@hanzlaa/rcode 3.4.4 → 3.4.6

package/rihal/skills/core/rihal-review-adversarial-general/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: rihal-review-adversarial-general
-description: 'Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something'
+description: "Perform a Cynical Review and produce a findings report."
 triggers:
   - "review adversarial general"
 ---

package/rihal/skills/core/rihal-review-edge-case-hunter/SKILL.md

@@ -1,8 +1,24 @@
 ---
 name: rihal-review-edge-case-hunter
-description: 'Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.'
+description: "Walk every branching path and boundary condition in content, report only unhandled edge cases."
 triggers:
+  # English
+  - "find edge cases"
+  - "edge case hunt"
+  - "edge cases in this"
   - "review edge case hunter"
+  - "corner cases"
+  - "boundary conditions"
+  - "what could break"
+  # Roman Urdu / Hindi
+  - "edge cases dhoondo"
+  - "edge cases nikalo"
+  # Arabic native
+  - "حالات استثنائية"
+  - "حالات حدية"
+  - "ابحث عن الحالات الاستثنائية"
+  - "افحص الحالات الحدية"
+  - "ما قد يفشل"
 ---
 @.rihal/references/karpathy-guidelines.md
 

package/rihal/skills/core/rihal-shard-doc/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: rihal-shard-doc
-description: 'Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document'
+description: "Splits large markdown documents into smaller, organized files based on level 2 (default) sections."
 triggers:
   - "shard doc"
 ---

package/rihal/skills/core/rihal-theme-system/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: rihal-theme-system
-description: Audit a frontend's design tokens BEFORE launch. Catches inconsistent colours, scattered hex values, hardcoded spacing, font drift, and missing dark/RTL mode support. Specifically encodes Rihal's "had to do complete rebranding mid-project" pain — themes accumulated drift until a full pass was the only fix. Pairs with rihal-rebrand if a rebrand becomes unavoidable.
+description: Audit a frontend's design tokens BEFORE launch.
 triggers:
   - "theme audit"
   - "design tokens"

package/rihal/team.yaml

@@ -514,13 +514,6 @@ tactical_agents:
     authority_level: design
     description: UX design, accessibility, and design system work
 
-  - id: rihal-plan-checker
-    name: Plan Checker
-    file_path: rihal/agents/rihal-sprint-checker.md
-    role: Plan Checker
-    authority_level: quality
-    description: Validates PLAN.md/SPRINT.md quality before execution (alias for sprint-checker)
-
   - id: rihal-verifier
     name: Verifier
     file_path: rihal/agents/rihal-verifier.md

package/rihal/templates/RESEARCH.md

@@ -0,0 +1,84 @@
+# Phase {{N}} — Research
+
+**Phase:** {{N}} — {{phase_name}}
+**Researcher:** {{user_name}}
+**Date:** {{date}}
+**Status:** Draft
+
+---
+
+## Question
+
+What does this phase need to know **before** the planner can write SPRINT.md?
+
+State the central question this RESEARCH.md answers. Keep it tight — one or two sentences. The planner reads this top-down and stops as soon as the question is answered, so do not bury the lede.
+
+---
+
+## Sources
+
+Only cite material you actually fetched in this session. WebSearch snippets are not sufficient evidence. See [`@rihal/skills/_shared/research-citation-rule.md`](../skills/_shared/research-citation-rule.md).
+
+| # | Source | Why it matters |
+|---|--------|----------------|
+| 1 | {{url or file path}} | {{one-line reason}} |
+| 2 | | |
+
+---
+
+## Findings
+
+Group by sub-question. Each finding should be defensible — link back to a source row above.
+
+### Finding A — {{summary}}
+
+- **Evidence:** [src #1, src #2]
+- **What:** {{two or three sentences max}}
+- **So what:** {{implication for the plan — concrete}}
+
+### Finding B — {{summary}}
+
+- **Evidence:** [src #3]
+- **What:**
+- **So what:**
+
+---
+
+## Decisions implied
+
+What does the research force us to decide? List the gray areas the planner now needs to lock down. These become discussion items in CONTEXT.md, not silent assumptions.
+
+- D-1: {{decision name}} — {{options + recommendation if any}}
+- D-2:
+
+---
+
+## Out of scope
+
+What did we NOT research and why. Name future work explicitly so it doesn't quietly fall through.
+
+- {{topic}} — {{reason: deferred / blocked on / not needed for this phase}}
+
+---
+
+## Open questions
+
+Questions that surfaced during research and stay open. The planner can ask the user, defer to a follow-up, or accept the risk. Don't pretend they are answered.
+
+- Q-1:
+- Q-2:
+
+---
+
+## Validation Architecture
+
+<!-- MANDATORY — absence of this section disables Dimension 8 (Nyquist Compliance) in the plan checker. -->
+<!-- If no automated tests are feasible, state that explicitly with a reason. -->
+
+| Concern | Test File | Command | When (Wave) |
+|---------|-----------|---------|-------------|
+| {{feature/requirement}} | {{path/to/test.ts}} | {{run command}} | Wave {{N}} |
+
+---
+
+*Phase {{N}} research artifact. Consumed by `rihal-planner` per the [`@.rihal/workflows/plan.md`](../workflows/plan.md) sequence.*

