@hanzlaa/rcode 3.6.16 → 4.0.0

package/rcode/workflows/plant-seed.md

@@ -0,0 +1,180 @@
+<purpose>
+Capture a forward-looking idea as a structured seed file with trigger conditions.
+Seeds auto-surface during /rcode-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:
+
+```
+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 `/rcode-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 $BREADCRUMBS with file paths}
+
+## Notes
+
+{any additional context from the current session}
+```
+</step>
+
+<step name="commit_seed">
+```bash
+node ".rcode/bin/rcode-tools.cjs" commit "docs: plant seed — {$IDEA}" --files .planning/seeds/SEED-{PADDED}-{slug}.md
+```
+</step>
+
+<step name="confirm">
+```
+✓ Seed planted: SEED-{PADDED}
+
+"{$IDEA}"
+Trigger: {$TRIGGER}
+Scope: {$SCOPE}
+File: .planning/seeds/SEED-{PADDED}-{slug}.md
+
+This seed will surface automatically when you run /rcode-new-milestone
+and the milestone scope matches the trigger condition.
+
+▶ Next Up
+  /rcode-status                 — review current focus before context-switching
+  /rcode-note "{$IDEA}"         — capture related thoughts while fresh
+  /rcode-new-milestone           — start the milestone that will consume this seed
+  /rcode-do                      — return to the dispatcher
+```
+</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>
+
+## Next Up
+
+- `/rcode-do` — continue with current work
+- `/rcode-new-milestone` — use seeds when trigger conditions match the new milestone scope

package/rcode/workflows/pr-branch.md

@@ -0,0 +1,134 @@
+<purpose>
+Create a clean branch for pull requests by filtering out .planning/ commits.
+The PR branch contains only code changes — reviewers don't see rcode artifacts
+(SPRINT.md, SUMMARY.md, STATE.md, CONTEXT.md, etc.).
+
+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 $TARGET — nothing to filter."
+  exit 0
+fi
+```
+
+Display:
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ rcode ► PR BRANCH
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Branch: {CURRENT_BRANCH}
+Target: {TARGET}
+Commits: {AHEAD} ahead
+```
+</step>
+
+<step name="analyze_commits">
+Classify commits:
+
+```bash
+# Get all commits ahead of target
+git log --oneline "$TARGET".."$CURRENT_BRANCH" --no-merges
+```
+
+For each commit, check if it ONLY touches .planning/ files:
+
+```bash
+# For each commit hash
+FILES=$(git diff-tree --no-commit-id --name-only -r $HASH)
+ALL_PLANNING=$(echo "$FILES" | grep -v "^\.planning/" | wc -l)
+```
+
+Classify:
+- **Code commits**: Touch at least one non-.planning/ file → INCLUDE
+- **Planning-only commits**: Touch only .planning/ files → EXCLUDE
+- **Mixed commits**: Touch both → INCLUDE (planning changes come along)
+
+Display analysis:
+```
+Commits to include: {N} (code changes)
+Commits to exclude: {N} (planning-only)
+Mixed commits: {N} (code + planning — included)
+```
+</step>
+
+<step name="create_pr_branch">
+```bash
+PR_BRANCH="${CURRENT_BRANCH}-pr"
+
+# Create PR branch from target
+git checkout -b "$PR_BRANCH" "$TARGET"
+```
+
+Cherry-pick only code commits (in order):
+
+```bash
+for HASH in $CODE_COMMITS; do
+  git cherry-pick "$HASH" --no-commit
+  # Remove any .planning/ files that came along in mixed commits
+  git rm -r --cached .planning/ 2>/dev/null || true
+  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 /rcode-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>
+
+## Next Up
+
+- `/rcode-ship` — push the PR branch and open the pull request
+- `/rcode-code-review` — review the PR branch before shipping

package/rcode/workflows/prfaq.md

@@ -0,0 +1,12 @@
+# Workflow: rcode-prfaq
+
+<purpose>
+Working Backwards PRFAQ challenge. Stress-test a product concept by writing the press release before building it. Produces a battle-hardened PRFAQ document + PRD distillate. Delegates to the rcode-prfaq skill for the full interview and generation protocol.
+</purpose>
+
+@rcode/skills/actions/1-analysis/rcode-prfaq/SKILL.md
+
+## Next Up
+
+- `/rcode-create-prd` — convert the battle-hardened PRFAQ into a full PRD
+- `/rcode-brainstorm` — continue ideation if the PRFAQ revealed new directions

package/rcode/workflows/profile-user.md

@@ -0,0 +1,173 @@
+# Workflow: rcode-profile-user
+
+<purpose>
+Classify developer on 4 dimensions: communication style, autonomy preference, domain depth, and iteration speed. Spawn a profiler subagent to ask questions and produce a USER-PROFILE.md artifact with YAML frontmatter + structured classification.
+</purpose>
+
+
+## Step 0 — Usage check
+
+If `$ARGUMENTS` is empty or contains only `--help` or `-h`:
+
+```
+/rcode-profile-user <argument-here>
+```
+
+**Examples:**
+```
+/rcode-profile-user
+/rcode-profile-user --json '{"communication":"Direct & dense","autonomy":"Autonomous","domain_depth":"Advanced","iteration_speed":"Fast"}'
+```
+
+STOP — do not proceed.
+
+<available_agent_types>
+- `rcode-profiler` — user classification agent (spawned once per session)
+</available_agent_types>
+
+## Step 0 — Initialize
+
+```bash
+INIT=$(node .rcode/bin/rcode-tools.cjs init profile-user "$ARGUMENTS" 2>/dev/null)
+if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
+```
+
+If `INIT` is empty or `INIT.ok` is false, print error and exit:
+```
+Error: rcode-tools init failed. Verify .rcode/ is installed and state.json is valid.
+```
+
+Parse:
+- `flags.json` — if set, parse as pre-filled profile JSON (skip questions)
+- `profile_path` — `.rcode/USER-PROFILE.md` (output location)
+
+**If no arguments and `--json` not provided:** Use AskUserQuestion to collect 4 profile dimensions interactively.
+
+## Step 1 — Collect Profile Data (if not `--json`)
+
+Use AskUserQuestion with 4 separate calls (one per dimension):
+
+**Q1: Communication Style**
+```
+header: "Communication"
+question: "How do you prefer to receive technical guidance?"
+multiSelect: false
+options:
+  - "Direct & dense (structured data, minimal prose)"
+  - "Balanced (explanation + examples)"
+  - "Narrative & conversational"
+  - "Persona-driven (character voice OK)"
+```
+
+**Q2: Autonomy Preference**
+```
+header: "Autonomy"
+question: "How should the agent handle decisions?"
+multiSelect: false
+options:
+  - "Autonomous (just do it, report after)"
+  - "Checkpoint-based (ask before each decision)"
+  - "Guided (suggestions + approval loops)"
+  - "Hands-off (full human control)"
+```
+
+**Q3: Domain Depth**
+```
+header: "Domain Depth"
+question: "How deep should technical explanations go?"
+multiSelect: false
+options:
+  - "Beginner (conceptual, no jargon)"
+  - "Intermediate (standard patterns, some internals)"
+  - "Advanced (architectural depth, trade-offs)"
+  - "Expert (research papers, edge cases)"
+```
+
+**Q4: Iteration Speed**
+```
+header: "Speed"
+question: "Preferred pace for feedback loops?"
+multiSelect: false
+options:
+  - "Fast (minimal detail, quick feedback)"
+  - "Balanced (normal pace)"
+  - "Thorough (deep analysis, slower)"
+  - "Adaptive (match the moment)"
+```
+
+Collect answers into `profile` object:
+```json
+{
+  "communication": "Direct & dense",
+  "autonomy": "Checkpoint-based",
+  "domain_depth": "Intermediate",
+  "iteration_speed": "Balanced"
+}
+```
+
+## Step 2 — Generate Profile
+
+**If `--json` provided:** Parse `flags.json` into `profile` object (skip questions).
+
+**Otherwise:** Use answers from Step 1.
+
+Spawn `rcode-profiler` subagent:
+
+```
+Task tool call:
+  subagent_type: "rcode-profiler"
+  description: "Generate user profile classification"
+  prompt: |
+    Generate a USER-PROFILE.md with the following profile data:
+    
+    Communication: {profile.communication}
+    Autonomy: {profile.autonomy}
+    Domain Depth: {profile.domain_depth}
+    Iteration Speed: {profile.iteration_speed}
+    
+    Output format:
+    1. YAML frontmatter with all 4 dimensions + metadata
+    2. One paragraph per dimension explaining implications
+    3. Recommended settings (e.g., verbosity, checkpoint frequency)
+    
+    Write to: {profile_path}
+```
+
+## Step 3 — Persist Profile
+
+Store `profile` object in state:
+
+```bash
+node .rcode/bin/rcode-tools.cjs state set-user-profile --json '{json-string}'
+```
+
+Print:
+```
+✓ Profile saved: {profile_path}
+
+Dimensions:
+  • Communication: {communication}
+  • Autonomy: {autonomy}
+  • Domain Depth: {domain_depth}
+  • Iteration Speed: {iteration_speed}
+
+This profile will personalize future /rcode-council and /rcode-execute responses.
+```
+
+## Success Criteria
+
+- USER-PROFILE.md created with YAML frontmatter
+- All 4 dimensions documented
+- Profile persisted to state.json
+- Message confirms location and dimensions
+
+## On Error
+
+- If AskUserQuestion fails: retry or skip to default profile
+- If subagent fails: manually create USER-PROFILE.md with frontmatter
+- If state write fails: print warning but continue (profile still written to disk)
+
+## Next Up
+
+- `/rcode-settings` — update project config to match the user profile
+- `/rcode-do` — continue with the profile now informing Claude's behaviour

package/rcode/workflows/progress.md

@@ -0,0 +1,51 @@
+# Workflow: rcode-progress
+
+<purpose>
+**`/rcode-progress` is an alias of `/rcode-status --verbose`.**
+
+Historically this was a separate workflow with overlapping data and a heavier render. They both read the same source of truth (`rcode-tools progress init`), so we collapsed them: `/rcode-status` is the canonical renderer with built-in slim/verbose modes, and `/rcode-progress` is a thin alias that always runs in verbose mode.
+
+Use whichever name you prefer — they produce the same output.
+</purpose>
+
+<required_reading>
+@.rcode/workflows/status.md
+</required_reading>
+
+<process>
+
+## Step 1 — Delegate to /rcode-status in verbose mode
+
+Execute the workflow defined in `.rcode/workflows/status.md` end-to-end, with one override:
+
+- Always render in **verbose mode** (full Steps 2–6 output: banner + phases + insights + decisions + blockers + Next Up route tree).
+- Treat `$ARGUMENTS` exactly as `/rcode-status --verbose $ARGUMENTS` would.
+
+Do not parse ROADMAP.md, walk SUMMARY.md files, or grep state.json directly. If the underlying CLI reports a drift insight, surface it — do not silently compensate.
+
+## Step 2 — Footer note (one-time alias hint)
+
+After the verbose status output, append a single grey line:
+
+```
+(/rcode-progress is an alias of /rcode-status --verbose — same data, same source.)
+```
+
+Skip this footer if `$ARGUMENTS` already contains `--no-alias-hint`.
+
+</process>
+
+## Success Criteria
+
+- [ ] Calls the status workflow with verbose mode forced
+- [ ] No independent CLI parsing — single source of truth via `progress init`
+- [ ] Optional alias hint footer printed unless suppressed
+
+## On Error
+
+Defer to `.rcode/workflows/status.md` error handling. This workflow adds nothing on top.
+
+## Next Up
+
+- `/rcode-next` — auto-advance to the next logical step
+- `/rcode-do` — take action on what the progress view surfaced