@hanzlaa/rcode 3.3.0 → 3.3.1

package/rihal/workflows/show.md

@@ -5,7 +5,7 @@ Print a specific SPRINT.md file or all plans in a phase, with execution status f
 ## Step 0: Usage Check
 
 Verify argument was provided:
-- If empty: `Usage: /rihal:show <phase-id|plan-id> (e.g., /rihal:show 01 or /rihal:show 01-01)`
+- If empty: `Usage: /rihal-show <phase-id|plan-id> (e.g., /rihal-show 01 or /rihal-show 01-01)`
 - Proceed to Step 1
 
 ## Step 1: Resolve ID
@@ -21,7 +21,7 @@ Expected output:
 }
 ```
 
-If `type === "unknown"`: Return error `ID not found: $ARGUMENTS. Try /rihal:show 01 for phase, 01-01 for specific plan.`
+If `type === "unknown"`: Return error `ID not found: $ARGUMENTS. Try /rihal-show 01 for phase, 01-01 for specific plan.`
 
 ## Step 2: Phase or Plan?
 

package/rihal/workflows/sprint-planning.md

@@ -1,4 +1,4 @@
-# Workflow: rihal:sprint-planning
+# Workflow: rihal-sprint-planning
 
 <purpose>
 Plan the next sprint. Authoritative implementation lives in the
@@ -50,7 +50,7 @@ Open with banner:
 ```
 TaskCreate: "Load phase scope + velocity", "Capacity gate (halt for numbers)", "Curate stories with user", "Register sprint + stories in state", "Write SPRINT.md", "Sync state", "Start sprint".
 Closure: `RIHAL ► SPRINT {NN.S} READY ✓ ({N} stories, {M} points)`
-Next Up: `/rihal:execute .planning/phases/{phase}/SPRINT.md`
+Next Up: `/rihal-execute .planning/phases/{phase}/SPRINT.md`
 </output_format>
 
 <process>
@@ -59,14 +59,14 @@ Next Up: `/rihal:execute .planning/phases/{phase}/SPRINT.md`
 If `$ARGUMENTS` contains `--help` or `-h`:
 
 ```
-/rihal:sprint-planning [--phase <NN>] [--velocity <points>] [--goal "Sprint goal"]
+/rihal-sprint-planning [--phase <NN>] [--velocity <points>] [--goal "Sprint goal"]
 ```
 
 **Examples:**
 ```
-/rihal:sprint-planning
-/rihal:sprint-planning --phase 01 --goal "Auth system MVP"
-/rihal:sprint-planning --velocity 13
+/rihal-sprint-planning
+/rihal-sprint-planning --phase 01 --goal "Auth system MVP"
+/rihal-sprint-planning --velocity 13
 ```
 
 STOP — do not proceed.
@@ -85,7 +85,7 @@ Extract:
 
 If no phases in state:
 ```
-No phases found. Run /rihal:new-project first to create a roadmap.
+No phases found. Run /rihal-new-project first to create a roadmap.
 ```
 Exit.
 
@@ -166,8 +166,8 @@ Stories: {count} ({total_points} points)
 Capacity: {velocity_target} points ({buffer}% buffer)
 
 Next:
-  /rihal:execute .planning/phases/{phase}/SPRINT.md   ← execute the sprint
-  /rihal:sprint-status                                ← check progress anytime
+  /rihal-execute .planning/phases/{phase}/SPRINT.md   ← execute the sprint
+  /rihal-sprint-status                                ← check progress anytime
 ```
 
 ## Output Format
@@ -179,7 +179,7 @@ Next:
 ## Examples
 
 ### Happy Path
-**Input:** `/rihal:sprint-planning --phase 01 --goal "Auth MVP"`
+**Input:** `/rihal-sprint-planning --phase 01 --goal "Auth MVP"`
 **Expected:** Load phase scope, estimate stories, present table, confirm, create SPRINT.md + register in state, start sprint.
 
 ### Edge Case: Over capacity
@@ -188,10 +188,10 @@ Next:
 
 ### Edge Case: No scope
 **Input:** Phase has no SCOPE.md or requirements
-**Expected:** "No scope found for this phase. Run /rihal:new-project or write a SCOPE.md first."
+**Expected:** "No scope found for this phase. Run /rihal-new-project or write a SCOPE.md first."
 
 ### Negative Test
-**Input:** `/rihal:sprint-planning` with no phases in state
-**Expected:** Graceful exit suggesting /rihal:new-project.
+**Input:** `/rihal-sprint-planning` with no phases in state
+**Expected:** Graceful exit suggesting /rihal-new-project.
 
 </process>

package/rihal/workflows/sprint-status.md

@@ -1,4 +1,4 @@
-# Workflow: rihal:sprint-status
+# Workflow: rihal-sprint-status
 
 <purpose>
 Display current sprint progress: stories by status, points done vs remaining, velocity comparison, and burndown. Quick situational awareness without starting execution.
@@ -27,13 +27,13 @@ End with Next Up routing based on sprint state.
 If `$ARGUMENTS` contains `--help` or `-h`:
 