package/rihal/templates/VALIDATION.md

@@ -0,0 +1,45 @@
+# Validation Architecture — {{phase_name}}
+
+<!-- Generated by /rihal-plan --research. Dimension 8 (Nyquist Compliance) reads this file. -->
+<!-- Delete this comment block after filling in. An empty VALIDATION.md causes Dimension 8e to BLOCK. -->
+
+**Phase:** {{phase_id}}
+**Generated:** {{date}}
+
+## Validation Architecture
+
+<!-- Describe how this phase will be validated. What tests exist or will be created? -->
+<!-- If no test files are planned, explicitly state why and what manual checks substitute. -->
+
+### Test Strategy
+
+| Concern | Test File | Command | When Run |
+|---------|-----------|---------|----------|
+| {{feature/requirement}} | {{test_file_path}} | {{run_command}} | Wave {{N}} |
+
+### Wave 0 Test Files (TDD tasks)
+
+<!-- List any test files that must be created BEFORE implementation tasks run. -->
+<!-- These are referenced as `<automated>MISSING</automated>` in task verify blocks. -->
+
+| Test File | Created By Task | For Task(s) |
+|-----------|----------------|-------------|
+| {{test_file_path}} | Task {{N}} | Task {{M}} |
+
+### Automated Verify Commands
+
+<!-- Summary of all `<automated>` commands across tasks. -->
+<!-- Executor and verifier use these as the ground-truth test set. -->
+
+```bash
+# Per-task verify commands (replicated here for quick reference)
+{{command}}
+```
+
+### Feedback Latency
+
+<!-- Are any verify commands slow (>30s)? Flag them. -->
+<!-- Long-running suites should have a faster smoke-test fallback. -->
+
+- Estimated total verify time: < {{N}} seconds
+- Slow commands (>30s): {{none / list}}

package/rihal/templates/memory/INDEX.md

@@ -13,6 +13,7 @@
 | [`project/stack.md`](project/stack.md) | Languages, frameworks, services in use |
 | [`project/decisions.md`](project/decisions.md) | Append-only architectural decision log |
 | [`project/glossary.md`](project/glossary.md) | Domain terms, internal names, acronyms |
+| [`project/design-system.md`](project/design-system.md) | Visual tokens, canonical components, conventions — read by `ui-phase`, `frontend-design`, `clone-website` |
 | [`people/stakeholders.md`](people/stakeholders.md) | External contacts, decision authority, comms |
 | [`people/team.md`](people/team.md) | Internal team, ownership, availability |
 | [`milestones/current.md`](milestones/current.md) | Active milestone — goal, phase, blockers |

