\nfor pid in $(pgrep -f \"hamster sync .*--watch\" 2>/dev/null); do\n  cwd=$(lsof -a -d cwd -p \"$pid\" -Fn 2>/dev/null | sed -n 's/^n//p' | head -1)\n  [ -z \"$cwd\" ] && cwd=$(readlink \"/proc/$pid/cwd\" 2>/dev/null)\n  [ \"$cwd\" = \"$repo\" ] && { watch=\"existing\"; break; }\n  [ -z \"$cwd\" ] && watch=\"unknown\"\ndone\nif [ -n \"$watch\" ]; then echo \"PREREQ_OK account=${account} sync_pid=${watch}\"\nelse hamster sync --watch > /dev/null 2>&1 & echo \"PREREQ_OK account=${account} sync_pid=$!\"; fi\n```\n\n- `PREREQ_FAIL` → show errors and stop (for uncommitted changes only: ask whether to proceed or stash)\n- `sync_pid=existing` → a watcher whose working directory is this repo is already running (an interrupted session, or the user's own). Reuse it; do NOT kill it at completion\n- `sync_pid=unknown` → a watcher exists but its working directory could not be read, so it may belong to another repo. Advisory only: reuse it rather than starting a second one, and never kill it\n- Numeric `sync_pid` → remember the literal number. Each Bash call is a fresh shell, so `$sync_pid` does not survive to later calls — at Completion, substitute it literally (e.g. `kill 12345`)\n\n---\n\n## Brief Selection and Scheduling\n\nFollow **Brief Selection** and **Scheduling** in [brief-selection](references/brief-selection.md): argument parsing, the brief picker, the inline frontmatter parse, and wave grouping, ending with the single execute/modify/cancel confirmation.\n\n---\n\n## Branch + Merge Base\n\nOne call:\n\n```bash\nlowest_id=$(ls \"$tasks_dir\"/*.md 2>/dev/null | xargs -n1 basename | grep -oE '^[a-z][a-z0-9]*-[0-9]+' | sort -t- -k2,2n | head -1)\nbranch=\"feature/${lowest_id}-${slug}\"\ngit checkout -b \"$branch\"\ndefault_branch=$(gh repo view --json defaultBranchRef -q .defaultBranchRef.name 2>/dev/null || echo \"main\")\ngit fetch origin \"$default_branch\" && git merge \"origin/$default_branch\" --no-edit\necho \"branch=$branch base=$default_branch\"\n```\n\nMerge conflict → **STOP**, report conflicts, do NOT auto-resolve.\n\n---\n\n## Execution and Completion\n\nRead [execution-loop](references/execution-loop.md) and follow it for every wave: parallel execution, the validate/test gate, wave review, bisectable per-parent commits, and the progress report — then its Completion section for the watcher shutdown, final validation, optional PR, and brief status update.\n\n---\n\n## Error Recovery\n\n| Error | Recovery |\n|-------|----------|\n| Prereq failure | Stop with instructions (uncommitted changes: ask stash/proceed) |\n| Account unresolved | Stop; follow Account Resolution's team-selection/re-sync guidance |\n| Brief not found | Show partial matches, ask user |\n| Auth expired | `hamster auth login`; continue without status updates if it fails |\n| Merge conflict (base or between executors) | Stop, report, never auto-resolve |\n| Test gate fails | Stop, report, ask fix or skip |\n| NEEDS_FIXES after 2 rounds | Report to user, ask skip or manual fix |\n| Worker fails | Report, ask retry or skip |\n| Executor returns PLAN_ISSUE | Verify: resolved authority-correct work → review; unresolved local fix → corrected re-launch; scope beyond authority or unresolved decision → ask user |\n| Task already done | Skip it |\n\n## Notes\n\n- One commit set per parent (subtasks are never committed individually)\n- Interrupted? `/hamster:resume-hamster` reconstructs state from git + task statuses\n- Single PR per brief by default; >15 tasks → ask about splitting\n"
}