 ```
-/rihal:sprint-status [--sprint <NN.S>]
+/rihal-sprint-status [--sprint <NN.S>]
 ```
 
 **Examples:**
 ```
-/rihal:sprint-status              # current sprint
-/rihal:sprint-status --sprint 01.2
+/rihal-sprint-status              # current sprint
+/rihal-sprint-status --sprint 01.2
 ```
 
 STOP — do not proceed.
@@ -48,7 +48,7 @@ STORIES=$(node .rihal/bin/rihal-tools.cjs state story list)
 
 If no current sprint:
 ```
-No active sprint. Run /rihal:sprint-planning to create one.
+No active sprint. Run /rihal-sprint-planning to create one.
 ```
 Exit.
 
@@ -96,8 +96,8 @@ REVIEW
 
 Based on data, suggest next action:
 
-- **All stories done:** "Sprint ready to close. Run `/rihal:sprint-planning` for next sprint."
-- **In progress stories exist:** "Continue executing. Run `/rihal:execute` to pick up next story."
+- **All stories done:** "Sprint ready to close. Run `/rihal-sprint-planning` for next sprint."
+- **In progress stories exist:** "Continue executing. Run `/rihal-execute` to pick up next story."
 - **Over capacity (committed > velocity avg):** "Over-committed by {N} points. Consider deferring lowest-priority story."
 - **No stories moved today:** "No progress since last check. Blockers?"
 
@@ -110,15 +110,15 @@ Based on data, suggest next action:
 ## Examples
 
 ### Happy Path
-**Input:** `/rihal:sprint-status`
+**Input:** `/rihal-sprint-status`
 **Expected:** Board showing 3 done / 1 in_progress / 2 todo, 8/13 points, velocity trend stable.
 
 ### Edge Case: No sprint
-**Input:** `/rihal:sprint-status` (no active sprint)
+**Input:** `/rihal-sprint-status` (no active sprint)
 **Expected:** "No active sprint" + suggestion to run sprint-planning.
 
 ### Negative Test
-**Input:** `/rihal:sprint-status --sprint 99.9`
+**Input:** `/rihal-sprint-status --sprint 99.9`
 **Expected:** "Sprint 99.9 not found."
 
 </process>

package/rihal/workflows/stats.md

@@ -1,4 +1,4 @@
-# Workflow: rihal:stats
+# Workflow: rihal-stats
 
 <purpose>
 Read .rihal/state.json and display project statistics: phases, plans, council sessions, decisions, blockers, timeline, and git stats.
@@ -10,13 +10,13 @@ Read .rihal/state.json and display project statistics: phases, plans, council se
 If `$ARGUMENTS` is empty or contains only `--help` or `-h`:
 
 ```
-/rihal:stats <argument-here>
+/rihal-stats <argument-here>
 ```
 
 **Examples:**
 ```
-/rihal:stats example 1
-/rihal:stats example 2
+/rihal-stats example 1
+/rihal-stats example 2
 ```
 
 STOP — do not proceed.
@@ -32,7 +32,7 @@ cat .rihal/state.json 2>/dev/null || echo '{}'
 Parse as JSON. If parse fails or file doesn't exist, print:
 ```
 ℹ️ No rihal state found in this project yet.
-Run /rihal:help to get started.
+Run /rihal-help to get started.
 ```
 Exit.
 
@@ -82,7 +82,7 @@ If `.git/` does not exist, set `rihal_commits` = 0 and omit recent_commits from
 Print a human-readable stats block:
 
 ```
-📊 rihal:stats — Project Timeline
+📊 rihal-stats — Project Timeline
 
 Project: $PROJECT_NAME
 Created: $TIMELINE_START

package/rihal/workflows/status.md

@@ -1,9 +1,9 @@
-# Workflow: rihal:status
+# Workflow: rihal-status
 
 <purpose>
 Render a human-readable project status dashboard. All data comes from a single `rihal-tools progress init` call — this workflow does NOT parse ROADMAP.md, walk SUMMARY.md files, or grep state.json itself. Rendering only. See `rihal-tools.cjs` `cmdProgress` for the source-of-truth logic (issue #159 M2.5).
 
