@hanzlaa/rcode 3.4.33 → 3.5.0

package/rihal/references/nyquist-auditor-playbook.md

@@ -0,0 +1,157 @@
+# Nyquist Auditor Playbook
+
+Shared reference `@`-included by `rihal-nyquist-auditor`. Holds the execution flow, structured-return formats, and success criteria for filling validation gaps.
+
+<execution_flow>
+
+<step name="load_context">
+Read ALL files from `<files_to_read>`. Extract:
+- Implementation: exports, public API, input/output contracts
+- PLANs: requirement IDs, task structure, verify blocks
+- SUMMARYs: what was implemented, files changed, deviations
+- Test infrastructure: framework, config, runner commands, conventions
+- Existing VALIDATION.md: current map, compliance status
+</step>
+
+<step name="analyze_gaps">
+For each gap in `<gaps>`:
+
+1. Read related implementation files
+2. Identify observable behavior the requirement demands
+3. Classify test type:
+
+| Behavior | Test Type |
+|----------|-----------|
+| Pure function I/O | Unit |
+| API endpoint | Integration |
+| CLI command | Smoke |
+| DB/filesystem operation | Integration |
+
+4. Map to test file path per project conventions
+
+Action by gap type:
+- `no_test_file` → Create test file
+- `test_fails` → Diagnose and fix the test (not impl)
+- `no_automated_command` → Determine command, update map
+</step>
+
+<step name="generate_tests">
+Convention discovery: existing tests → framework defaults → fallback.
+
+| Framework | File Pattern | Runner | Assert Style |
+|-----------|-------------|--------|--------------|
+| pytest | `test_{name}.py` | `pytest {file} -v` | `assert result == expected` |
+| jest | `{name}.test.ts` | `npx jest {file}` | `expect(result).toBe(expected)` |
+| vitest | `{name}.test.ts` | `npx vitest run {file}` | `expect(result).toBe(expected)` |
+| go test | `{name}_test.go` | `go test -v -run {Name}` | `if got != want { t.Errorf(...) }` |
+
+Per gap: Write test file. One focused test per requirement behavior. Arrange/Act/Assert. Behavioral test names (`test_user_can_reset_password`), not structural (`test_reset_function`).
+</step>
+
+<step name="run_and_verify">
+Execute each test. If passes: record success, next gap. If fails: enter debug loop.
+
+Run every test. Never mark untested tests as passing.
+</step>
+
+<step name="debug_loop">
+Max 3 iterations per failing test.
+
+| Failure Type | Action |
+|--------------|--------|
+| Import/syntax/fixture error | Fix test, re-run |
+| Assertion: actual matches impl but violates requirement | IMPLEMENTATION BUG → ESCALATE |
+| Assertion: test expectation wrong | Fix assertion, re-run |
+| Environment/runtime error | ESCALATE |
+
+Track: `{ gap_id, iteration, error_type, action, result }`
+
+After 3 failed iterations: ESCALATE with requirement, expected vs actual behavior, impl file reference.
+</step>
+
+<step name="report">
+Resolved gaps: `{ task_id, requirement, test_type, automated_command, file_path, status: "green" }`
+Escalated gaps: `{ task_id, requirement, reason, debug_iterations, last_error }`
+
+Return one of three structured formats below.
+</step>
+
+</execution_flow>
+
+<structured_returns>
+
+## GAPS FILLED
+
+```markdown
+## GAPS FILLED
+
+**Phase:** {N} — {name}
+**Resolved:** {count}/{count}
+
+### Tests Created
+| # | File | Type | Command |
+|---|------|------|---------|
+| 1 | {path} | {unit/integration/smoke} | `{cmd}` |
+
+### Verification Map Updates
+| Task ID | Requirement | Command | Status |
+|---------|-------------|---------|--------|
+| {id} | {req} | `{cmd}` | green |
+
+### Files for Commit
+{test file paths}
+```
+
+## PARTIAL
+
+```markdown
+## PARTIAL
+
+**Phase:** {N} — {name}
+**Resolved:** {M}/{total} | **Escalated:** {K}/{total}
+
+### Resolved
+| Task ID | Requirement | File | Command | Status |
+|---------|-------------|------|---------|--------|
+| {id} | {req} | {file} | `{cmd}` | green |
+
+### Escalated
+| Task ID | Requirement | Reason | Iterations |
+|---------|-------------|--------|------------|
+| {id} | {req} | {reason} | {N}/3 |
+
+### Files for Commit
+{test file paths for resolved gaps}
+```
+
+## ESCALATE
+
+```markdown
+## ESCALATE
+
+**Phase:** {N} — {name}
+**Resolved:** 0/{total}
+
+### Details
+| Task ID | Requirement | Reason | Iterations |
+|---------|-------------|--------|------------|
+| {id} | {req} | {reason} | {N}/3 |
+
+### Recommendations
+- **{req}:** {manual test instructions or implementation fix needed}
+```
+
+</structured_returns>
+
+<success_criteria>
+- [ ] All `<files_to_read>` loaded before any action
+- [ ] Each gap analyzed with correct test type
+- [ ] Tests follow project conventions
+- [ ] Tests verify behavior, not structure
+- [ ] Every test executed — none marked passing without running
+- [ ] Implementation files never modified
+- [ ] Max 3 debug iterations per gap
+- [ ] Implementation bugs escalated, not fixed
+- [ ] Structured return provided (GAPS FILLED / PARTIAL / ESCALATE)
+- [ ] Test files listed for commit
+</success_criteria>

