@hanzlaa/rcode 3.2.1 → 3.3.1

package/rihal/agents/rihal-verifier.md

@@ -49,7 +49,7 @@ Before verifying, discover project context:
 10. **Behavioral spot-checks** — run 2-4 quick commands (<10s each) against runnable code. Skip if no runnable entry points.
 11. **Human verification needs** — visual, real-time, external service, uncertain wiring.
 12. **Determine status** — passed | gaps_found | human_needed. Score = verified_truths / total_truths.
-13. **Structure gap output** — YAML frontmatter for `/rihal:plan --gaps`.
+13. **Structure gap output** — YAML frontmatter for `/rihal-plan --gaps`.
 14. **Create VERIFICATION.md** — use Write tool (never heredoc). Return to orchestrator. DO NOT COMMIT.
 
 ## Final Status Tables
@@ -91,7 +91,7 @@ Read these ONLY when the current step needs them. Don't preemptively load.
 - **DO NOT trust SUMMARY claims** — verify the component actually renders messages, not a placeholder.
 - **DO NOT assume existence = implementation** — need level 2 (substantive), 3 (wired), and 4 (data flowing) for dynamic-data artifacts.
 - **DO NOT skip key link verification** — 80% of stubs hide in wiring.
-- **Structure gaps in YAML frontmatter** for `/rihal:plan --gaps`.
+- **Structure gaps in YAML frontmatter** for `/rihal-plan --gaps`.
 - **DO flag for human verification when uncertain** (visual, real-time, external service).
 - **Keep verification fast** — use grep/file checks, not running the app.
 - **DO NOT commit** — leave committing to the orchestrator.

package/rihal/agents/rihal-waleed.md

@@ -3,7 +3,7 @@ name: rihal-waleed
 description: |
   CTO and Chief Architect — for architecture decisions, stack selection,
   technical feasibility, ADR writing, scalability ceilings, security posture,
-  tech-debt prioritisation. Spawned by /rihal:council and technical dispatch.
+  tech-debt prioritisation. Spawned by /rihal-council and technical dispatch.
   Activates: "should we use X or Y", "can we scale to N", "is this feasible",
   "right architecture for", "ADR for", "talk to Waleed", "rewrite vs refactor",
   "monolith vs microservices", "which database / queue / cache".

package/rihal/agents/rihal-yousef.md

@@ -1,7 +1,7 @@
 ---
 name: rihal-yousef
 description: |
-  Senior Backend Engineer — spawned by /rihal:council, /rihal:plan, and any
+  Senior Backend Engineer — spawned by /rihal-council, /rihal-plan, and any
   backend dispatch (API design, queries, services, queues, perf, integrations).
   Activates for: API design, schema design, query optimization, p50/p95/p99
   latency, throughput tuning, BullMQ / Celery / SQS / RabbitMQ, webhooks,
@@ -113,7 +113,7 @@ Always read on activation:
 **Negative routing** — Out of scope
 > *"What's the React component for the leads table?"*
 >
-> ⚙️ **Yousef:** Frontend — Haitham's lane. Hand off via `/rihal:discuss haitham`.
+> ⚙️ **Yousef:** Frontend — Haitham's lane. Hand off via `/rihal-discuss haitham`.
 
 ## Redirects
 

package/rihal/agents/rihal-zahra.md

@@ -1,6 +1,6 @@
 ---
 name: rihal-zahra
-description: Branding & Creative Director — spawned by /rihal:council for brand identity, visual language, typography systems (Latin + Arabic), color systems, design tokens, and cross-touchpoint brand consistency. Defers to Layla on UX interaction design, Haitham on frontend implementation, Mariam on marketing copy.
+description: Branding & Creative Director — spawned by /rihal-council for brand identity, visual language, typography systems (Latin + Arabic), color systems, design tokens, and cross-touchpoint brand consistency. Defers to Layla on UX interaction design, Haitham on frontend implementation, Mariam on marketing copy.
 tools: Read, Grep, Glob, WebFetch
 color: magenta
 ---

