gsd-remix 1.0.0

package/get-shit-done/workflows/plan-review-convergence.md

@@ -0,0 +1,254 @@
+<purpose>
+Cross-AI plan convergence loop — automates the manual chain:
+gsd-plan-phase N → gsd-review N --codex → gsd-plan-phase N --reviews → gsd-review N --codex → ...
+Each step runs inside an isolated Agent that calls the corresponding Skill.
+Orchestrator only does: init, loop control, HIGH count check, stall detection, escalation.
+</purpose>
+
+<required_reading>
+Read all files referenced by the invoking prompt's execution_context before starting.
+
+@$HOME/.claude/get-shit-done/references/revision-loop.md
+@$HOME/.claude/get-shit-done/references/gates.md
+@$HOME/.claude/get-shit-done/references/agent-contracts.md
+</required_reading>
+
+<process>
+
+## 1. Parse and Normalize Arguments
+
+Extract from $ARGUMENTS: phase number, reviewer flags (`--codex`, `--gemini`, `--claude`, `--opencode`, `--all`), `--max-cycles N`, `--text`, `--ws`.
+
+```bash
+PHASE=$(echo "$ARGUMENTS" | grep -oE '[0-9]+\.?[0-9]*' | head -1)
+
+REVIEWER_FLAGS=""
+echo "$ARGUMENTS" | grep -q '\-\-codex' && REVIEWER_FLAGS="$REVIEWER_FLAGS --codex"
+echo "$ARGUMENTS" | grep -q '\-\-gemini' && REVIEWER_FLAGS="$REVIEWER_FLAGS --gemini"
+echo "$ARGUMENTS" | grep -q '\-\-claude' && REVIEWER_FLAGS="$REVIEWER_FLAGS --claude"
+echo "$ARGUMENTS" | grep -q '\-\-opencode' && REVIEWER_FLAGS="$REVIEWER_FLAGS --opencode"
+echo "$ARGUMENTS" | grep -q '\-\-all' && REVIEWER_FLAGS="$REVIEWER_FLAGS --all"
+if [ -z "$REVIEWER_FLAGS" ]; then REVIEWER_FLAGS="--codex"; fi
+
+MAX_CYCLES=$(echo "$ARGUMENTS" | grep -oE '\-\-max-cycles\s+[0-9]+' | awk '{print $2}')
+if [ -z "$MAX_CYCLES" ]; then MAX_CYCLES=3; fi
+
+GSD_WS=""
+echo "$ARGUMENTS" | grep -qE '\-\-ws\s+\S+' && GSD_WS=$(echo "$ARGUMENTS" | grep -oE '\-\-ws\s+\S+')
+```
+
+## 2. Initialize
+
+```bash
+INIT=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" init plan-phase "$PHASE")
+if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
+```
+
+Parse JSON for: `phase_dir`, `phase_number`, `padded_phase`, `phase_name`, `has_plans`, `plan_count`, `commit_docs`, `text_mode`, `response_language`.
+
+**If `response_language` is set:** All user-facing output should be in `{response_language}`.
+
+Set `TEXT_MODE=true` if `--text` is present in $ARGUMENTS OR `text_mode` from init JSON is `true`. When `TEXT_MODE` is active, replace every `AskUserQuestion` call with a plain-text numbered list and ask the user to type their choice number.
+
+## 3. Validate Phase + Pre-flight Gate
+
+```bash
+PHASE_INFO=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" roadmap get-phase "${PHASE}")
+```
+
+**If `found` is false:** Error with available phases. Exit.
+
+Display startup banner:
+
+```text
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► PLAN CONVERGENCE — Phase {phase_number}
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+ Reviewers: {REVIEWER_FLAGS}
+ Max cycles: {MAX_CYCLES}
+```
+
+## 4. Initial Planning (if no plans exist)
+
+**If `has_plans` is true:** Skip to step 5. Display: `Plans found: {plan_count} PLAN.md files — skipping initial planning.`
+
+**If `has_plans` is false:**
+
+Display: `◆ No plans found — spawning initial planning agent...`
+
+```text
+Agent(
+  description="Initial planning Phase {PHASE}",
+  prompt="Run /gsd-plan-phase for Phase {PHASE}.