-**SSOT:** `.rihal/state.json`. `/rihal:status` and `/rihal:progress` both call the same CLI so they cannot disagree. If the CLI reports a drift insight, surface it — do not silently compensate.
+**SSOT:** `.rihal/state.json`. `/rihal-status` and `/rihal-progress` both call the same CLI so they cannot disagree. If the CLI reports a drift insight, surface it — do not silently compensate.
 </purpose>
 
 <required_reading>
@@ -21,7 +21,7 @@ VERBOSE=$(node .rihal/bin/rihal-tools.cjs config-get output.verbose 2>/dev/null
 
 Parse as JSON. If `SNAPSHOT.ok` is not true, print a one-line error and stop.
 
-**Slim mode** (default when `VERBOSE != "true"`): Output Steps 2–3 only (banner + phases list). Skip decisions, blockers detail, and route menu — just print the top route as a single "Next: `/rihal:X`" line. Append `(run /rihal:status --verbose for full detail)`.
+**Slim mode** (default when `VERBOSE != "true"`): Output Steps 2–3 only (banner + phases list). Skip decisions, blockers detail, and route menu — just print the top route as a single "Next: `/rihal-X`" line. Append `(run /rihal-status --verbose for full detail)`.
 
 **Verbose mode** (`VERBOSE == "true"` or `$ARGUMENTS` contains `--verbose`): Full Steps 2–6 output.
 
@@ -44,24 +44,32 @@ Then stop.
 │ Milestone:  {SNAPSHOT.milestone or "—"}                 │
 │ Phase:      {SNAPSHOT.current_phase or "none started"}  │
 │ Progress:   {SNAPSHOT.bar}                              │
+│ Weighted:   {SNAPSHOT.weighted_bar}                     │
 │ Updated:    {relative_time(SNAPSHOT.updated)}           │
 ╰─────────────────────────────────────────────────────────╯
 ```
 
+If `SNAPSHOT.weighted_progress > 0` but `SNAPSHOT.completed_count === 0`, display
+the weighted bar as the primary progress indicator to avoid a misleading `0/N (0%)`.
+
 ## Step 3 — Phases section
 
 For each entry in `SNAPSHOT.phases[]`:
 
 - `▶` if `phase.number === SNAPSHOT.current_phase`
 - `✓` if `phase.disk.summary_count > 0` AND matches `phase.disk.plan_count` (complete)
-- `◆` if `phase.disk.plan_count > phase.disk.summary_count` (in progress)
-- `○` otherwise (planned)
+- `◆` if `phase.disk.plan_count > phase.disk.summary_count` (executing — has plans, not all summarized)
+- `◇` if `phase.disk.has_context && !phase.disk.plan_count` (discussing — CONTEXT.md exists but no plan yet)
+- `◈` if `phase.disk.has_research && !phase.disk.plan_count` (researched — RESEARCH.md but no plan)
+- `○` otherwise (planned — no artifacts on disk)
 
 ```
 Phases:
-  ▶ [04] Component compaction — in progress (1/3 plans)
+  ▶ [04] Component compaction — executing (1/3 plans)
   ✓ [03] Auth hardening — complete
-  ○ [05] Billing rewrite — planned
+  ◇ [05] Billing rewrite — discussing
+  ◈ [06] API optimization — researched
+  ○ [07] Final cleanup — planned
 ```
 
 If a phase number starts with `999.`, render with a `🅿` marker and the label `(parking lot)`.

package/rihal/workflows/ui-phase.md

@@ -1,4 +1,4 @@
-# Workflow: rihal:ui-phase
+# Workflow: rihal-ui-phase
 
 <purpose>
 Produce UI-SPEC.md with formalized design contract: color tokens, typography system, component inventory, interaction states, accessibility requirements. Detects frontend keywords (React, Next.js, Vue, Tailwind, CSS, UI) and suggests this workflow early if UI-SPEC.md is absent.
@@ -10,13 +10,13 @@ Produce UI-SPEC.md with formalized design contract: color tokens, typography sys
 If `$ARGUMENTS` is empty or contains only `--help` or `-h`:
 
