msd-core/get-shit-done/workflows/ship.md

Create a pull request from completed phase/milestone work, generate a rich PR body from planning artifacts, optionally run code review, and prepare for merge. Closes the plan → execute → verify → ship loop.

<required_reading> Read all files referenced by the invoking prompt's execution_context before starting. </required_reading>

Parse arguments and load project state:

_GSD_SHIM_NAME="gsd-tools.cjs"; _GSD_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"; GSD_TOOLS="${_GSD_RUNTIME_ROOT}/get-shit-done/bin/${_GSD_SHIM_NAME}"; if [ -f "$GSD_TOOLS" ]; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.claude/get-shit-done/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.claude/get-shit-done/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif command -v gsd-tools >/dev/null 2>&1; then GSD_TOOLS="$(command -v gsd-tools)"; gsd_run() { "$GSD_TOOLS" "$@"; }; elif [ -f "$HOME/.claude/get-shit-done/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="$HOME/.claude/get-shit-done/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd-tools is not on PATH. Run: npx -y @opengsd/gsd-core@latest --claude --local" >&2; exit 1; fi
INIT=$(gsd_run query init.phase-op "${PHASE_ARG}")
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi

Parse from init JSON: phase_found, phase_dir, phase_number, phase_name, padded_phase, commit_docs.

Also load config for branching strategy:

CONFIG=$(gsd_run query state.load)

Extract: branching_strategy, branch_name.

Detect base branch for PRs and merges:

BASE_BRANCH=$(gsd_run query config-get git.base_branch 2>/dev/null || echo "")
if [ -z "$BASE_BRANCH" ] || [ "$BASE_BRANCH" = "null" ]; then
  BASE_BRANCH=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|^refs/remotes/origin/||')
  BASE_BRANCH="${BASE_BRANCH:-main}"
fi

Verify the work is ready to ship:

1. Verification passed?

   VERIFICATION=$(cat ${PHASE_DIR}/*-VERIFICATION.md 2>/dev/null)
   

   Check for status: pass or status: passed. If no VERIFICATION.md or status is anything other than pass / passed (including human_needed / gaps_found): block with PHASE_VERIFICATION_INCOMPLETE; complete or formally re-run verification before shipping.

2. Clean working tree?

   git status --short
   

   If uncommitted changes exist: ask user to commit or stash first.

3. On correct branch?

   CURRENT_BRANCH=$(git branch --show-current)
   

   If on ${BASE_BRANCH}: warn — should be on a feature branch. If branching_strategy is none: offer to create a branch now.

4. Remote configured?

   git remote -v | head -2
   

   Detect origin remote. If no remote: error — can't create PR.

5. gh CLI available?

   which gh && gh auth status 2>&1
   

   If gh not found or not authenticated: provide setup instructions and exit.

Push the current branch to remote:

git push origin ${CURRENT_BRANCH} 2>&1

If push fails (e.g., no upstream): set upstream:

git push --set-upstream origin ${CURRENT_BRANCH} 2>&1

Report: "Pushed {branch} to origin ({commit_count} commits ahead of ${BASE_BRANCH})"

Auto-generate a rich PR body from planning artifacts:

1. Title:

Phase {phase_number}: {phase_name}

Or for milestone: Milestone {version}: {name}

2. Summary section: Read ROADMAP.md for phase goal. Read VERIFICATION.md for verification status.

## Summary

**Phase {N}: {Name}**
**Goal:** {goal from ROADMAP.md}
**Status:** Verified ✓

{One paragraph synthesized from SUMMARY.md files — what was built}

3. Changes section: For each SUMMARY.md in the phase directory:

## Changes

### Plan {plan_id}: {plan_name}
{one_liner from SUMMARY.md frontmatter}

**Key files:**
{key-files.created and key-files.modified from SUMMARY.md frontmatter}

4. Requirements section:

## Requirements Addressed

{REQ-IDs from plan frontmatter, linked to REQUIREMENTS.md descriptions}

5. Testing section:

## Verification

- [x] Automated verification: {pass/fail from VERIFICATION.md}
- {human verification items from VERIFICATION.md, if any}

6. Decisions section:

## Key Decisions

{Decisions from STATE.md accumulated context relevant to this phase}

7. Configured project sections: Read append-only project-specific PRD/PR body sections from config:

CUSTOM_PR_SECTIONS=$(gsd_run query config-get ship.pr_body_sections --default '[]' 2>/dev/null || echo '[]')

ship.pr_body_sections is an onboarding-time extension point for teams that need extra PRD-style sections such as User Stories & Acceptance Criteria, Risks & Dependencies, Success Metrics, Release Criteria, or Stakeholder Review & Approval.