package/rihal/templates/memory/project/design-system.md

@@ -0,0 +1,128 @@
+# Design System — `{{PROJECT_NAME}}`
+
+> Single source of truth for visual tokens, component patterns, and UI conventions. Agents writing UI code (frontend skills, ui-phase, frontend-design, clone-website) MUST read this before producing components or styles. UI-SPEC.md files for individual phases cite this as their root reference.
+
+**Last updated:** {{INIT_DATE}}
+**Source of truth:** this file + the canonical token files it points to
+
+---
+
+## Tokens
+
+Document the canonical token names — never restate hex / rem values inline in code. Components should reference tokens.
+
+### Color
+
+| Token | Purpose | Source file |
+|---|---|---|
+| `--ds-bg` | Page background | (e.g. `app/globals.css`) |
+| `--ds-bg-raised` | Card / surface background | |
+| `--ds-border` | Default border | |
+| `--ds-text` | Body text | |
+| `--ds-text-muted` | Secondary text | |
+| `--ds-accent` | Primary accent / CTA | |
+| `--ds-hover` | Hover background | |
+
+### Typography
+
+| Token | Purpose |
+|---|---|
+| `--ds-font-display` | Headings |
+| `--ds-font-body` | Body text |
+| `--ds-font-mono` | Code / inline mono |
+
+### Spacing scale
+
+Document the discrete spacing values used (e.g. `4 / 8 / 12 / 16 / 24 / 32` rem-relative) and what each maps to in Tailwind / CSS variables.
+
+### Radius scale
+
+| Token | Tailwind | Use for |
+|---|---|---|
+| `--ds-radius-sm` | `rounded` | Inputs, small chips |
+| `--ds-radius-md` | `rounded-xl` | Form inputs, secondary cards |
+| `--ds-radius-lg` | `rounded-2xl` | Primary surfaces, modals |
+| `--ds-radius-full` | `rounded-full` | Avatars, pills |
+
+---
+
+## Canonical component patterns
+
+The exact class lists / token compositions that define the project's visual identity. New components MUST match these patterns.
+
+### Card / surface shell
+
+```html
+<div class="bg-ds-raised rounded-2xl border border-ds-border/70 p-6">
+  ...
+</div>
+```
+
+### Form input
+
+```html
+<input class="rounded-xl bg-ds-hover px-3 py-2 focus:ring-1 focus:ring-ds-accent/20" />
+```
+
+### Primary button
+
+```html
+<button class="rounded-xl bg-ds-accent text-white px-4 py-2 hover:opacity-90">
+  ...
+</button>
+```
+
+(Add: secondary button, link, badge, modal, dropdown, table row, etc. — whatever the project actually uses.)
+
+---
+
+## Conventions
+
+Hard rules. Violating these = anti-pattern, must be flagged in code review.
+
+- **Reach for `bg-ds-raised` not `bg-white`** — direct color literals lose dark-mode and theming
+- **Never use `style={{}}`** — Tailwind classes or design tokens only
+- **Never use `React.FC` / `React.FunctionComponent`** — function declarations only
+- **Borders use `/70` or `/60` opacity** — solid `border-ds-border` is reserved for emphasis
+- **Spacing increments only** — no `px-[7]` or arbitrary values; if a value isn't on the scale, the scale needs to expand or the component is wrong
+- **Radius hierarchy**: outer card 2xl → inner element xl → micro element `rounded`. Never invert.
+
+---
+
+## RTL / multilingual
+
+(Skip if not applicable.)
+
+- Direction-aware spacing: use `ms-` / `me-` (Tailwind logical) not `ml-` / `mr-`
+- Mirror icons that have directional intent (chevrons, arrows) for RTL
+- Typography: separate Arabic + Latin font stacks via `--ds-font-display-ar` / `--ds-font-display-lat`
+
+---
+
+## Inspiration / source-of-language
+
+Where did this visual language come from? Link the originating commits, PRs, or external references so future agents understand the lineage.
+
+- **Recent canonical commits**: (e.g. `08e2e03d`, `bcc86535` — "Attio-standard redesigns of calling tabs")
+- **External references**: (e.g. linear.app, attio.com, your own brand guidelines)
+
+When extending the system, mirror the lineage rather than inventing.
+
+---
+
+## How agents use this file
+
+1. **Frontend / UI skills** read this first before producing any component code
+2. **`/rihal-ui-phase`** cites this file in the produced UI-SPEC.md as `read_first`
+3. **`rihal-frontend-design`** ports design directions FROM this — never independently
+4. **Code review skills** flag any new code that introduces hex values, raw colors, or pattern violations
+5. **`/rihal-clone-website`** uses this to translate cloned styles into project-native tokens — never preserves source-site classes verbatim
+
+---
+
+## Maintenance
+
+- Update when a new canonical pattern lands (e.g. a redesign sprint that shifts radius scale)
+- Reference the commit that established each pattern in the "Inspiration" section
+- Distillate version is regenerated by `/rcode-memory-distill`
+- Audit via `/rcode-memory-audit` at every milestone close

package/rihal/templates/summary.md

@@ -1,10 +1,16 @@
+---
+phase: "{{phase_id}}"
+status: complete
+closed_at: "{{closed_at}}"
+---
+
 # Phase Summary — {{phase_name}}
 
 <!-- P2: Omit any section that has nothing substantive to say. An empty section is worse than no section. -->
 