+
+Execute: Skill(skill='gsd-plan-phase', args='{PHASE} {GSD_WS}')
+
+Complete the full planning workflow. Do NOT return until planning is complete and PLAN.md files are committed.",
+  mode="auto"
+)
+```
+
+After agent returns, verify plans were created:
+```bash
+PLAN_COUNT=$(ls ${phase_dir}/${padded_phase}-*-PLAN.md 2>/dev/null | wc -l)
+```
+
+If PLAN_COUNT == 0: Error — initial planning failed. Exit.
+
+Display: `Initial planning complete: ${PLAN_COUNT} PLAN.md files created.`
+
+## 5. Convergence Loop
+
+Initialize loop variables:
+
+```text
+cycle = 0
+prev_high_count = Infinity
+```
+
+### 5a. Review (Spawn Agent)
+
+Increment `cycle`.
+
+Display: `◆ Cycle {cycle}/{MAX_CYCLES} — spawning review agent...`
+
+```text
+Agent(
+  description="Cross-AI review Phase {PHASE} cycle {cycle}",
+  prompt="Run /gsd-review for Phase {PHASE}.
+
+Execute: Skill(skill='gsd-review', args='--phase {PHASE} {REVIEWER_FLAGS} {GSD_WS}')
+
+Complete the full review workflow. Do NOT return until REVIEWS.md is committed.",
+  mode="auto"
+)
+```
+
+After agent returns, verify REVIEWS.md exists:
+```bash
+REVIEWS_FILE=$(ls ${phase_dir}/${padded_phase}-REVIEWS.md 2>/dev/null)
+```
+
+If REVIEWS_FILE is empty: Error — review agent did not produce REVIEWS.md. Exit.
+
+### 5b. Check for HIGH Concerns
+
+```bash
+HIGH_COUNT=$(grep -c '\*\*HIGH' "${REVIEWS_FILE}" 2>/dev/null || true)
+HIGH_COUNT=${HIGH_COUNT:-0}
+HIGH_LINES=$(grep -B0 -A1 '\*\*HIGH' "${REVIEWS_FILE}" 2>/dev/null)
+```
+
+**If HIGH_COUNT == 0 (converged):**
+
+```bash
+node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" state planned-phase --phase "${PHASE}" --name "${phase_name}" --plans "${PLAN_COUNT}"
+```
+
+Display:
+```text
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► CONVERGENCE COMPLETE ✓
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+ Phase {phase_number} converged in {cycle} cycle(s).
+ No HIGH concerns remaining.
+
+ REVIEWS.md: {REVIEWS_FILE}
+ Next: /gsd-execute-phase {PHASE}
+```
+
+Exit — convergence achieved.
+
+**If HIGH_COUNT > 0:** Continue to 5c.
+
+### 5c. Stall Detection + Escalation Check
+
+Display: `◆ Cycle {cycle}/{MAX_CYCLES} — {HIGH_COUNT} HIGH concerns found`
+
+**Stall detection:** If `HIGH_COUNT >= prev_high_count`:
+```text
+⚠ Convergence stalled — HIGH concern count not decreasing
+  ({HIGH_COUNT} HIGH concerns, previous cycle had {prev_high_count})
+```
+
+**Max cycles check:** If `cycle >= MAX_CYCLES`:
+
+If `TEXT_MODE` is true, present as plain-text numbered list:
+```text
+Plan convergence did not complete after {MAX_CYCLES} cycles.
+{HIGH_COUNT} HIGH concerns remain:
+
+{HIGH_LINES}
+
+How would you like to proceed?
+
+1. Proceed anyway — Accept plans with remaining HIGH concerns and move to execution
+2. Manual review — Stop here, review REVIEWS.md and address concerns manually
+
+Enter number:
+```
+
+Otherwise use AskUserQuestion:
+```js
+AskUserQuestion([
+  {
+    question: "Plan convergence did not complete after {MAX_CYCLES} cycles. {HIGH_COUNT} HIGH concerns remain:\n\n{HIGH_LINES}\n\nHow would you like to proceed?",
+    header: "Convergence",
+    multiSelect: false,
+    options: [
+      { label: "Proceed anyway", description: "Accept plans with remaining HIGH concerns and move to execution" },
+      { label: "Manual review", description: "Stop here — review REVIEWS.md and address concerns manually" }
+    ]
+  }
+])
+```
+
+If "Proceed anyway": Display final status and exit.