package/rihal/references/workstream-flag.md

@@ -97,10 +97,10 @@ Use workspaces (`--workspace` flag) for:
 /rihal-plan <task> --workspace=Hotfix
 
 # Switch to another workspace's context
-/rihal-workspace <name>
+/rihal-workstream switch --name <name>
 
 # Return to main planning
-/rihal-workspace main
+/rihal-workstream switch --name main
 ```
 
 ## Merging Workspaces Back

package/rihal/skills/actions/1-analysis/rihal-prfaq/SKILL.md

@@ -4,6 +4,11 @@ internal: true
 description: Working Backwards PRFAQ challenge to forge product concepts.
 triggers:
   - "prfaq"
+  - "working backwards"
+  - "press release first"
+  - "create a prfaq"
+  - "product concept challenge"
+  - "forge a product idea"
 ---
 @.rihal/references/karpathy-guidelines.md
 
@@ -133,3 +138,7 @@ When the user gets stuck, offer concrete suggestions based on what they've share
 ### Negative Test
 **Input:** "Create a PRFAQ for a product that doesn't have a clear customer"
 **Expected:** Skill challenges immediately: "Who specifically buys this? Job title + decision criteria?" Refuses vague answers.
+
+## When NOT to use this skill
+
+Do NOT use this skill for writing a full PRD (use rihal-create-prd), validating an existing PRD (use rihal-validate-prd), market research (use rihal-sadiq-analyst), or sprint planning. PRFAQ is a concept-forging challenge, not a requirements document.

package/rihal/skills/actions/4-implementation/rihal-checkpoint-preview/SKILL.md

@@ -4,6 +4,11 @@ internal: true
 description: "LLM-assisted human-in-the-loop review."
 triggers:
   - "checkpoint preview"
+  - "preview the checkpoint"
+  - "human-in-the-loop review"
+  - "review before checkpoint"
+  - "checkpoint review session"
+  - "preview changes before approval"
 ---
 
 ## Overview
@@ -63,3 +68,7 @@ Read fully and follow `./step-01-orientation.md` to begin.
 
 ### Edge Case: No changes to review
 **Expected:** Exit early, suggest the user make changes first.
+
+## When NOT to use this skill
+
+Do NOT use this skill for autonomous execution without a human (it is human-in-the-loop by design), for full code review (use rihal-code-review), or for phase verification (use rihal-verify-phase).

package/rihal/skills/actions/4-implementation/rihal-ci/SKILL.md

@@ -105,6 +105,10 @@ Next steps:
 
 **Negative — "just disable the failing check"** — Refuse. The check exists for a reason. Either fix what's broken or remove the check with a documented rationale.
 
+## When NOT to use this skill
+
+Do NOT use this skill for application code changes, deployment infrastructure beyond CI (use rihal-deploy-unify), security hardening (use rihal-harden), or MVP-to-production migration (use rihal-migrate).
+
 ## Memory Bank Hooks
 
 - **Reads:** `.rihal/memory/project/stack.md` (deploy target)

package/rihal/skills/actions/4-implementation/rihal-code-review/steps/step-02-review.md

@@ -20,10 +20,10 @@ failed_layers: '' # set at runtime: comma-separated list of layers that failed o
    **Subagent mapping** (issue #720): the three reviewer roles below map to actual agents shipped in `.claude/agents/`. The skill names that used to be referenced here (`rihal-review-adversarial-general`, `rihal-review-edge-case-hunter`) are skills, not subagents, and `Task(subagent_type=...)` cannot reach them. Use the agents listed.
 
    - **Blind Hunter** — receives `{diff_output}` only. No spec, no context docs, no project access. Dispatch:
-     `Task(subagent_type="rihal-security-adversary", model="sonnet", prompt="<adversarial review of diff>")`. The security-adversary persona's cynical mindset is the right fit for an isolated diff-only review.
+     `Task(subagent_type="rihal-security-adversary", model="{review_model}", prompt="<adversarial review of diff>")`. The security-adversary persona's cynical mindset is the right fit for an isolated diff-only review.
 
    - **Edge Case Hunter** — receives `{diff_output}` and read access to the project. Dispatch:
-     `Task(subagent_type="rihal-edge-case-hunter", model="sonnet", prompt="<enumerate edge cases for diff>")`.
+     `Task(subagent_type="rihal-edge-case-hunter", model="{review_model}", prompt="<enumerate edge cases for diff>")`.
 
    - **Acceptance Auditor** (only if `{review_mode}` = `"full"`) — receives `{diff_output}`, the content of the file at `{spec_file}`, and any loaded context docs. Dispatch via `rihal-code-reviewer`. Its prompt:
      > You are an Acceptance Auditor. Review this diff against the spec and context docs. Check for: violations of acceptance criteria, deviations from spec intent, missing implementation of specified behavior, contradictions between spec constraints and actual code. Output findings as a Markdown list. Each finding: one-line title, which AC/constraint it violates, and evidence from the diff.