 **Phase ID:** {{phase_id}}
 **Closed:** {{closed_at}}
-**Plan:** PLAN.md
+**Sprint:** SPRINT.md
 
 ## Outcomes
 
@@ -12,19 +18,43 @@
 
 ## Decisions Made
 
-<!-- Omit if no decisions were made that aren't already in PLAN.md -->
+<!-- Omit if no decisions were made that aren't already in SPRINT.md -->
 - {{key choices and their rationale}}
 
 ## Deviations from Plan
 
 <!-- Omit if execution matched the plan exactly -->
-- {{anything that diverged from PLAN.md and why}}
+- {{anything that diverged from SPRINT.md and why}}
 
 ## Issues Encountered
 
 <!-- Omit if no tasks were pruned, escalated, or skipped -->
 - {{tasks pruned, escalated, or skipped}}
 
+## Patterns Established
+
+<!-- Omit if no new patterns were introduced. List architectural/coding patterns future phases should follow. -->
+<!-- Example: "All service errors now wrap in ServiceError(code, message) — see auth.service.ts:42" -->
+- {{new pattern introduced by this phase and where it lives}}
+
+## Provides
+
+<!-- What this phase exposes for future phases to build on. Be specific: function names, API endpoints, data models, config keys. -->
+<!-- Example: "UserRepository.findByEmail() — src/repositories/user.repo.ts" -->
+- {{what future phases can reuse from this phase}}
+
+## Requires
+
+<!-- What this phase consumed from prior phases. Helps trace dependency chains. -->
+<!-- Example: "Database connection from Phase 3 (src/db/connection.ts)" -->
+- {{what this phase depended on from earlier phases}}
+
+## Affects
+
+<!-- Downstream phases or components that may be impacted by what changed here. -->
+<!-- Example: "Phase 9 (checkout flow) — depends on Cart model introduced here" -->
+- {{phases or components that should re-verify after this phase}}
+
 ## Hand-off
 
 Next phase: {{next phase id and goal}}

package/rihal/workflows/add-tests.md

@@ -55,7 +55,7 @@ Read the phase artifacts (in order of priority):
 If no SUMMARY.md exists:
 ```
 ERROR: No SUMMARY.md found for phase ${PHASE_ARG}
-This command works on completed phases. Run /rihal-execute-phase first.
+This command works on completed phases. Run /rihal-execute first.
 ```
 Exit.
 

package/rihal/workflows/add-todo.md

@@ -179,3 +179,9 @@ If arguments are invalid, missing files, or subagent fails:
 - Check that required files exist
 - Retry with clearer arguments or report the specific error to the user
 
+
+## On Completion
+
+/rihal-check-todos — review all open todos
+/rihal-next — get suggested next action
+/rihal-progress — see overall roadmap status

package/rihal/workflows/analyze-dependencies.md

@@ -136,3 +136,9 @@ After applying: "ROADMAP.md updated. Run `/rihal-manager` to execute phases in t
 - **ROADMAP.md missing:** Print error and suggest creating project first
 - **Phase parsing fails:** Print which phase and why parsing failed
 - **File write fails:** Print error and suggest manual update
+
+## ▶ Next Up
+
+- **Circular deps found:** Fix dependency cycle, then re-run analysis
+- **Ready to execute:** `/rihal-execute {phase}` — run with dependency awareness
+- **Review roadmap:** `/rihal-progress` — see full project state

package/rihal/workflows/audit-fix.md

@@ -190,3 +190,15 @@ If arguments are invalid, missing files, or subagent fails:
 - Check that required files exist
 - Retry with clearer arguments or report the specific error to the user
 
+
+## On Completion
+
+/rihal-audit — re-run audit to verify fixes applied correctly
+/rihal-code-review — review the auto-applied changes
+/rihal-progress — see overall project state
+
+## ▶ Next Up
+
+- **Fixes applied:** `/rihal-verify-phase {phase}` — re-verify after fixes
+- **More issues:** `/rihal-audit {phase}` — run audit again to confirm
+- **All clean:** `/rihal-progress` — check project state

package/rihal/workflows/audit-milestone.md

@@ -144,7 +144,7 @@ If no SUMMARY.md files found, **do not dead-halt** (closes #234). Probe
 for executed-phase signals and offer recovery options:
 
 ```bash
-PLANS=$(find "$MILESTONE_DIR" -name PLAN.md 2>/dev/null | wc -l)
+PLANS=$(find "$MILESTONE_DIR" \( -name PLAN.md -o -name '*-SPRINT.md' \) 2>/dev/null | wc -l)
 GIT_FEAT=$(git log --oneline --grep='^feat' 2>/dev/null | wc -l)
 APPS=$(ls -d apps packages src 2>/dev/null | wc -l)
 ```
@@ -156,7 +156,7 @@ If `PLANS > 0` AND (`GIT_FEAT > 0` OR `APPS > 0`):
   Phases were executed but never formally closed.
 