Use these sections for lean/agile PRD material that should travel with the PR without making the core /gsd:ship body configurable:

• User stories and acceptance criteria that explain the functional increment from the user's point of view.
• Definition of Done or release criteria that make the completion standard explicit.
• Risks, dependencies, stakeholder review, and traceability notes needed by regulated or approval-heavy projects.

Rules:

• Treat configured sections as append-only. They are rendered after Key Decisions and cannot replace, remove, or reorder the required core sections: Summary, Changes, Requirements Addressed, Verification, and Key Decisions.
• Each entry must have heading plus at least one of source, template, or fallback.
• enabled defaults to true; when enabled is false, skip the section without warning. This lets onboarding seed optional sections that a project can enable later.
• source is a fallback chain of planning artifact headings: PLAN.md ## Risks || VERIFICATION.md ## Manual Checks. Allowed artifacts are ROADMAP.md, PLAN.md, SUMMARY.md, VERIFICATION.md, STATE.md, REQUIREMENTS.md, and CONTEXT.md.
• template is literal Markdown with a closed token namespace only: {phase_number}, {phase_name}, {phase_dir}, {base_branch}, {padded_phase}.
• fallback is literal Markdown used when source finds no content and no template is present.
• Omit sections whose final rendered body is empty after trimming.

Example configured sections:

[
  {
    "heading": "User Stories & Acceptance Criteria",
    "enabled": true,
    "source": "REQUIREMENTS.md ## User Stories || REQUIREMENTS.md ## Acceptance Criteria",
    "fallback": "- Acceptance criteria are covered by the linked requirements and verification evidence."
  },
  {
    "heading": "Risks & Dependencies",
    "enabled": true,
    "source": "PLAN.md ## Risks || PLAN.md ## Dependencies",
    "fallback": "- No known high-risk rollout dependencies."
  },
  {
    "heading": "Stakeholder Review & Approval",
    "enabled": false,
    "template": "- Product owner approval pending for {phase_name}."
  }
]

Create the PR using the generated body. Write the body to a temp file first so large generated PRD sections do not hit shell argument limits:

PR_BODY_FILE=$(mktemp "${TMPDIR:-/tmp}/gsd-pr-body.XXXXXX.md")
trap 'rm -f "${PR_BODY_FILE:-}"' EXIT
printf '%s\n' "${PR_BODY}" > "${PR_BODY_FILE}"

gh pr create \
  --title "Phase ${PHASE_NUMBER}: ${PHASE_NAME}" \
  --body-file "${PR_BODY_FILE}" \
  --base "${BASE_BRANCH}"

If --draft flag was passed: add --draft.

Report: "PR #{number} created: {url}"

External code review command (automated sub-step):

Before prompting the user, check if an external review command is configured:

REVIEW_CMD=$(gsd_run query config-get workflow.code_review_command 2>/dev/null | jq -r '.' 2>/dev/null || echo "")

If REVIEW_CMD is non-empty and not "null", run the external review:

1. Generate diff and stats:

   DIFF=$(git diff ${BASE_BRANCH}...HEAD)
   DIFF_STATS=$(git diff --stat ${BASE_BRANCH}...HEAD)
   

2. Load phase context from STATE.md:

   STATE_STATUS=$(gsd_run query state.load 2>/dev/null | head -20)
   

3. Build review prompt and pipe to command via stdin: Construct a review prompt containing the diff, diff stats, and phase context, then pipe it to the configured command:

   REVIEW_PROMPT="You are reviewing a pull request.\n\nDiff stats:\n${DIFF_STATS}\n\nPhase context:\n${STATE_STATUS}\n\nFull diff:\n${DIFF}\n\nRespond with JSON: { \"verdict\": \"APPROVED\" or \"REVISE\", \"confidence\": 0-100, \"summary\": \"...\", \"issues\": [{\"severity\": \"...\", \"file\": \"...\", \"line_range\": \"...\", \"description\": \"...\", \"suggestion\": \"...\"}] }"
   REVIEW_OUTPUT=$(echo "${REVIEW_PROMPT}" | timeout 120 ${REVIEW_CMD} 2>/tmp/gsd-review-stderr.log)
   REVIEW_EXIT=$?
   