package/rihal/agents/rihal-zayd.md

@@ -1,6 +1,6 @@
 ---
 name: rihal-zayd
-description: Senior ML Engineer — spawned by /rihal:council for machine learning, OCR, LLM integration, RAG/retrieval, vector search, reranking, embeddings, prompt engineering, and eval questions. Defers to Waleed on architecture, Yousef on integration points (queues, APIs), Fatima on eval methodology.
+description: Senior ML Engineer — spawned by /rihal-council for machine learning, OCR, LLM integration, RAG/retrieval, vector search, reranking, embeddings, prompt engineering, and eval questions. Defers to Waleed on architecture, Yousef on integration points (queues, APIs), Fatima on eval methodology.
 tools: Read, Grep, Glob, Bash, WebFetch
 color: purple
 ---

package/rihal/agents/rules/phase-researcher/detailed-guide.md

@@ -307,7 +307,7 @@ Verified patterns from official sources:
 ### Sampling Rate
 - **Per task commit:** `{quick run command}`
 - **Per wave merge:** `{full suite command}`
-- **Phase gate:** Full suite green before `/rihal:verify-work`
+- **Phase gate:** Full suite green before `/rihal-verify-work`
 
 ### Wave 0 Gaps
 - [ ] `{tests/test_file.py}` — covers REQ-{XX}

package/rihal/agents/rules/roadmapper/detailed-guide.md

@@ -522,7 +522,7 @@ After incorporating user feedback and updating files:
 
 ### Ready for Planning
 
-Next: `/rihal:plan 1`
+Next: `/rihal-plan 1`
 ```
 
 ## Roadmap Blocked

package/rihal/agents/rules/sprint-checker/dimensions.md

@@ -189,7 +189,7 @@ issue:
 
 ## Dimension 7: Context Compliance (if CONTEXT.md exists)
 
-**Question:** Do plans honor user decisions from /rihal:discuss-phase?
+**Question:** Do plans honor user decisions from /rihal-discuss-phase?
 
 **Only check if CONTEXT.md was provided in the verification context.**
 
@@ -244,7 +244,7 @@ Before running checks 8a-8d, verify VALIDATION.md exists:
 ls "${PHASE_DIR}"/*-VALIDATION.md 2>/dev/null
 ```
 
-**If missing:** **BLOCKING FAIL** — "VALIDATION.md not found for phase {N}. Re-run `/rihal:plan {N} --research` to regenerate."
+**If missing:** **BLOCKING FAIL** — "VALIDATION.md not found for phase {N}. Re-run `/rihal-plan {N} --research` to regenerate."
 Skip checks 8a-8d entirely. Report Dimension 8 as FAIL with this single issue.
 
 **If exists:** Proceed to checks 8a-8d.
@@ -406,7 +406,7 @@ issue:
   missing_symbols:
     - "imaginary_function"
   verified_ratio: 0.2
-  fix_hint: "Plan was built on hallucinated findings. Re-run /rihal:debug to verify actual code state before replanning."
+  fix_hint: "Plan was built on hallucinated findings. Re-run /rihal-debug to verify actual code state before replanning."
 ```
 
 </verification_dimensions>

package/rihal/agents/rules/sprint-checker/process.md

@@ -162,7 +162,7 @@ console.log(JSON.stringify(result, null, 2));
 
 Check result:
 - If `summary.ratio < 0.5`: **BLOCKER** — "Plan references files/symbols that don't exist. Plan was built on hallucinated findings."
-- If `summary.ratio >= 0.5 AND < 0.8`: **WARNING** — List missing files/symbols, suggest re-planning with /rihal:debug
+- If `summary.ratio >= 0.5 AND < 0.8`: **WARNING** — List missing files/symbols, suggest re-planning with /rihal-debug
 - If `summary.ratio >= 0.8`: **INFO** — Most references verified, proceed
 
 Append to verification output:
@@ -288,7 +288,7 @@ Return all issues as a structured `issues:` YAML list (see dimension examples fo
 | 01   | 3     | 5     | 1    | Valid  |
 | 02   | 2     | 4     | 2    | Valid  |
 
-Plans verified. Run `/rihal:execute {phase}` to proceed.
+Plans verified. Run `/rihal-execute {phase}` to proceed.
 ```
 