   Options:
-    1. Synthesize SUMMARY.md per phase from PLAN.md + git log [recommended]
+    1. Synthesize SUMMARY.md per phase from SPRINT.md + git log [recommended]
        (groups commits by phase tag like "feat(03-1):", writes a
         first-pass SUMMARY.md the user can edit)
     2. Run /rihal-verify-phase NN per phase (manual close path)

package/rihal/workflows/audit.md

@@ -17,13 +17,14 @@ and auto-picks the most-relevant target based on project state. In
 If `$ARGUMENTS` contains `--help` or `-h`:
 
 ```
-/rihal-audit                       # interactive — asks what to audit
-/rihal-audit phase [<NN>]          # → /rihal-verify-phase
-/rihal-audit milestone [--strict]  # → /rihal-audit-milestone (with synth fallback)
-/rihal-audit uat                   # → /rihal-audit-uat
-/rihal-audit code [--scope=...]    # → /rihal-code-review --karpathy
-/rihal-audit fix                   # → /rihal-audit-fix
-/rihal-audit work                  # → /rihal-verify-work
+/rihal-audit                           # interactive — asks what to audit
+/rihal-audit phase [<NN>]              # → /rihal-verify-phase
+/rihal-audit milestone [--strict]      # → /rihal-audit-milestone (with synth fallback)
+/rihal-audit uat                       # → /rihal-audit-uat
+/rihal-audit code [--scope=...]        # → /rihal-code-review --karpathy
+/rihal-audit fix                       # → /rihal-audit-fix
+/rihal-audit work                      # → /rihal-verify-work
+/rihal-audit lens [<1-15> | all]       # → /rihal-lens-audit (15-lens methodology)
 ```
 
 **Examples:**
@@ -31,6 +32,8 @@ If `$ARGUMENTS` contains `--help` or `-h`:
 /rihal-audit
 /rihal-audit milestone --strict
 /rihal-audit phase 03
+/rihal-audit lens security
+/rihal-audit lens all
 ```
 
 ## Step 1 — Resolve mode + arguments
@@ -42,7 +45,7 @@ DISCUSS=$($TOOL config-get workflow.discuss_mode 2>/dev/null || echo "adaptive")
 ```
 
 Parse `$ARGUMENTS`:
-- First word ∈ {phase, milestone, uat, code, fix, work} → set `$TARGET`, drop it from args, jump to Step 4.
+- First word ∈ {phase, milestone, uat, code, fix, work, lens} → set `$TARGET`, drop it from args, jump to Step 4.
 - Empty or unrecognised → continue to Step 2.
 
 ## Step 2 — Detect project state
@@ -52,7 +55,7 @@ Probe what's audit-able right now:
 ```bash
 ROADMAP=$([ -f .planning/ROADMAP.md ] && echo yes || echo no)
 PHASES=$(ls -d .planning/phases/*/ 2>/dev/null | wc -l)
-PLANS=$(find .planning/phases -name PLAN.md 2>/dev/null | wc -l)
+PLANS=$(find .planning/phases \( -name PLAN.md -o -name '*-SPRINT.md' \) 2>/dev/null | wc -l)
 SUMMARIES=$(find .planning/phases -name SUMMARY.md 2>/dev/null | wc -l)
 UAT_FILES=$(find .planning -name 'UAT*.md' 2>/dev/null | wc -l)
 ON_BRANCH=$(git rev-parse --abbrev-ref HEAD 2>/dev/null)
@@ -81,6 +84,7 @@ Options:
   4. code-quality    — Karpathy 4-principle code review        (current diff)
   5. auto-fix        — audit then auto-fix findings            (uses #1–4 output)
   6. work            — verify current branch / WIP             ({ON_BRANCH}, dirty={DIRTY})
+  7. lens            — 15-lens methodology audit               (security, perf, tests…)
   0. cancel
 ```
 