4. Handle timeout (120s) and failure: If REVIEW_EXIT is non-zero or the command times out:

   if [ $REVIEW_EXIT -ne 0 ]; then
     REVIEW_STDERR=$(cat /tmp/gsd-review-stderr.log 2>/dev/null)
     echo "WARNING: External review command failed (exit ${REVIEW_EXIT}). stderr: ${REVIEW_STDERR}"
     echo "Continuing with manual review flow..."
   fi
   

   On failure, warn with stderr output and fall through to the manual review flow below.

5. Parse JSON result: If the command succeeded, parse the JSON output and report the verdict:

   # Parse verdict and summary from REVIEW_OUTPUT JSON
   VERDICT=$(echo "${REVIEW_OUTPUT}" | node -e "
     let d=''; process.stdin.on('data',c=>d+=c); process.stdin.on('end',()=>{
       try { const r=JSON.parse(d); console.log(r.verdict); }
       catch(e) { console.log('INVALID_JSON'); }
     });
   ")
   

   • If verdict is "APPROVED": report approval with confidence and summary.
   • If verdict is "REVISE": report issues found, list each issue with severity, file, line_range, description, and suggestion.
   • If JSON is invalid (INVALID_JSON): warn "External review returned invalid JSON" with stderr and continue.

   Regardless of the external review result, fall through to the manual review options below.

---

Manual review options:

Ask if user wants to trigger a code review:

Text mode (workflow.text_mode: true in config or --text flag): Set TEXT_MODE=true if --text is present in $ARGUMENTS OR text_mode from init JSON is true. When TEXT_MODE is active, replace every AskUserQuestion call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where AskUserQuestion is not available.

AskUserQuestion:
  question: "PR created. Run a code review before merge?"
  options:
    - label: "Skip review"
      description: "PR is ready — merge when CI passes"
    - label: "Self-review"
      description: "I'll review the diff in the PR myself"
    - label: "Request review"
      description: "Request review from a teammate"

If "Request review":

gh pr edit ${PR_NUMBER} --add-reviewer "${REVIEWER}"

If "Self-review": Report the PR URL and suggest: "Review the diff at {url}/files"

Update STATE.md to reflect the shipping action:

gsd_run query state.update "Last Activity" "$(date +%Y-%m-%d)"
gsd_run query state.update "Status" "Phase ${PHASE_NUMBER} shipped — PR #${PR_NUMBER}"

If commit_docs is true:

gsd_run query commit "docs(${padded_phase}): ship phase ${PHASE_NUMBER} — PR #${PR_NUMBER}" --files .planning/STATE.md

``` ───────────────────────────────────────────────────────────────

✓ Phase {X}: {Name} — Shipped

PR: #{number} ({url}) Branch: {branch} → ${BASE_BRANCH} Commits: {count} Verification: ✓ Passed Requirements: {N} REQ-IDs addressed

Next steps:

• Review/approve PR
• Merge when CI passes
• /gsd:complete-milestone (if last phase in milestone)
• /gsd:progress (to see what's next)

───────────────────────────────────────────────────────────────

</step>

</process>

<offer_next>
After shipping:

- /gsd:complete-milestone — if all phases in milestone are done
- /gsd:progress — see overall project state
- /gsd:execute-phase {next} — continue to next phase
</offer_next>

<success_criteria>
- [ ] Preflight checks passed (verification, clean tree, branch, remote, gh)
- [ ] Branch pushed to remote
- [ ] PR created with rich auto-generated body
- [ ] STATE.md updated with shipping status
- [ ] User knows PR number and next steps
</success_criteria>