 ## ISSUES FOUND

package/rihal/agents/rules/verifier/gap-output.md

@@ -28,7 +28,7 @@
 
 ## Step 10: Structure Gap Output (If Gaps Found)
 
-Structure gaps in YAML frontmatter for `/rihal:plan --gaps`:
+Structure gaps in YAML frontmatter for `/rihal-plan --gaps`:
 
 ```yaml
 gaps:

package/rihal/agents/rules/verifier/verification-report.md

@@ -119,7 +119,7 @@ All must-haves verified. Phase goal achieved. Ready to proceed.
 1. **{Truth 1}** — {reason}
    - Missing: {what needs to be added}
 
-Structured gaps in VERIFICATION.md frontmatter for `/rihal:plan --gaps`.
+Structured gaps in VERIFICATION.md frontmatter for `/rihal-plan --gaps`.
 
 {If human_needed:}
 ### Human Verification Required

package/rihal/bin/rihal-hooks.cjs

@@ -4,7 +4,7 @@
  *
  * Subcommands:
  *   pre-edit    — verify file was Read before Edit/Write (exit 2 if not)
- *   pre-workflow — soft warning for rihal:* commands with suspicious args
+ *   pre-workflow — soft warning for rihal-* commands with suspicious args
  *   post-commit — verify commit format and no forbidden patterns
  *
  * All subcommands read stdin JSON from the hook execution context.
@@ -61,7 +61,7 @@ async function preEdit() {
 }
 
 /**
- * pre-workflow: Soft warning for rihal:* commands with suspicious args.
+ * pre-workflow: Soft warning for rihal-* commands with suspicious args.
  * Does not block (exit 0), but prints warning.
  */
 async function preWorkflow() {
@@ -70,8 +70,8 @@ async function preWorkflow() {
     const command = input.command || '';
     const args = input.args || '';
 
-    // Only check rihal:* commands
-    if (!command.startsWith('rihal:')) {
+    // Only check rihal-* commands
+    if (!command.startsWith('rihal-')) {
       process.exit(0);
     }
 
@@ -94,8 +94,8 @@ async function preWorkflow() {
       }
     }
 
-    if (hasSuspiciousPattern && (command === 'rihal:plan' || command === 'rihal:discuss')) {
-      console.warn(`⚠ "${command}" with args: "${args}". Did you mean /rihal:do or /rihal:council?`);
+    if (hasSuspiciousPattern && (command === 'rihal-plan' || command === 'rihal-discuss')) {
+      console.warn(`⚠ "${command}" with args: "${args}". Did you mean /rihal-do or /rihal-council?`);
     }
 
     process.exit(0);

package/rihal/bin/rihal-tools.cjs

@@ -505,7 +505,7 @@ function cmdClassifyQuestion(raw) {
 }
 
 /**
- * init execute — returns context blob for the /rihal:execute workflow.
+ * init execute — returns context blob for the /rihal-execute workflow.
  * Resolves plan_path (single file or phase directory), reads the plan
  * frontmatter, and returns dependency wave groupings.
  */
@@ -738,7 +738,7 @@ function cmdState(subArgs) {
   if (sub === 'read' || sub === 'get') {
     if (!fs.existsSync(statePath)) {
       // Auto-init with defaults if config.yaml exists (install happened).
-      // Removes the "run /rihal:init first" friction — any workflow can
+      // Removes the "run /rihal-init first" friction — any workflow can
       // call `state read` and get a usable state back.
       const configPath = path.join(RIHAL_DIR, 'config.yaml');
       if (fs.existsSync(configPath)) {
@@ -754,7 +754,7 @@ function cmdState(subArgs) {
       }
       return {
         ok: false,
-        error: 'No state.json yet. Run /rihal:install to set up this project, or `state init --project <name>` directly.'
+        error: 'No state.json yet. Run /rihal-install to set up this project, or `state init --project <name>` directly.'
       };
     }
     const state = readState();
@@ -2229,7 +2229,7 @@ function classifyScope(input) {
   return 'feature';
 }
 
-/** init plan — context blob for /rihal:plan workflow. */
+/** init plan — context blob for /rihal-plan workflow. */
 function cmdInitPlan(rawArgs) {
   const config = readConfig();
   const tokens = (rawArgs || '').trim().split(/\s+/).filter(Boolean);
@@ -2322,7 +2322,7 @@ function cmdInitPlan(rawArgs) {
       workflow: 'plan',
       input_type: 'executable_plan',
       resolved_path: resolvedPath,
-      suggestion: `This file is already an executable plan. Run: /rihal:execute ${path.relative(PROJECT_ROOT, resolvedPath)}`,