package/rihal/skills/actions/4-implementation/rihal-harden/SKILL.md

@@ -88,6 +88,10 @@ Memory Bank update:
 
 **Negative — "we'll add security later"** — Refuse. Security retrofits are 10× the cost of building it in. Block until at least the Critical findings have a plan.
 
+## When NOT to use this skill
+
+Do NOT use this skill for CI/CD setup (use rihal-ci), performance optimization (use rihal-perf), general code review (use rihal-code-review), or MVP-to-production migration (use rihal-migrate).
+
 ## Memory Bank Hooks
 
 - **Reads:** `.rihal/memory/project/stack.md` (auth layer detection), `.rihal/memory/incidents/post-mortems/` (prior auth/security incidents)

package/rihal/skills/actions/4-implementation/rihal-migrate/SKILL.md

@@ -83,6 +83,10 @@ Each week is reversible: if anything goes sideways, the previous week's state sh
 
 **Negative — "let's rewrite in $NEW_FRAMEWORK"** — Refuse. A rewrite is not graduation. Graduation means filling specific gaps in the current system. Rewrites take 6 months and break what worked.
 
+## When NOT to use this skill
+
+Do NOT use this skill for greenfield projects, framework rewrites (graduation fills gaps, it does not rewrite), feature development, or CI setup alone (use rihal-ci).
+
 ## Memory Bank Hooks
 
 - **Reads:** `.rihal/memory/project/stack.md` (current state), `.rihal/memory/incidents/known-issues.md` (operational pain), `.rihal/memory/milestones/current.md`

package/rihal/skills/agents/haitham-frontend/SKILL.md

@@ -41,6 +41,7 @@ triggers:
   - "مكون React"
 ---
 @.rihal/references/karpathy-guidelines.md
+@.rihal/references/design-tokens.md
 
 
 # Haitham — Senior Frontend Engineer
@@ -69,6 +70,7 @@ Concrete. Code samples over prose. Cites file paths and line numbers. Shows befo
 - Server Components by default in Next.js App Router; Client Components only when needed
 - Tailwind classes organized with `cn()` helper and variants via `cva`
 - Never commit code that doesn't pass `tsc --noEmit`
+- **Missing token? Add the token. Never inline hex.** (see `@.rihal/references/design-tokens.md`)
 
 ## Rihal Frontend Context
 

package/rihal/templates/settings-hooks.json

@@ -8,6 +8,10 @@
           {
             "type": "command",
             "command": "node .rihal/bin/rihal-hooks.cjs pre-edit"
+          },
+          {
+            "type": "command",
+            "command": "node .rihal/bin/rihal-hooks.cjs compact-nudge"
           }
         ]
       },
@@ -19,6 +23,15 @@
             "command": "node .rihal/bin/rihal-hooks.cjs pre-workflow"
           }
         ]
+      },
+      {
+        "matcher": "Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node .rihal/bin/rihal-hooks.cjs bash-guard"
+          }
+        ]
       }
     ],
     "PostToolUse": [
@@ -31,6 +44,32 @@
           }
         ]
       }
+    ],
+    "PreCompact": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node .rihal/bin/rihal-hooks.cjs pre-compact"
+          }
+        ]
+      }
+    ],
+    "Stop": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node .rihal/bin/rihal-hooks.cjs stop-verify"
+          },
+          {
+            "type": "command",
+            "command": "node .rihal/bin/rihal-hooks.cjs cost-track"
+          }
+        ]
+      }
     ]
   }
 }

package/rihal/workflows/check-todos.md

@@ -110,6 +110,7 @@ Use AskUserQuestion:
   - "Add to phase plan" — include when planning Phase [N]
   - "Brainstorm approach" — think through before deciding
   - "Put it back" — return to list
+  - "Cancel" — exit /rihal-check-todos without changing anything
 
 **If no roadmap match:**
 
@@ -121,6 +122,9 @@ Use AskUserQuestion:
   - "Create a phase" — /rihal-add-phase with this scope
   - "Brainstorm approach" — think through before deciding
   - "Put it back" — return to list
+  - "Cancel" — exit /rihal-check-todos without changing anything
+
+**If user picks "Cancel" (or hits Esc):** print `Cancelled — todo untouched.` and STOP. Do not proceed to execute_action.
 </step>
 
 <step name="execute_action">

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

@@ -5,6 +5,7 @@ Auto-fix issues from REVIEW.md. Validates phase, checks config gate, verifies RE
 <required_reading>
 Read all files referenced by the invoking prompt's execution_context before starting.
 @.rihal/references/karpathy-guidelines.md
+@.rihal/references/git-preflight.md
 </required_reading>
 
 <available_agent_types>
@@ -208,7 +209,7 @@ Use Task() to spawn agent:
 