@@ -94,12 +98,13 @@ sub-workflow.
 
 | target | precondition | failure message |
 |---|---|---|
-| phase | at least one `.planning/phases/*/PLAN.md` | `No PLAN.md found. Run /rihal-plan first.` |
+| phase | at least one `.planning/phases/*/PLAN.md` or `*-SPRINT.md` | `No plan file found. Run /rihal-plan first.` |
 | milestone | ROADMAP.md exists | `No ROADMAP.md. Run /rihal-new-milestone first.` |
 | uat | at least one UAT*.md exists | `No UAT files yet. Run /rihal-execute on a phase first.` |
 | code | git repo with at least one commit | `Empty repo — nothing to audit yet.` |
 | fix | a prior audit report exists OR a prior `--report` artefact | `No audit findings yet. Run /rihal-audit first.` |
 | work | inside a git worktree | `Not in a git repo.` |
+| lens | `rihal/` or `.rihal/` directory exists | `No rihal source found. Run: npx @hanzlaa/rcode install .` |
 
 For `milestone` specifically, check the **graceful-degrade** condition
 (closes #234 audit-milestone halt):
@@ -111,7 +116,7 @@ if [ "$TARGET" = "milestone" ] && [ "$SUMMARIES" -eq 0 ] && [ "$PLANS" -gt 0 ];
   echo "⚠ $PLANS phases planned, 0 SUMMARY.md, $GIT_FEAT_COMMITS feat commits."
   echo "  Phases were executed but never formally closed."
   # Offer (yolo: auto-pick 1; guided: ask):
-  #   1. Synthesize SUMMARY.md per phase from PLAN.md + git log    [recommended]
+  #   1. Synthesize SUMMARY.md per phase from SPRINT.md + git log    [recommended]
   #   2. Run /rihal-verify-phase per phase (manual close)
   #   3. Continue audit anyway (will only assess what's documented)
   #   0. Cancel
@@ -121,13 +126,13 @@ fi
 In `mode: yolo`, auto-pick option 1: group `git log --oneline` output by
 phase tag (e.g. commits matching `^feat\(0?(\d+)`) and write a first-pass
 `SUMMARY.md` per phase under `.planning/phases/<phase>/SUMMARY.md`
-containing the goal (from PLAN.md), the commit list, and a `# TODO:
+containing the goal (from SPRINT.md), the commit list, and a `# TODO:
 expand outcomes` marker. The user can then refine before re-running the
 audit.
 
 A native `phase synthesize-summaries` CLI subcommand is tracked separately
 (see #234 follow-ups) — until it lands, the LLM performs the synthesis
-inline using `git log` + `Read PLAN.md` + `Write SUMMARY.md`.
+inline using `git log` + `Read SPRINT.md` + `Write SUMMARY.md`.
 
 ## Step 5 — Dispatch
 
@@ -139,6 +144,7 @@ Run the target's slash command, forwarding remaining args:
 | milestone | `/rihal-audit-milestone $REST_ARGS` |
 | uat | `/rihal-audit-uat $REST_ARGS` |
 | code | `/rihal-code-review $REST_ARGS --karpathy` |
+| lens | `/rihal-lens-audit $REST_ARGS` |
 | fix | `/rihal-audit-fix $REST_ARGS` |
 | work | `/rihal-verify-work $REST_ARGS` |
 
@@ -155,6 +161,7 @@ Findings: {count}
 Next:
   /rihal-audit fix         — auto-fix findings classified as auto-fixable
   /rihal-audit code        — drill into code-quality issues
+  /rihal-audit lens        — 15-lens methodology audit
   /rihal-settings show     — review which audit gates are enabled
 ```
 
@@ -162,7 +169,9 @@ Next:
 
 - [ ] `/rihal-audit` (no args) presents menu in guided mode, auto-picks in yolo
 - [ ] `/rihal-audit milestone` short-circuits the menu
-- [ ] When SUMMARY.md absent but PLAN.md present, milestone offers synthesize/verify/skip — does not dead-halt
+- [ ] `/rihal-audit lens` dispatches to `/rihal-lens-audit` interactive picker
+- [ ] `/rihal-audit lens security` passes `security` directly to `/rihal-lens-audit`
+- [ ] When SUMMARY.md absent but SPRINT.md present, milestone offers synthesize/verify/skip — does not dead-halt
 - [ ] Sub-workflow's closing report is surfaced unchanged
 
 ## On Error