+      suggestion: `This file is already an executable plan. Run: /rihal-execute ${path.relative(PROJECT_ROOT, resolvedPath)}`,
       config,
       paths: { project_root: PROJECT_ROOT, rihal: RIHAL_DIR, planning_root: PLANNING_DIR, state: path.join(RIHAL_DIR, 'state.json') },
     };
@@ -2355,7 +2355,7 @@ function cmdPlanList() {
   };
 }
 
-/** init chain — context blob for /rihal:chain workflow. */
+/** init chain — context blob for /rihal-chain workflow. */
 function cmdInitChain(rawArgs) {
   const config = readConfig();
   const installedAgents = listInstalledAgents();
@@ -2427,7 +2427,7 @@ function cmdInitChain(rawArgs) {
   };
 }
 
-/** init discuss — context blob for /rihal:discuss workflow. */
+/** init discuss — context blob for /rihal-discuss workflow. */
 function cmdInitDiscuss(rawArgs) {
   const config = readConfig();
   const installedAgents = listInstalledAgents();
@@ -2460,9 +2460,9 @@ function cmdModule(subArgs) {
     // Hardcoded available modules (known at build time)
     return {
       modules: [
-        { name: 'core', description: 'Council agents, /rihal:council, /rihal:discuss, /rihal:status, /rihal:do router, /rihal:help, and state management' },
-        { name: 'execution', description: 'Plan execution — /rihal:execute, /rihal:plan, /rihal:quick, /rihal:debug, /rihal:audit-fix, /rihal:undo' },
-        { name: 'discovery', description: 'Project discovery — /rihal:new-project, /rihal:map-codebase, /rihal:scan, /rihal:explore, /rihal:code-review, /rihal:docs-update' },
+        { name: 'core', description: 'Council agents, /rihal-council, /rihal-discuss, /rihal-status, /rihal-do router, /rihal-help, and state management' },
+        { name: 'execution', description: 'Plan execution — /rihal-execute, /rihal-plan, /rihal-quick, /rihal-debug, /rihal-audit-fix, /rihal-undo' },
+        { name: 'discovery', description: 'Project discovery — /rihal-new-project, /rihal-map-codebase, /rihal-scan, /rihal-explore, /rihal-code-review, /rihal-docs-update' },
       ]
     };
   }
@@ -2609,7 +2609,7 @@ function cmdConfigSet(subArgs) {
  *   --title <t>   required headline
  *   --body <b>    optional detail text
  *   --event <e>   optional short event tag (e.g. "execute-done", "council-done")
- *   --only slack|discord|teams   restrict to one platform (for /rihal:notify-test)
+ *   --only slack|discord|teams   restrict to one platform (for /rihal-notify-test)
  *
  * Returns: { sent: [...], skipped: [...], failed: [...] }
  * Never throws on webhook failure — this runs at the tail of workflows and
@@ -3016,7 +3016,7 @@ function cmdBrain(args) {
  * cmdProgress — single pre-computed progress blob (issue #159).
  *
  * Subcommands:
- *   progress init          Full snapshot — everything /rihal:progress needs.
+ *   progress init          Full snapshot — everything /rihal-progress needs.
  *   progress bar --raw     ASCII bar only (e.g. "[████░░░░] 50%").
  *   progress insights      insights[] array (drift warnings, between-milestone detection).
  *   progress routes        intent-tree routes[] for Next Up menu.
@@ -3162,7 +3162,7 @@ function cmdProgress(args) {
         insights.push({
           kind: 'between-milestones',
           severity: 'info',
-          message: 'All registered phases complete — effectively between milestones. Consider /rihal:audit-milestone or /rihal:new-milestone.',
+          message: 'All registered phases complete — effectively between milestones. Consider /rihal-audit-milestone or /rihal-new-milestone.',
         });
       }
     }
@@ -3184,7 +3184,7 @@ function cmdProgress(args) {
       routes.push({
         letter: 'A',
         label: `Execute phase ${k} — unfinished plans`,
-        command: `/rihal:execute-phase ${k}`,
+        command: `/rihal-execute-phase ${k}`,
       });
     }
 
@@ -3196,7 +3196,7 @@ function cmdProgress(args) {
       routes.push({
         letter: 'B',
         label: `Plan phase ${num} — researched, awaiting plan`,
-        command: `/rihal:plan-phase ${num}`,
+        command: `/rihal-plan-phase ${num}`,
       });
     }
 
@@ -3213,21 +3213,21 @@ function cmdProgress(args) {
       routes.push({
         letter: 'B',