 ```
 Task(subagent_type="rihal-code-fixer",
-  model="sonnet", prompt="
+  model="{model}", prompt="
 <files_to_read>
 ${REVIEW_PATH}
 </files_to_read>
@@ -290,7 +291,7 @@ if [ "$AUTO_MODE" = "true" ]; then
     # Spawn rihal-code-reviewer agent to re-review
     # (This overwrites REVIEW_PATH with latest review state)
     Task(subagent_type="rihal-code-reviewer",
-  model="sonnet", prompt="
+  model="{model}", prompt="
 <config>
 depth: ${REVIEW_DEPTH}
 phase_dir: ${PHASE_DIR}
@@ -324,7 +325,7 @@ Do NOT commit the output — the orchestrator handles that.
     echo "Issues remain. Applying fixes for iteration ${ITERATION}..."
     
     Task(subagent_type="rihal-code-fixer",
-  model="sonnet", prompt="
+  model="{model}", prompt="
 <files_to_read>
 ${REVIEW_PATH}
 </files_to_read>

package/rihal/workflows/code-review.md

@@ -389,7 +389,7 @@ Spawn the rihal-code-reviewer agent:
 
 ```
 Task(subagent_type="rihal-code-reviewer",
-  model="sonnet", prompt="
+  model="{model}", prompt="
 <files_to_read>
 ${FILES_TO_READ}
 </files_to_read>

package/rihal/workflows/debug.md

@@ -116,7 +116,7 @@ For each issue, fill the debug-subagent-prompt template and spawn:
 Task(
   prompt=filled_debug_subagent_prompt + "\n\n<files_to_read>\n- .rihal/STATE.md\n</files_to_read>\n${AGENT_SKILLS_DEBUGGER}",
   subagent_type="rihal-debugger",
-  model="sonnet",
+  model="{model}",
   description="Debug: {truth_short}"
 )
 ```

package/rihal/workflows/dev-story.md

@@ -11,6 +11,10 @@ Wrap a STORY.md file for AI-coder consumption. Produces:
 This workflow creates the execution prompt for a pair-programming session with an AI coder.
 </purpose>
 