 ```
-/rihal:ui-phase <argument-here>
+/rihal-ui-phase <argument-here>
 ```
 
 **Examples:**
 ```
-/rihal:ui-phase example 1
-/rihal:ui-phase example 2
+/rihal-ui-phase example 1
+/rihal-ui-phase example 2
 ```
 
 STOP — do not proceed.
@@ -114,7 +114,7 @@ If enabled, print:
 ```
 ⚠ Frontend project detected. Before planning, create a design contract:
 
-/rihal:ui-phase
+/rihal-ui-phase
 
 This ensures consistent UI patterns, accessibility, and design tokens across all components.
 ```
@@ -124,13 +124,13 @@ Offer via AskUserQuestion:
 header: "UI Safety Gate"
 question: "Should we define UI-SPEC.md before planning component development?"
 options:
-  - "Yes, run /rihal:ui-phase first"
+  - "Yes, run /rihal-ui-phase first"
   - "Skip for now, continue planning"
 ```
 
-If "Yes, run /rihal:ui-phase first":
+If "Yes, run /rihal-ui-phase first":
 ```
-Run /rihal:ui-phase, then return to /rihal:plan
+Run /rihal-ui-phase, then return to /rihal-plan
 ```
 
 ## Success Criteria

package/rihal/workflows/ui-review.md

@@ -1,4 +1,4 @@
-# Workflow: rihal:ui-review
+# Workflow: rihal-ui-review
 
 <purpose>
 Retroactively audit completed UI work against the UI-SPEC.md contract. Validates across 6 pillars: color consistency, typography compliance, component inventory coverage, accessibility requirements, responsive behavior, and design coherence. Produces audit report with pass/fail per pillar.
@@ -10,13 +10,13 @@ Retroactively audit completed UI work against the UI-SPEC.md contract. Validates
 If `$ARGUMENTS` is empty or contains only `--help` or `-h`:
 
 ```
-/rihal:ui-review <argument-here>
+/rihal-ui-review <argument-here>
 ```
 
 **Examples:**
 ```
-/rihal:ui-review example 1
-/rihal:ui-review example 2
+/rihal-ui-review example 1
+/rihal-ui-review example 2
 ```
 
 STOP — do not proceed.
@@ -45,7 +45,7 @@ test -f ".rihal/UI-SPEC.md"
 
 **If missing:**
 ```
-⚠ UI-SPEC.md not found. Run /rihal:ui-phase first to create design contract.
+⚠ UI-SPEC.md not found. Run /rihal-ui-phase first to create design contract.
 ```
 
 Exit.

package/rihal/workflows/undo.md

@@ -8,13 +8,13 @@ Safe git revert workflow. Rolls back Rihal phase or plan commits using the phase
 If `$ARGUMENTS` is empty or contains only `--help` or `-h`:
 
 ```
-/rihal:undo <argument-here>
+/rihal-undo <argument-here>
 ```
 
 **Examples:**
 ```
-/rihal:undo example 1
-/rihal:undo example 2
+/rihal-undo example 1
+/rihal-undo example 2
 ```
 
 STOP — do not proceed.
@@ -47,21 +47,21 @@ Parse $ARGUMENTS for the undo mode:
 If no valid argument is provided, display usage and exit:
 
 ```
-Usage: /rihal:undo --last N | --phase NN [--to-snapshot] | --plan NN-MM
+Usage: /rihal-undo --last N | --phase NN [--to-snapshot] | --plan NN-MM
 
 Modes:
   --last N              Show last N Rihal commits for interactive selection
   --phase NN            Revert all commits for phase NN (uses manifest, fallback to git log)
   --phase NN --to-snapshot
                         Revert every commit between rihal/snapshot/phase-NN and HEAD —
-                        exact restore to the pre-execution tag created by /rihal:execute
+                        exact restore to the pre-execution tag created by /rihal-execute
   --plan NN-MM          Revert all commits for plan NN-MM
 
 Examples:
-  /rihal:undo --last 5
-  /rihal:undo --phase 03
-  /rihal:undo --phase 03 --to-snapshot
-  /rihal:undo --plan 03-02
+  /rihal-undo --last 5
+  /rihal-undo --phase 03
+  /rihal-undo --phase 03 --to-snapshot
+  /rihal-undo --plan 03-02
 ```
 