         label: `Plan phase ${k} — in progress without SPRINT.md`,
-        command: `/rihal:plan ${k}`,
+        command: `/rihal-plan ${k}`,
       });
     }
 
     // Route C — close out milestone if everything seems done
     const allDone = statePhases.length > 0 && statePhases.every(p => p.status === 'complete' || p.completed);
     if (allDone) {
-      routes.push({ letter: 'C', label: 'Audit current milestone', command: '/rihal:audit-milestone' });
-      routes.push({ letter: 'C', label: 'Complete current milestone', command: '/rihal:complete-milestone' });
+      routes.push({ letter: 'C', label: 'Audit current milestone', command: '/rihal-audit-milestone' });
+      routes.push({ letter: 'C', label: 'Complete current milestone', command: '/rihal-complete-milestone' });
     }
 
     // Fallback — nothing obvious: offer status
     if (routes.length === 0) {
-      routes.push({ letter: 'A', label: 'Check progress detail', command: '/rihal:progress' });
-      routes.push({ letter: 'B', label: 'Start a council on what to do next', command: '/rihal:council' });
+      routes.push({ letter: 'A', label: 'Check progress detail', command: '/rihal-progress' });
+      routes.push({ letter: 'B', label: 'Start a council on what to do next', command: '/rihal-council' });
     }
 
     return routes;
@@ -3242,6 +3242,40 @@ function cmdProgress(args) {
     return `[${bar}] ${completed}/${total} (${pct}%)`;
   }
 
+  /**
+   * Compute weighted progress that recognizes intermediate phase states.
+   * Weights: has_context only = 0.15, has_research = 0.25, has plan = 0.5,
+   * has verification or summary = 1.0.
+   * Returns { weighted: number (0..total), pct: number (0..100) }.
+   */
+  function computeWeightedProgress(stPhases, diskMap) {
+    if (!stPhases.length) return { weighted: 0, pct: 0 };
+    const norm = (k) => String(k ?? '').replace(/^0+(\d)/, '$1');
+    let sum = 0;
+    for (const p of stPhases) {
+      const k = norm(phaseKey(p));
+      if (p.status === 'complete' || p.completed) { sum += 1; continue; }
+      const disk = diskMap[k] || diskMap[phaseKey(p)];
+      if (!disk) continue;
+      if (disk.summary_count > 0)       { sum += 1;    continue; }
+      if (disk.has_verification)         { sum += 0.85; continue; }
+      if (disk.plan_count > 0)           { sum += 0.5;  continue; }
+      if (disk.has_research)             { sum += 0.25; continue; }
+      if (disk.has_context)              { sum += 0.15; continue; }
+    }
+    const total = Math.max(stPhases.length, 1);
+    return { weighted: Math.round(sum * 100) / 100, pct: Math.round((sum / total) * 100) };
+  }
+
+  function buildWeightedBar(stPhases, diskMap, total) {
+    const { weighted, pct } = computeWeightedProgress(stPhases, diskMap);
+    if (!total) return '[░░░░░░░░░░░░░░░░░░░░] 0/0 (0%)';
+    const width = 20;
+    const filled = Math.min(width, Math.round((weighted / total) * width));
+    const bar = '█'.repeat(filled) + '░'.repeat(width - filled);
+    return `[${bar}] ~${pct}% weighted`;
+  }
+
   // Build the core snapshot once — all subcommands derive from it.
   const state = readState();
   const roadmapPhases = parseRoadmapPhases();
@@ -3268,6 +3302,7 @@ function cmdProgress(args) {
   const currentPhase = state && state.current_phase;
   const insights = detectInsights(state, roadmapPhases, diskByNum);
   const routes = deriveRoutes(state, roadmapPhases, diskByNum);
+  const { weighted: weightedCompleted, pct: weightedPct } = computeWeightedProgress(statePhases, diskByNum);
 
   return {
     ok: true,
@@ -3276,7 +3311,9 @@ function cmdProgress(args) {
     current_phase: currentPhase,
     phase_count: phaseCount,
     completed_count: completedCount,
+    weighted_progress: weightedPct,
     bar: buildBar(completedCount, phaseCount),
+    weighted_bar: buildWeightedBar(statePhases, diskByNum, phaseCount),
     phases: (() => {
       // Prefer ROADMAP-parsed phases when available; fall back to state.phases
       // when the roadmap doesn't use a parseable format. Normalize "07" / "7" / 7.
@@ -3472,8 +3509,8 @@ function cmdGitignore(args) {
     let sliceStart = start;