+<required_reading>
+@.rihal/references/git-preflight.md
+</required_reading>
+
 
 ## Step 0 — Parse Arguments
 

package/rihal/workflows/diff.md

@@ -39,7 +39,7 @@ If no changes: Return `No changes between {sha1}..{sha2}`
 
 For each file in diff output:
 
-1. Extract filename: `.planning/phases/01-foundation/01-01-SPRINT.md`
+1. Extract filename: `.planning/phases/01-foundation/01-1-SPRINT.md`
 2. Read that file's YAML frontmatter (if .md): extract phase/plan ID
 3. Prefix the hunk with: `Phase {id} — {filename}`
 4. Show the diff +/- lines
@@ -49,7 +49,7 @@ For `.rihal/state.json`: Show raw diff (no frontmatter parsing)
 Example output:
 
 ```
-Phase 01-01 — .planning/phases/01-foundation/01-01-SPRINT.md
+Phase 01-01 — .planning/phases/01-foundation/01-1-SPRINT.md
   @@ -5,3 +5,4 @@
   - old line
   + new line

package/rihal/workflows/do.md

@@ -93,25 +93,33 @@ If `$QUESTION` is empty, present the main menu via AskUserQuestion:
 ```
 What would you like to do?
 
+— Talk —
 1. Quick chat with one expert (/rihal-discuss)
 2. Convene the council (/rihal-council)
 3. Discuss an unlocked phase (/rihal-discuss-phase)
+
+— Plan & build —
 4. Plan a phase (/rihal-plan)
 5. Execute a phase (/rihal-execute)
 6. Sprint planning (/rihal-sprint-planning)
 7. Execute a sprint (/rihal-execute-sprint)
-8. Check sprint status (/rihal-sprint-status)
-9. Break milestone into epics & stories (/rihal-create-epics-and-stories)
-10. Implement a story (/rihal-dev-story)
-11. Check progress (/rihal-progress)
+8. Break milestone into epics & stories (/rihal-create-epics-and-stories)
+9. Implement a story (/rihal-dev-story)
+
+— Status & recovery —
+10. Check progress (/rihal-progress)
+11. Check sprint status (/rihal-sprint-status)
 12. Auto-advance to next step (/rihal-next)
 13. Debug an issue (/rihal-debug)
 14. Resume paused work (/rihal-resume-work)
+
+— Other —
 15. Add a note (/rihal-note)
 16. Something else — describe it
+0.  Cancel — exit without running anything
 ```
 
-If user picks 1-15, invoke that command. If 16, capture text and continue.
+If user picks 1-15, invoke that command. If 16, capture text and continue. If 0 (or empty / Esc), print `Cancelled.` and STOP — do not fall through to project-state survey.
 </step>
 
 <step name="check_project">
@@ -120,7 +128,7 @@ If user picks 1-15, invoke that command. If 16, capture text and continue.
 Detect PRD / epics with glob — projects use either singular files (`.planning/prd.md`) OR per-milestone directories (`.planning/prds/v1.8.md`). Closes #377 — false 'create-prd first' redirects on multi-milestone repos.
 
 ```bash
-INIT=$(node ".rihal/bin/rihal-tools.cjs" state load 2>/dev/null)
+INIT=$(node ".rihal/bin/rihal-tools.cjs" state load 2>/dev/null || echo '{"ok":false,"error":"state_load_failed"}')
 HAS_PRD=$( ( ls .planning/prd.md .planning/PRD.md .planning/prds/*.md .planning/milestones/*/PRD.md 2>/dev/null | head -1 ) && echo true || echo false)
 HAS_EPICS=$( ( ls .planning/epics.md .planning/EPICS.md .planning/epics/*.md .planning/milestones/*/EPICS.md 2>/dev/null | head -1 ) && echo true || echo false)
 PHASE_COUNT=$(node ".rihal/bin/rihal-tools.cjs" progress init 2>/dev/null | python3 -c "import sys,json;print(json.load(sys.stdin).get('phase_count',0))" 2>/dev/null || echo 0)
@@ -221,7 +229,7 @@ The full mapping is in the dictionary's "Scope nouns" table. Pre-conditions enfo
 | epic | `/rihal-create-epics-and-stories` | HAS_PRD true |
 | sprint | `/rihal-sprint-planning` | HAS_EPICS true |
 | PRD | `/rihal-create-prd` | none |
-| roadmap | `/rihal-create-milestone` | HAS_PRD true |
+| roadmap | `/rihal-new-milestone` | HAS_PRD true |
 | council | `/rihal-council` | none |
 | plan (verb) | `/rihal-plan` | HAS_PHASES true |
 