+If "Manual review":
+```text
+Review the concerns in: {REVIEWS_FILE}
+
+To replan manually:  /gsd-plan-phase {PHASE} --reviews
+To restart loop:     /gsd-plan-review-convergence {PHASE} {REVIEWER_FLAGS}
+```
+Exit workflow.
+
+### 5d. Replan (Spawn Agent)
+
+**If under max cycles:**
+
+Update `prev_high_count = HIGH_COUNT`.
+
+Display: `◆ Spawning replan agent with review feedback...`
+
+```text
+Agent(
+  description="Replan Phase {PHASE} with review feedback cycle {cycle}",
+  prompt="Run /gsd-plan-phase with --reviews for Phase {PHASE}.
+
+Execute: Skill(skill='gsd-plan-phase', args='{PHASE} --reviews --skip-research {GSD_WS}')
+
+This will replan incorporating cross-AI review feedback from REVIEWS.md.
+Do NOT return until replanning is complete and updated PLAN.md files are committed.
+
+IMPORTANT: When gsd-plan-phase outputs '## PLANNING COMPLETE', that means replanning is done. Return at that point.",
+  mode="auto"
+)
+```
+
+After agent returns → go back to **step 5a** (review again).
+
+</process>
+
+<success_criteria>
+- [ ] Initial planning via Agent → Skill("gsd-plan-phase") if no plans exist
+- [ ] Review via Agent → Skill("gsd-review") — isolated, not inline
+- [ ] Replan via Agent → Skill("gsd-plan-phase --reviews") — isolated, not inline
+- [ ] Orchestrator only does: init, loop control, grep HIGHs, stall detection, escalation
+- [ ] Each Agent fully completes its Skill before returning
+- [ ] Loop exits on: no HIGH concerns (converged) OR max cycles (escalation)
+- [ ] Stall detection reported when HIGH count not decreasing
+- [ ] STATE.md updated on convergence completion
+</success_criteria>

package/get-shit-done/workflows/plant-seed.md

@@ -0,0 +1,172 @@
+<purpose>
+Capture a forward-looking idea as a structured seed file with trigger conditions.
+Seeds auto-surface during /gsd-new-milestone when trigger conditions match the
+new milestone's scope.
+
+Seeds beat deferred items because they:
+- Preserve WHY the idea matters (not just WHAT)
+- Define WHEN to surface (trigger conditions, not manual scanning)
+- Track breadcrumbs (code references, related decisions)
+- Auto-present at the right time via new-milestone scan
+</purpose>
+
+<process>
+
+<step name="parse_idea">
+Parse `$ARGUMENTS` for the idea summary.
+
+If empty, ask:
+```
+What's the idea? (one sentence)
+```
+
+Store as `$IDEA`.
+</step>
+
+<step name="create_seed_dir">
+```bash
+mkdir -p .planning/seeds
+```
+</step>
+
+<step name="gather_context">
+Ask focused questions to build a complete seed:
+
+
+**Text mode (`workflow.text_mode: true` in config or `--text` flag):** Set `TEXT_MODE=true` if `--text` is present in `$ARGUMENTS` OR `text_mode` from init JSON is `true`. When TEXT_MODE is active, replace every `AskUserQuestion` call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where `AskUserQuestion` is not available.
+
+```
+AskUserQuestion(
+  header: "Trigger",
+  question: "When should this idea surface? (e.g., 'when we add user accounts', 'next major version', 'when performance becomes a priority')",
+  options: []  // freeform
+)
+```
+
+Store as `$TRIGGER`.
+
+```
+AskUserQuestion(
+  header: "Why",
+  question: "Why does this matter? What problem does it solve or what opportunity does it create?",
+  options: []
+)
+```
+
+Store as `$WHY`.
+
+```
+AskUserQuestion(
+  header: "Scope",
+  question: "How big is this? (rough estimate)",
+  options: [
+    { label: "Small", description: "A few hours — could be a quick task" },
+    { label: "Medium", description: "A phase or two — needs planning" },
+    { label: "Large", description: "A full milestone — significant effort" }
+  ]
+)
+```
+
+Store as `$SCOPE`.
+</step>
+
+<step name="collect_breadcrumbs">
+Search the codebase for relevant references:
+
+```bash
+# Find files related to the idea keywords
+grep -rl "$KEYWORD" --include="*.ts" --include="*.js" --include="*.md" . 2>/dev/null | head -10
+```
+
+Also check:
+- Current STATE.md for related decisions
+- ROADMAP.md for related phases
+- todos/ for related captured ideas
+
+Store relevant file paths as `$BREADCRUMBS`.
+</step>
+
+<step name="generate_seed_id">
+```bash
+# Find next seed number
+EXISTING=$( (ls .planning/seeds/SEED-*.md 2>/dev/null || true) | wc -l )
+NEXT=$((EXISTING + 1))
+PADDED=$(printf "%03d" $NEXT)
+```
+
+Generate slug from idea summary.
+</step>
+
+<step name="write_seed">
+Write `.planning/seeds/SEED-{PADDED}-{slug}.md`:
+
+```markdown
+---
+id: SEED-{PADDED}
+status: dormant
+planted: {ISO date}
+planted_during: {current milestone/phase from STATE.md}
+trigger_when: {$TRIGGER}
+scope: {$SCOPE}
+---
+
+# SEED-{PADDED}: {$IDEA}
+
+## Why This Matters
+
+{$WHY}
+
+## When to Surface
+
+**Trigger:** {$TRIGGER}
+
+This seed should be presented during `/gsd-new-milestone` when the milestone
+scope matches any of these conditions:
+- {trigger condition 1}
+- {trigger condition 2}
+
+## Scope Estimate
+
+**{$SCOPE}** — {elaboration based on scope choice}
+
+## Breadcrumbs
+
+Related code and decisions found in the current codebase:
+
+{list of $BREADCRUMBS with file paths}
+
+## Notes
+
+{any additional context from the current session}
+```
+</step>
+
+<step name="commit_seed">
+```bash
+gsd-remix-sdk query commit "docs: plant seed — {$IDEA}" .planning/seeds/SEED-{PADDED}-{slug}.md
+```
+</step>
+
+<step name="confirm">
+```
+✅ Seed planted: SEED-{PADDED}
+
+"{$IDEA}"
+Trigger: {$TRIGGER}
+Scope: {$SCOPE}
+File: .planning/seeds/SEED-{PADDED}-{slug}.md
+
+This seed will surface automatically when you run /gsd-new-milestone
+and the milestone scope matches the trigger condition.
+```
+</step>
+
+</process>
+
+<success_criteria>
+- [ ] Seed file created in .planning/seeds/
+- [ ] Frontmatter includes status, trigger, scope
+- [ ] Breadcrumbs collected from codebase
+- [ ] Committed to git
+- [ ] User shown confirmation with trigger info
+</success_criteria>

package/get-shit-done/workflows/pr-branch.md

@@ -0,0 +1,157 @@
+<purpose>
+Create a clean branch for pull requests by filtering out transient .planning/ commits.
+The PR branch contains only code changes and structural planning state — reviewers
+don't see GSD transient artifacts (PLAN.md, SUMMARY.md, CONTEXT.md, RESEARCH.md, etc.)
+but milestone archives, STATE.md, ROADMAP.md, and PROJECT.md changes are preserved.
+
+Uses git cherry-pick with path filtering to rebuild a clean history.
+</purpose>
+
+<process>
+
+<step name="detect_state">
+Parse `$ARGUMENTS` for target branch (default: `main`).
+
+```bash
+CURRENT_BRANCH=$(git branch --show-current)
+TARGET=${1:-main}
+```
+
+Check preconditions:
+- Must be on a feature branch (not main/master)
+- Must have commits ahead of target
+
+```bash
+AHEAD=$(git rev-list --count "$TARGET".."$CURRENT_BRANCH" 2>/dev/null)
+if [ "$AHEAD" = "0" ]; then
+  echo "No commits ahead of $TARGET — nothing to filter."
+  exit 0
+fi
+```
+
+Display:
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► PR BRANCH
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Branch: {CURRENT_BRANCH}
+Target: {TARGET}
+Commits: {AHEAD} ahead
+```
+</step>
+
+<step name="analyze_commits">
+Classify commits:
+
+```bash
+# Get all commits ahead of target
+git log --oneline "$TARGET".."$CURRENT_BRANCH" --no-merges
+```
+
+**Structural planning files** — always preserved (repository planning state):
+- `.planning/STATE.md`
+- `.planning/ROADMAP.md`
+- `.planning/MILESTONES.md`
+- `.planning/PROJECT.md`
+- `.planning/REQUIREMENTS.md`
+- `.planning/milestones/**`
+
+**Transient planning files** — excluded from PR branch (reviewer noise):
+- `.planning/phases/**` (PLAN.md, SUMMARY.md, CONTEXT.md, RESEARCH.md, etc.)