     if (sliceStart > 0 && existing[sliceStart - 1] === '\n') sliceStart -= 1;
     let sliceEnd = endIdx + END.length;
-    if (existing[sliceEnd] === '\n') sliceEnd += 1;
-    return existing.slice(0, sliceStart) + newBlock + existing.slice(sliceEnd);
+    if (existing[slice_end] === '\n') slice_end += 1;
+    return existing.slice(0, sliceStart) + newBlock + existing.slice(slice_end);
   }
 
   if (!fs.existsSync(gitignorePath)) {
@@ -3688,7 +3725,7 @@ async function main() {
         console.log('  state read                                   → print full state.json');
         console.log('  state get                                    → alias for state read');
         console.log('  state init --project <name>                  → create state.json if missing');
-        console.log('  state set-phase <name>                       → set current phase, reset plan counter');
+        console.log('  state set-phase <name>                       → set current_phase, reset current_plan, append to phases[]');
         console.log('  state advance-plan                           → increment current_plan counter');
         console.log('  state record-execution --plan <p> --tasks <n> --duration <ms> --hash <h>');
         console.log('  state add-decision "<summary>"               → append to decisions[] + ~/.rihal/decisions.jsonl');

package/rihal/brain/README.md

@@ -1,6 +1,6 @@
 # rihal/brain — The Rihal Context Layer
 
-This directory is populated on install (and on every `/rihal:update`) by `rihal-tools brain pull`. Its job is simple: pull Rihal's institutional knowledge — PR/commit/issue standards, architecture decisions, internal guides — into every Rihalian's project so their AI assistant already knows how Rihal builds.
+This directory is populated on install (and on every `/rihal-update`) by `rihal-tools brain pull`. Its job is simple: pull Rihal's institutional knowledge — PR/commit/issue standards, architecture decisions, internal guides — into every Rihalian's project so their AI assistant already knows how Rihal builds.
 
 ## Structure
 
@@ -22,7 +22,7 @@ Content is pulled from three kinds of source:
 
 ## Update policy
 
-- Local edits to any file under `rihal/brain/` are **overwritten** on every `/rihal:update`. Rihal Code treats the upstream sources as the single source of truth. If the Rihal standard needs to change, the change happens upstream — then every Rihalian benefits.
+- Local edits to any file under `rihal/brain/` are **overwritten** on every `/rihal-update`. Rihal Code treats the upstream sources as the single source of truth. If the Rihal standard needs to change, the change happens upstream — then every Rihalian benefits.
 - Per-invocation: `node .rihal/bin/rihal-tools.cjs brain pull`.
 - Per project: runs automatically as part of `npx rihal-code install`.
 

package/rihal/brain/best-practices/no-autonomous-bypass.md

@@ -13,7 +13,7 @@ Phrases like *"just write it autonomously"*, *"create the full thing ready to ex
 There are exactly two ways to legitimately run a skill without halting at menus:
 
 1. **Project-wide:** `.rihal/config.yaml` → `mode: yolo`. The config loader flags `yoloMode=true` in the runtime context; step files check this flag and may auto-advance.
-2. **Per-invocation:** `/rihal:do --auto <question>` on the router. The router sets `autoMode=true` and passes it to the dispatched skill.
+2. **Per-invocation:** `/rihal-do --auto <question>` on the router. The router sets `autoMode=true` and passes it to the dispatched skill.
 
 If **neither** flag is set, halt is mandatory regardless of what the user's prompt text says.
 
@@ -34,4 +34,4 @@ That response invents a mode that does not exist and violates the halt invariant
 
 ## Correct Response
 
-> ✅ Agent: *"I hear you want the PRD written end-to-end. The halt rule applies unless you set `mode: yolo` in `.rihal/config.yaml` or re-invoke via `/rihal:do --auto`. Here is the step-01 menu — pick Continue and I will drive each step concisely."*
+> ✅ Agent: *"I hear you want the PRD written end-to-end. The halt rule applies unless you set `mode: yolo` in `.rihal/config.yaml` or re-invoke via `/rihal-do --auto`. Here is the step-01 menu — pick Continue and I will drive each step concisely."*