@@ -290,7 +298,7 @@ Evaluate `$QUESTION` against these routing rules. Apply the **first matching** r
 | "Sprint planning", "plan the sprint", "next sprint", "what's in this sprint" | `/rihal-sprint-planning` | Sprint-level scope/capacity planning |
 | Executing a sprint, "run the sprint", "start sprint", "work on sprint" | `/rihal-execute-sprint` | Sprint execution with wave batching |
 | Sprint status, "how is the sprint going", "sprint board", "sprint progress" | `/rihal-sprint-status` | Current sprint state |
-| "Create milestones", "plan milestones", "create roadmap", "what milestones do I need", "break project into milestones" | `/rihal-create-milestone` | Roadmap-level planning — designs M1..Mn from the PRD. Do NOT route to `create-epics-and-stories`; that skill decomposes a single milestone into epics |
+| "Create milestones", "plan milestones", "create roadmap", "what milestones do I need", "break project into milestones" | `/rihal-new-milestone` | Roadmap-level planning — designs M1..Mn from the PRD. Do NOT route to `create-epics-and-stories`; that skill decomposes a single milestone into epics |
 | Break milestone into epics/stories, "create stories", "user stories", "epics" | `/rihal-create-epics-and-stories` | Milestone → epic → story decomposition (assumes roadmap already exists) |
 | Create a single story, "add story", "write a story for X" | `/rihal-create-story` | Single story addition |
 | Implement a story, "work on story", "dev story", "build story" | `/rihal-dev-story` | Story-level implementation |

package/rihal/workflows/docs-update.md

@@ -157,7 +157,7 @@ For each doc in the queue, spawn a `rihal-noor` agent in parallel waves (up to 3
 ```
 Task(
   subagent_type="rihal-noor",
-  model="sonnet",
+  model="{model}",
   prompt="
 Generate documentation for {doc_type}.
 Output path: {resolved_path}
@@ -180,7 +180,7 @@ For each generated doc:
 ```
 Task(
   subagent_type="rihal-docs-auditor",
-  model="sonnet",
+  model="{model}",
   prompt="
 Verify this documentation file against the live codebase:
 Path: {resolved_path}

package/rihal/workflows/enable-hooks.md

@@ -1,7 +1,7 @@
 # Workflow: rihal-enable-hooks
 
 <purpose>
-Merge Rihal opt-in hooks from settings-hooks.json into .claude/settings.json. Creates settings.json if missing. Enables pre-edit (read-before-edit check), pre-workflow (command hint), and post-commit (format validation) guardrails.
+Merge Rihal opt-in hooks from settings-hooks.json into .claude/settings.json. Creates settings.json if missing. Enables all 8 guardrails: pre-edit (read-before-edit check), pre-workflow (command hint), post-commit (format validation), bash-guard (blocks dangerous commands), pre-compact (refreshes HANDOFF.json before context compaction), stop-verify (syntax-checks files changed during the response), cost-track (logs measured token usage to .rihal/telemetry/cost.jsonl), and compact-nudge (advises /rihal-trim or /clear after many edits).
 </purpose>
 
 
@@ -81,6 +81,11 @@ Enabled guardrails:
   • pre-edit: Verifies files are Read() before Edit/Write
   • pre-workflow: Warns if rihal-* commands look suspicious
   • post-commit: Validates commit format and bans "Generated with Claude" patterns
+  • bash-guard: Blocks unapproved git push, --force, --no-verify, and unscoped rm -rf
+  • pre-compact: Refreshes HANDOFF.json before context compaction
+  • stop-verify: Syntax-checks files changed during the response
+  • cost-track: Logs measured token usage to .rihal/telemetry/cost.jsonl
+  • compact-nudge: Advises /rihal-trim or /clear after many edits
 
 To disable, remove the hooks section from .claude/settings.json or edit .rihal/templates/settings-hooks.json and re-run.
 ```