 </step>
@@ -76,7 +76,7 @@ Before gathering any commits, display:
 
 Unsure what will be reverted? Run first:
 
-/rihal:undo --last 5
+/rihal-undo --last 5
 
 to preview the last 5 Rihal commits before choosing.
 ```
@@ -141,10 +141,10 @@ if ! git rev-parse --verify "refs/tags/${SNAPSHOT_TAG}" >/dev/null 2>&1; then
   cat <<EOF
 No snapshot tag found: ${SNAPSHOT_TAG}
 
-Snapshots are created automatically when /rihal:execute runs for a phase.
+Snapshots are created automatically when /rihal-execute runs for a phase.
 Options:
-  - Drop --to-snapshot and use manifest/git-log fallback:   /rihal:undo --phase ${TARGET_PHASE}
-  - Re-run /rihal:execute <phase> to create a snapshot for future undo
+  - Drop --to-snapshot and use manifest/git-log fallback:   /rihal-undo --phase ${TARGET_PHASE}
+  - Re-run /rihal-execute <phase> to create a snapshot for future undo
 EOF
   exit 0
 fi
@@ -294,7 +294,7 @@ Store the response as REVERT_REASON. Continue to execute_revert.
 
 Run `git status --porcelain`. If the output is non-empty, display the dirty files and abort:
 ```
-Working tree has uncommitted changes. Commit or stash them before running /rihal:undo.
+Working tree has uncommitted changes. Commit or stash them before running /rihal-undo.
 ```
 Exit immediately — do not proceed to any revert operations.
 
@@ -380,13 +380,13 @@ Show next steps:
 
 /clear then:
 
-/rihal:progress
+/rihal-progress
 
 ───────────────────────────────────────────────────────────────
 
 **Also available:**
-- `/rihal:execute ${PHASE}` — re-execute if needed
-- `/rihal:undo --last 1` — undo the revert itself if something went wrong
+- `/rihal-execute ${PHASE}` — re-execute if needed
+- `/rihal-undo --last 1` — undo the revert itself if something went wrong
 
 ───────────────────────────────────────────────────────────────
 ```

package/rihal/workflows/update.md

@@ -1,4 +1,4 @@
-# Workflow: rihal:update
+# Workflow: rihal-update
 
 <purpose>
 Pull the latest rcode from npm and install it **non-destructively** —
@@ -29,16 +29,16 @@ Per-project state is ALWAYS preserved (never touched by either mode):
 If `$ARGUMENTS` contains `--help` or `-h`:
 
 ```
-/rihal:update                       # pull latest, preserve user-modified files
-/rihal:update v2.4.0                # pin to a specific version
-/rihal:update --force-overwrite     # discard local edits, overwrite all rcode files
+/rihal-update                       # pull latest, preserve user-modified files
+/rihal-update v2.4.0                # pin to a specific version
+/rihal-update --force-overwrite     # discard local edits, overwrite all rcode files
 ```
 
 **Examples:**
 ```
-/rihal:update
-/rihal:update v2.4.0
-/rihal:update --force-overwrite
+/rihal-update
+/rihal-update v2.4.0
+/rihal-update --force-overwrite
 ```
 
 ## Step 1 — Locate installed package
@@ -154,7 +154,7 @@ when they intentionally want to discard their customizations):
 npx @hanzlaa/rcode@latest install . --force-overwrite --yes
 ```
 
-**Version pinning** — if the user passed `/rihal:update v2.4.0`, pass
+**Version pinning** — if the user passed `/rihal-update v2.4.0`, pass
 the version through:
 
 ```bash
@@ -189,8 +189,8 @@ when relevant. Capture it and re-print as a callout so users notice:
    - rihal/workflows/sprint-planning.md
    - .rihal/references/output-format.md
 
-These will not auto-update on future /rihal:update calls. To force
-their update next time, run /rihal:update --force-overwrite.
+These will not auto-update on future /rihal-update calls. To force
+their update next time, run /rihal-update --force-overwrite.
 ```
 
 ## Step 8 — Pull Rihal brain content (v2.0)
@@ -206,7 +206,7 @@ Parse the JSON output. Report counts to the user:
 - `skipped[]` — sources with `<PLACEHOLDER>` URLs (waiting on issue #162 / M5)
 - `errors[]` — sources that failed (network, auth, etc.)
 
-If the user passed a version argument (`/rihal:update v1.3.0`), pass it through to `brain pull` as `--version v1.3.0`. When supported, `brain pull` will pin each source to the commit recorded in that release's `sources.yaml`. Unknown versions: treat as latest and warn.
+If the user passed a version argument (`/rihal-update v1.3.0`), pass it through to `brain pull` as `--version v1.3.0`. When supported, `brain pull` will pin each source to the commit recorded in that release's `sources.yaml`. Unknown versions: treat as latest and warn.
 
 ## Step 9 — Success summary
 
@@ -224,7 +224,7 @@ Rihal brain: M sources pulled, K skipped (placeholder URLs)
 
 New version available at: .rihal/
 
-Run /rihal:status to verify installation.
+Run /rihal-status to verify installation.
 ```
 
 ## Success Criteria

package/rihal/workflows/validate-phase.md

@@ -28,7 +28,7 @@ AUDITOR_MODEL=$(node ".rihal/bin/rihal-tools.cjs" resolve-model rihal-nyquist-au
 NYQUIST_CFG=$(node ".rihal/bin/rihal-tools.cjs" config-get workflow.nyquist_validation --raw)
 ```
 
-If `NYQUIST_CFG` is `false`: exit with "Nyquist validation is disabled. Enable via /rihal:settings."
+If `NYQUIST_CFG` is `false`: exit with "Nyquist validation is disabled. Enable via /rihal-settings."
 
 Display banner: `Rihal > VALIDATE PHASE {N}: {name}`
 
@@ -41,7 +41,7 @@ SUMMARY_FILES=$(ls "${PHASE_DIR}"/*-SUMMARY.md 2>/dev/null)
 
 - **State A** (`VALIDATION_FILE` non-empty): Audit existing
 - **State B** (`VALIDATION_FILE` empty, `SUMMARY_FILES` non-empty): Reconstruct from artifacts
-- **State C** (`SUMMARY_FILES` empty): Exit — "Phase {N} not executed. Run /rihal:execute-phase {N} ${Rihal_WS} first."
+- **State C** (`SUMMARY_FILES` empty): Exit — "Phase {N} not executed. Run /rihal-execute-phase {N} ${Rihal_WS} first."
 
 ## 2. Discovery
 
@@ -98,7 +98,7 @@ Otherwise call AskUserQuestion with gap table and options:
 
 ```
 Task(
-  prompt="Read $HOME/.claude/agents/rihal:nyquist-auditor.md for instructions.\n\n" +
+  prompt="Read $HOME/.claude/agents/rihal-nyquist-auditor.md for instructions.\n\n" +
     "<files_to_read>{PLAN, SUMMARY, impl files, VALIDATION.md}</files_to_read>" +
     "<gaps>{gap list}</gaps>" +
     "<test_infrastructure>{framework, config, commands}</test_infrastructure>" +
@@ -150,14 +150,14 @@ node ".rihal/bin/rihal-tools.cjs" commit "docs(phase-${PHASE}): add/update valid
 ```
 Rihal > PHASE {N} IS NYQUIST-COMPLIANT
 All requirements have automated verification.
-▶ Next: /rihal:audit-milestone ${Rihal_WS}
+▶ Next: /rihal-audit-milestone ${Rihal_WS}
 ```
 
 **Partial:**
 ```
 Rihal > PHASE {N} VALIDATED (PARTIAL)
 {M} automated, {K} manual-only.
-▶ Retry: /rihal:validate-phase {N} ${Rihal_WS}
+▶ Retry: /rihal-validate-phase {N} ${Rihal_WS}
 ```
 
 Display `/clear` reminder.

package/rihal/workflows/verify-work.md

@@ -1,5 +1,5 @@
 <purpose>
-Validate built features through conversational testing with persistent state. Creates UAT.md that tracks test progress, survives /clear, and feeds gaps into /rihal:plan --gaps.
+Validate built features through conversational testing with persistent state. Creates UAT.md that tracks test progress, survives /clear, and feeds gaps into /rihal-plan --gaps.
 
 User tests, Claude records. One test at a time. Plain text responses.
 </purpose>
@@ -13,8 +13,8 @@ Open with banner:
 ```
 TaskCreate: one entry per story to verify.
 Per-story status: `✓ Story 01.1.01 — passed`, `✗ Story 01.1.02 — FAILED: {reason}`, `⚠ Story 01.1.03 — partial`.
-If any fail: route to `/rihal:plan --gaps` for remediation.
-If all pass: `RIHAL ► SPRINT {NN.S} VERIFIED ✓` + Next Up: `/rihal:next`.
+If any fail: route to `/rihal-plan --gaps` for remediation.
+If all pass: `RIHAL ► SPRINT {NN.S} VERIFIED ✓` + Next Up: `/rihal-next`.
 </output_format>
 
 <required_reading>
@@ -95,7 +95,7 @@ If no, continue to `create_uat_file`.
 ```
 No active UAT sessions.
 
-Provide a phase number to start testing (e.g., /rihal:verify-work 4)
+Provide a phase number to start testing (e.g., /rihal-verify-work 4)
 ```
 
 **If no active sessions AND $ARGUMENTS provided:**
@@ -436,31 +436,31 @@ SECURITY_FILE=$(ls "${PHASE_DIR}"/*-SECURITY.md 2>/dev/null | head -1)
 
 If `SECURITY_CFG` is `true` AND `SECURITY_FILE` is empty:
 ```
-⚠ Security enforcement enabled — /rihal:secure-phase {phase} has not run.
+⚠ Security enforcement enabled — /rihal-secure-phase {phase} has not run.
 Run before advancing to the next phase.
 
 All tests passed. Ready to continue.
 
-- `/rihal:secure-phase {phase}` — security review (required before advancing)
-- `/rihal:plan {next}` — Plan next phase
-- `/rihal:execute-phase {next}` — Execute next phase
-- `/rihal:ui-review {phase}` — visual quality audit (if frontend files were modified)
+- `/rihal-secure-phase {phase}` — security review (required before advancing)
+- `/rihal-plan {next}` — Plan next phase
+- `/rihal-execute-phase {next}` — Execute next phase
+- `/rihal-ui-review {phase}` — visual quality audit (if frontend files were modified)
 ```
 
 If `SECURITY_CFG` is `true` AND `SECURITY_FILE` exists: check frontmatter `threats_open`. If > 0:
 ```
 ⚠ Security gate: {threats_open} threats open
-  /rihal:secure-phase {phase} — resolve before advancing
+  /rihal-secure-phase {phase} — resolve before advancing
 ```
 
 If `SECURITY_CFG` is `false` OR (`SECURITY_FILE` exists AND `threats_open` is `0`):
 ```
 All tests passed. Ready to continue.
 
-- `/rihal:plan {next}` — Plan next phase
-- `/rihal:execute-phase {next}` — Execute next phase
-- `/rihal:secure-phase {phase}` — security review
-- `/rihal:ui-review {phase}` — visual quality audit (if frontend files were modified)
+- `/rihal-plan {next}` — Plan next phase
+- `/rihal-execute-phase {next}` — Execute next phase
+- `/rihal-secure-phase {phase}` — security review
+- `/rihal-ui-review {phase}` — visual quality audit (if frontend files were modified)
 ```
 </step>
 
@@ -518,7 +518,7 @@ ${AGENT_SKILLS_PLANNER}
 </planning_context>
 
 <downstream_consumer>
-Output consumed by /rihal:execute-phase
+Output consumed by /rihal-execute-phase
 Plans must be executable prompts.
 </downstream_consumer>
 """,
@@ -631,7 +631,7 @@ Display: `Max iterations reached. {N} issues remain.`
 Offer options:
 1. Force proceed (execute despite issues)
 2. Provide guidance (user gives direction, retry)
-3. Abandon (exit, user runs /rihal:plan manually)
+3. Abandon (exit, user runs /rihal-plan manually)
 
 Wait for user response.
 </step>
@@ -659,7 +659,7 @@ Plans verified and ready for execution.
 
 **Execute fixes** — run fix plans
 
-`/clear` then `/rihal:execute-phase {phase} --gaps-only`
+`/clear` then `/rihal-execute-phase {phase} --gaps-only`
 
 ───────────────────────────────────────────────────────────────
 ```
@@ -713,5 +713,5 @@ Default to **major** if unclear. User can correct if needed.
 - [ ] If issues: rihal-planner creates fix plans (gap_closure mode)
 - [ ] If issues: rihal-plan-checker verifies fix plans
 - [ ] If issues: revision loop until plans pass (max 3 iterations)
-- [ ] Ready for `/rihal:execute-phase --gaps-only` when complete
+- [ ] Ready for `/rihal-execute-phase --gaps-only` when complete
 </success_criteria>