package/rihal/brain/best-practices/research-citation-rule.md

@@ -28,7 +28,7 @@ This pattern is forbidden. A citation block without `WebFetch` evidence is a lie
 
 ## If the User Is Running Autonomously
 
-`mode: yolo` and `/rihal:do --auto` bypass halt-at-menu, but they do **not** bypass this rule. A fully-autonomous run still has to fetch every cited URL before writing the claim.
+`mode: yolo` and `/rihal-do --auto` bypass halt-at-menu, but they do **not** bypass this rule. A fully-autonomous run still has to fetch every cited URL before writing the claim.
 
 ## Checklist Before Writing a Citation
 

package/rihal/brain/best-practices/state-sync-rule.md

@@ -1,6 +1,6 @@
 # State Sync Rule
 
-Referenced by skills that write `ROADMAP.md`, `epics.md`, or sprint artifacts. These artifacts are not authoritative on their own — downstream workflows (`/rihal:status`, `/rihal:progress`, `/rihal:execute`) read `.rihal/state.json`. If you write a planning artifact and skip state sync, the project ends up with two divergent pictures.
+Referenced by skills that write `ROADMAP.md`, `epics.md`, or sprint artifacts. These artifacts are not authoritative on their own — downstream workflows (`/rihal-status`, `/rihal-progress`, `/rihal-execute`) read `.rihal/state.json`. If you write a planning artifact and skip state sync, the project ends up with two divergent pictures.
 
 ## The Rule
 
@@ -29,15 +29,15 @@ If `rihal-tools.cjs` does not yet expose the needed subcommand, fall back to `st
 ## Verification After Sync
 
 - `node .rihal/bin/rihal-tools.cjs state read` returns a phase count that matches the phase table in `ROADMAP.md`.
-- `/rihal:status` and `/rihal:progress`, run back-to-back, agree on the current milestone name and phase count.
+- `/rihal-status` and `/rihal-progress`, run back-to-back, agree on the current milestone name and phase count.
 
 ## Why This Matters
 
 Observed failure (rihal-code, social-poster-x install, Apr 2026):
 
-- User ran `/rihal:create-epics-and-stories`.
+- User ran `/rihal-create-epics-and-stories`.
 - `ROADMAP.md` gained 10 phases; `epics.md` gained 62 stories.
 - `.rihal/state.json` remained at the initial bootstrap with 1 phase.
-- `/rihal:status` showed 1 phase; `/rihal:progress` showed 10.
+- `/rihal-status` showed 1 phase; `/rihal-progress` showed 10.
 
 That divergence is what this rule exists to prevent.

package/rihal/commands/add-phase.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:add-phase
+name: rihal-add-phase
 description: "Add a new integer phase to the end of the current milestone. Auto-calculates the next phase number, creates the phase directory, and updates ROADMAP.md. Use when scope expands mid-milestone."
 argument-hint: "<phase-name>"
 allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion

package/rihal/commands/add-tests.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:add-tests
+name: rihal-add-tests
 description: Generate unit and E2E tests for a completed phase based on its SUMMARY.md, CONTEXT.md, and implementation. Classifies ea
 argument-hint: ""
 allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, Agent

package/rihal/commands/add-todo.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:add-todo
+name: rihal-add-todo
 description: Capture an idea or task for later work
 argument-hint: "<todo-title>"
 allowed-tools: bash, read, write

package/rihal/commands/analyze-dependencies.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:analyze-dependencies
+name: rihal-analyze-dependencies
 description: Analyze phase dependencies, suggest "Depends on" entries for ROADMAP.md
 argument-hint: ""
 allowed-tools:

package/rihal/commands/audit-fix.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:audit-fix
+name: rihal-audit-fix
 description: Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit.
 argument-hint: "[--max N] [--severity high|medium|all] [--dry-run] [--source <audit>]"
 allowed-tools:

package/rihal/commands/audit-milestone.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:audit-milestone
+name: rihal-audit-milestone