+- `.planning/quick/**`
+- `.planning/research/**`
+- `.planning/threads/**`
+- `.planning/todos/**`
+- `.planning/debug/**`
+- `.planning/seeds/**`
+- `.planning/codebase/**`
+- `.planning/ui-reviews/**`
+
+For each commit, check what it touches:
+
+```bash
+# For each commit hash
+FILES=$(git diff-tree --no-commit-id --name-only -r $HASH)
+NON_PLANNING=$(echo "$FILES" | grep -v "^\.planning/" | wc -l)
+STRUCTURAL=$(echo "$FILES" | grep -E "^\.planning/(STATE|ROADMAP|MILESTONES|PROJECT|REQUIREMENTS)\.md|^\.planning/milestones/" | wc -l)
+TRANSIENT_ONLY=$(echo "$FILES" | grep "^\.planning/" | grep -vE "^\.planning/(STATE|ROADMAP|MILESTONES|PROJECT|REQUIREMENTS)\.md|^\.planning/milestones/" | wc -l)
+```
+
+Classify:
+- **Code commits**: Touch at least one non-.planning/ file → INCLUDE
+- **Structural planning commits**: Touch only structural .planning/ files (STATE.md, ROADMAP.md, MILESTONES.md, PROJECT.md, REQUIREMENTS.md, milestones/**) → INCLUDE
+- **Transient planning commits**: Touch only transient .planning/ files (phases/, quick/, research/, etc.) → EXCLUDE
+- **Mixed commits**: Touch code + any planning files → INCLUDE (transient planning changes come along; acceptable in mixed context)
+
+Display analysis:
+```
+Commits to include: {N} (code changes + structural planning)
+Commits to exclude: {N} (transient planning-only)
+Mixed commits: {N} (code + planning — included)
+Structural planning commits: {N} (STATE/ROADMAP/milestone updates — included)
+```
+</step>
+
+<step name="create_pr_branch">
+```bash
+PR_BRANCH="${CURRENT_BRANCH}-pr"
+
+# Create PR branch from target
+git checkout -b "$PR_BRANCH" "$TARGET"
+```
+
+Cherry-pick code commits and structural planning commits (in order):
+
+```bash
+for HASH in $CODE_AND_STRUCTURAL_COMMITS; do
+  git cherry-pick "$HASH" --no-commit
+  # Remove only transient .planning/ subdirectories that came along in mixed commits.
+  # DO NOT remove structural files (STATE.md, ROADMAP.md, MILESTONES.md, PROJECT.md,
+  # REQUIREMENTS.md, milestones/) — these must survive into the PR branch.
+  for dir in phases quick research threads todos debug seeds codebase ui-reviews; do
+    git rm -r --cached ".planning/$dir/" 2>/dev/null || true
+  done
+  git commit -C "$HASH"
+done
+```
+
+Return to original branch:
+```bash
+git checkout "$CURRENT_BRANCH"
+```
+</step>
+
+<step name="verify">
+```bash
+# Verify no .planning/ files in PR branch
+PLANNING_FILES=$(git diff --name-only "$TARGET".."$PR_BRANCH" | grep "^\.planning/" | wc -l)
+TOTAL_FILES=$(git diff --name-only "$TARGET".."$PR_BRANCH" | wc -l)
+PR_COMMITS=$(git rev-list --count "$TARGET".."$PR_BRANCH")
+```
+
+Display results:
+```
+✅ PR branch created: {PR_BRANCH}
+
+Original: {AHEAD} commits, {ORIGINAL_FILES} files
+PR branch: {PR_COMMITS} commits, {TOTAL_FILES} files
+Planning files: {PLANNING_FILES} (should be 0)
+
+Next steps:
+  git push origin {PR_BRANCH}
+  gh pr create --base {TARGET} --head {PR_BRANCH}
+
+Or use /gsd-ship to create the PR automatically.
+```
+</step>
+
+</process>
+
+<success_criteria>
+- [ ] PR branch created from target
+- [ ] Planning-only commits excluded
+- [ ] No .planning/ files in PR branch diff
+- [ ] Commit messages preserved from original
+- [ ] User shown next steps
+</success_criteria>