 description: Cross-phase audit — verify milestone completion against original goals
 argument-hint: "[--strict] [--report]"
 allowed-tools:

package/rihal/commands/audit-uat.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:audit-uat
+name: rihal-audit-uat
 description: Cross-phase audit of all UAT and verification files. Finds every outstanding item (pending, skipped, blocked, human_need
 argument-hint: ""
 allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, Agent

package/rihal/commands/audit.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:audit
+name: rihal-audit
 description: Single audit entry point — asks what to audit (phase, milestone, UAT, code, fix, work) and dispatches to the right subroute. Honours .rihal/config.yaml mode.
 argument-hint: "[phase | milestone | uat | code | fix | work] [...subroute args]"
 allowed-tools: Read, Write, Bash, AskUserQuestion

package/rihal/commands/autonomous.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:autonomous
+name: rihal-autonomous
 description: Execute remaining phases autonomously with minimal human intervention. Runs plan → execute → verify cycles for unfinished work, pausing at checkpoints and failures.
 argument-hint: "[--from N] [--to M] [--only N] [--interactive]"
 allowed-tools: Read, Bash, Agent, AskUserQuestion

package/rihal/commands/brainstorm.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:brainstorm
+name: rihal-brainstorm
 description: Guided brainstorming session — select a method, apply it to your challenge, generate ideas systematically
 argument-hint: "<challenge> [--method=METHOD] [--people=N] [--personas=LIST]"
 allowed-tools:

package/rihal/commands/chain.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:chain
+name: rihal-chain
 description: Run a sequential agent pipeline (research → scope → build). Each stage reads the previous stage's artifact.
 argument-hint: "<preset|agent-list> <topic>"
 allowed-tools: Read, Write, Bash, Agent

package/rihal/commands/check-todos.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:check-todos
+name: rihal-check-todos
 description: List all pending todos, allow selection, load full context for the selected todo, and route to appropriate action.
 argument-hint: ""
 allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, Agent

package/rihal/commands/checkpoint-preview.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:checkpoint-preview
+name: rihal-checkpoint-preview
 description: Human-in-the-loop change review — makes sense of a diff, focuses attention where it matters, and walks through testing. Use when you say "checkpoint", "walk me through this", or "human review".
 argument-hint: "[<branch-or-diff>]"
 allowed-tools:

package/rihal/commands/cleanup.md

@@ -1,6 +1,6 @@
 ---
-name: rihal:cleanup
-description: "Archive completed milestone phase directories into .planning/milestones/. Run after /rihal:complete-milestone to keep .planning/ tidy. Shows a dry-run summary before moving anything."
+name: rihal-cleanup
+description: "Archive completed milestone phase directories into .planning/milestones/. Run after /rihal-complete-milestone to keep .planning/ tidy. Shows a dry-run summary before moving anything."
 argument-hint: "[--dry-run]"
 allowed-tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, Agent
 ---

package/rihal/commands/code-review-fix.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:code-review-fix
+name: rihal-code-review-fix
 description: Auto-fix issues found by code review.
 argument-hint: "<phase> [--all] [--auto]"
 allowed-tools:

package/rihal/commands/code-review.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:code-review
+name: rihal-code-review
 description: Review source files for bugs, security issues, and code quality problems.
 argument-hint: "<phase> [--depth=quick|standard|deep] [--files=file1,file2,...] [--karpathy] [--attack] [--edge-cases]"
 allowed-tools:

package/rihal/commands/complete-milestone.md

@@ -1,5 +1,5 @@
 ---
-name: rihal:complete-milestone
+name: rihal-complete-milestone
 description: Archive and reset — move completed milestone to archive and prepare for next cycle
 argument-hint: "[--archive-path=PATH]"
 allowed-tools: