@cregis-dev/cckit 0.3.0 → 0.4.0

package/templates/bmad/tea/workflows/testarch/test-review/steps-c/step-03c-subagent-maintainability.md

@@ -0,0 +1,102 @@
+---
+name: 'step-03c-subagent-maintainability'
+description: 'Subagent: Check test maintainability (readability, structure, DRY)'
+subagent: true
+outputFile: '/tmp/tea-test-review-maintainability-{{timestamp}}.json'
+---
+
+# Subagent 3C: Maintainability Quality Check
+
+## SUBAGENT CONTEXT
+
+This is an **isolated subagent** running in parallel with other quality dimension checks.
+
+**Your task:** Analyze test files for MAINTAINABILITY violations only.
+
+---
+
+## MANDATORY EXECUTION RULES
+
+- ✅ Check MAINTAINABILITY only (not other quality dimensions)
+- ✅ Output structured JSON to temp file
+- ❌ Do NOT check determinism, isolation, coverage, or performance
+
+---
+
+## SUBAGENT TASK
+
+### 1. Identify Maintainability Violations
+
+**HIGH SEVERITY Violations**:
+
+- Tests >100 lines (too complex)
+- No test.describe grouping
+- Duplicate test logic (copy-paste)
+- Unclear test names (no Given/When/Then structure)
+- Magic numbers/strings without constants
+
+**MEDIUM SEVERITY Violations**:
+
+- Tests missing comments for complex logic
+- Inconsistent naming conventions
+- Excessive nesting (>3 levels)
+- Large setup/teardown blocks
+
+**LOW SEVERITY Violations**:
+
+- Minor code style issues
+- Could benefit from helper functions
+- Inconsistent assertion styles
+
+### 2. Calculate Maintainability Score
+
+```javascript
+const severityWeights = { HIGH: 10, MEDIUM: 5, LOW: 2 };
+const totalPenalty = violations.reduce((sum, v) => sum + severityWeights[v.severity], 0);
+const score = Math.max(0, 100 - totalPenalty);
+```
+
+---
+
+## OUTPUT FORMAT
+
+```json
+{
+  "dimension": "maintainability",
+  "score": 75,
+  "max_score": 100,
+  "grade": "C",
+  "violations": [
+    {
+      "file": "tests/e2e/complex-flow.spec.ts",
+      "line": 1,
+      "severity": "HIGH",
+      "category": "test-too-long",
+      "description": "Test file is 250 lines - too complex to maintain",
+      "suggestion": "Split into multiple smaller test files by feature area",
+      "code_snippet": "test.describe('Complex flow', () => { /* 250 lines */ });"
+    }
+  ],
+  "passed_checks": 10,
+  "failed_checks": 5,
+  "violation_summary": {
+    "HIGH": 2,
+    "MEDIUM": 2,
+    "LOW": 1
+  },
+  "recommendations": [
+    "Split large test files into smaller, focused files (<100 lines each)",
+    "Add test.describe grouping for related tests",
+    "Extract duplicate logic into helper functions"
+  ],
+  "summary": "Tests have maintainability issues - 5 violations (2 HIGH)"
+}
+```
+
+---
+
+## EXIT CONDITION
+
+Subagent completes when JSON output written to temp file.
+
+**Subagent terminates here.**

package/templates/bmad/tea/workflows/testarch/test-review/steps-c/step-03e-subagent-performance.md

@@ -0,0 +1,117 @@
+---
+name: 'step-03e-subagent-performance'
+description: 'Subagent: Check test performance (speed, efficiency, parallelization)'
+subagent: true
+outputFile: '/tmp/tea-test-review-performance-{{timestamp}}.json'
+---
+
+# Subagent 3E: Performance Quality Check
+
+## SUBAGENT CONTEXT
+
+This is an **isolated subagent** running in parallel with other quality dimension checks.
+
+**Your task:** Analyze test files for PERFORMANCE violations only.
+
+---
+
+## MANDATORY EXECUTION RULES
+
+- ✅ Check PERFORMANCE only (not other quality dimensions)
+- ✅ Output structured JSON to temp file
+- ❌ Do NOT check determinism, isolation, maintainability, or coverage
+
+---
+
+## SUBAGENT TASK
+
+### 1. Identify Performance Violations
+
+**HIGH SEVERITY Violations**:
+
+- Tests not parallelizable (using test.describe.serial unnecessarily)
+- Slow setup/teardown (creating fresh DB for every test)
+- Excessive navigation (reloading pages unnecessarily)
+- No fixture reuse (repeating expensive operations)
+
+**MEDIUM SEVERITY Violations**:
+
+- Hard waits >2 seconds (waitForTimeout(5000))
+- Inefficient selectors (page.$$ instead of locators)
+- Large data sets in tests without pagination
+- Missing performance optimizations
+
+**LOW SEVERITY Violations**:
+
+- Could use parallelization (test.describe.configure({ mode: 'parallel' }))
+- Minor inefficiencies
+- Excessive logging
+
+### 2. Calculate Performance Score
+
+```javascript
+const severityWeights = { HIGH: 10, MEDIUM: 5, LOW: 2 };
+const totalPenalty = violations.reduce((sum, v) => sum + severityWeights[v.severity], 0);
+const score = Math.max(0, 100 - totalPenalty);
+```
+
+---
+
+## OUTPUT FORMAT
+
+```json
+{
+  "dimension": "performance",
+  "score": 80,
+  "max_score": 100,
+  "grade": "B",
+  "violations": [
+    {
+      "file": "tests/e2e/search.spec.ts",
+      "line": 10,
+      "severity": "HIGH",
+      "category": "not-parallelizable",
+      "description": "Tests use test.describe.serial unnecessarily - reduces parallel execution",
+      "suggestion": "Remove .serial unless tests truly share state",
+      "code_snippet": "test.describe.serial('Search tests', () => { ... });"
+    },
+    {
+      "file": "tests/api/bulk-operations.spec.ts",
+      "line": 35,
+      "severity": "MEDIUM",
+      "category": "slow-setup",
+      "description": "Test creates 1000 records in setup - very slow",
+      "suggestion": "Use smaller data sets or fixture factories",
+      "code_snippet": "beforeEach(async () => { for (let i=0; i<1000; i++) { ... } });"
+    }
+  ],
+  "passed_checks": 13,
+  "failed_checks": 2,
+  "violation_summary": {
+    "HIGH": 1,
+    "MEDIUM": 1,
+    "LOW": 0
+  },
+  "performance_metrics": {
+    "parallelizable_tests": 80,
+    "serial_tests": 20,
+    "avg_test_duration_estimate": "~2 seconds",
+    "slow_tests": ["bulk-operations.spec.ts (>30s)"]
+  },
+  "recommendations": [
+    "Enable parallel mode where possible",
+    "Reduce setup data to minimum needed",
+    "Use fixtures to share expensive setup across tests",
+    "Remove unnecessary .serial constraints"
+  ],
+  "summary": "Good performance with 2 violations - 80% tests can run in parallel"
+}
+```
+
+---
+
+## EXIT CONDITION
+
+Subagent completes when JSON output written to temp file.
+
+**Subagent terminates here.**

package/templates/bmad/tea/workflows/testarch/test-review/steps-c/step-03f-aggregate-scores.md

@@ -9,7 +9,7 @@ outputFile: '{test_artifacts}/test-review.md'
 
 ## STEP GOAL
 
-Read outputs from 4 quality subprocesses, calculate weighted overall score (0-100), and aggregate violations for report generation.
+Read outputs from 4 quality subagents, calculate weighted overall score (0-100), and aggregate violations for report generation.
 
 ---
 
@@ -17,10 +17,10 @@ Read outputs from 4 quality subprocesses, calculate weighted overall score (0-10
 
 - 📖 Read the entire step file before acting
 - ✅ Speak in `{communication_language}`
-- ✅ Read all 4 subprocess outputs
+- ✅ Read all 4 subagent outputs
 - ✅ Calculate weighted overall score
 - ✅ Aggregate violations by severity
-- ❌ Do NOT re-evaluate quality (use subprocess outputs)
+- ❌ Do NOT re-evaluate quality (use subagent outputs)
 
 ---
 
@@ -34,11 +34,11 @@ Read outputs from 4 quality subprocesses, calculate weighted overall score (0-10
 
 ## MANDATORY SEQUENCE
 
-### 1. Read All Subprocess Outputs
+### 1. Read All Subagent Outputs
 
 ```javascript
 // Use the SAME timestamp generated in Step 3 (do not regenerate).
-const timestamp = subprocessContext?.timestamp;
+const timestamp = subagentContext?.timestamp;
 if (!timestamp) {
   throw new Error('Missing timestamp from Step 3 context. Pass Step 3 timestamp into Step 3F.');
 }
@@ -56,7 +56,7 @@ dimensions.forEach((dim) => {
 ```javascript
 const allSucceeded = dimensions.every((dim) => results[dim].score !== undefined);
 if (!allSucceeded) {
-  throw new Error('One or more quality subprocesses failed!');
+  throw new Error('One or more quality subagents failed!');
 }
 ```
 
@@ -179,7 +179,7 @@ const reviewSummary = {
 
   top_10_recommendations: prioritizedRecommendations,
 
-  subprocess_execution: 'PARALLEL (4 quality dimensions)',
+  subagent_execution: 'PARALLEL (4 quality dimensions)',
   performance_gain: '~60% faster than sequential',
 };
 
@@ -247,7 +247,7 @@ fs.writeFileSync(`/tmp/tea-test-review-summary-${timestamp}.json`, JSON.stringif
 
 Proceed to Step 4 when:
 
-- ✅ All subprocess outputs read successfully
+- ✅ All subagent outputs read successfully
 - ✅ Overall score calculated
 - ✅ Violations aggregated
 - ✅ Recommendations prioritized
@@ -263,14 +263,14 @@ Load next step: `{nextStepFile}`
 
 ### ✅ SUCCESS:
 
-- All 4 subprocess outputs read and parsed
+- All 4 subagent outputs read and parsed
 - Overall score calculated with proper weights
 - Violations aggregated correctly
 - Summary complete and saved
 
 ### ❌ FAILURE:
 
-- Failed to read one or more subprocess outputs
+- Failed to read one or more subagent outputs
 - Score calculation incorrect
 - Summary missing or incomplete
 

package/templates/bmad/tea/workflows/testarch/test-review/validation-report-20260127-095021.md

@@ -1,7 +1,7 @@
 ---
 validationDate: 2026-01-27
 workflowName: testarch-test-review
-workflowPath: /Users/murat.ozcan/opensource/bmad-method-test-architecture-enterprise/src/workflows/testarch/test-review
+workflowPath: {project-root}/src/workflows/testarch/test-review
 validationStatus: COMPLETE
 completionDate: 2026-01-27 10:03:10
 ---

package/templates/bmad/tea/workflows/testarch/test-review/validation-report-20260127-102401.md

@@ -1,7 +1,7 @@
 ---
 validationDate: 2026-01-27
 workflowName: testarch-test-review
-workflowPath: /Users/murat.ozcan/opensource/bmad-method-test-architecture-enterprise/src/workflows/testarch/test-review
+workflowPath: {project-root}/src/workflows/testarch/test-review
 validationStatus: COMPLETE
 completionDate: 2026-01-27 10:24:01
 ---
@@ -85,9 +85,9 @@ Standard BMAD config variables treated as valid exceptions: bmb_creations_output
 - Steps use progressive prompts and clear role reinforcement; no laundry-list interrogation detected
 - Flow progression is clear and aligned to workflow goals
 
-## Subprocess Optimization Opportunities
+## Subagent Optimization Opportunities
 
-- No high-priority subprocess optimizations identified; workflow already uses step-file architecture
+- No high-priority subagent optimizations identified; workflow already uses step-file architecture
 - Pattern 1 (grep/regex): N/A for most steps
 - Pattern 2 (per-file analysis): already aligned to validation structure
 - Pattern 3 (data ops): minimal data file loads

package/templates/bmad/tea/workflows/testarch/test-review/workflow.yaml

@@ -1,6 +1,7 @@
 # Test Architect workflow: test-review
 name: testarch-test-review
-description: "Review test quality using best practices validation. Use when the user says 'lets review tests' or 'I want to evaluate test quality'"
+# prettier-ignore
+description: 'Review test quality using best practices validation. Use when the user says "lets review tests" or "I want to evaluate test quality"'
 
 # Critical variables from config
 config_source: "{project-root}/_bmad/tea/config.yaml"
@@ -45,4 +46,3 @@ execution_hints:
   interactive: false # Minimize prompts
   autonomous: true # Proceed without user input unless blocked
   iterative: true # Can review multiple files
-

package/templates/bmad/tea/workflows/testarch/trace/steps-c/step-04-analyze-gaps.md

@@ -1,6 +1,6 @@
 ---
 name: 'step-04-analyze-gaps'
-description: 'Complete Phase 1: Generate coverage matrix with gap analysis'
+description: 'Complete Phase 1 with adaptive orchestration (agent-team, subagent, or sequential)'
 nextStepFile: './step-05-gate-decision.md'
 outputFile: '{test_artifacts}/traceability-report.md'
 tempOutputFile: '/tmp/tea-trace-coverage-matrix-{{timestamp}}.json'
@@ -19,6 +19,8 @@ tempOutputFile: '/tmp/tea-trace-coverage-matrix-{{timestamp}}.json'
 - 📖 Read the entire step file before acting
 - ✅ Speak in `{communication_language}`
 - ✅ Output coverage matrix to temp file
+- ✅ Resolve execution mode from explicit user request first, then config
+- ✅ Apply fallback rules deterministically when requested mode is unsupported
 - ❌ Do NOT make gate decision (that's Phase 2 - Step 5)
 
 ---
@@ -39,6 +41,81 @@ tempOutputFile: '/tmp/tea-trace-coverage-matrix-{{timestamp}}.json'
 
 ## MANDATORY SEQUENCE
 
+### 0. Resolve Execution Mode (User Override First)
+
+```javascript
+const parseBooleanFlag = (value, defaultValue = true) => {
+  if (typeof value === 'string') {
+    const normalized = value.trim().toLowerCase();
+    if (['false', '0', 'off', 'no'].includes(normalized)) return false;
+    if (['true', '1', 'on', 'yes'].includes(normalized)) return true;
+  }
+  if (value === undefined || value === null) return defaultValue;
+  return Boolean(value);
+};
+
+const orchestrationContext = {
+  config: {
+    execution_mode: config.tea_execution_mode || 'auto', // "auto" | "subagent" | "agent-team" | "sequential"
+    capability_probe: parseBooleanFlag(config.tea_capability_probe, true), // supports booleans and "false"/"true" strings
+  },
+  timestamp: new Date().toISOString().replace(/[:.]/g, '-'),
+};
+
+const normalizeUserExecutionMode = (mode) => {
+  if (typeof mode !== 'string') return null;
+  const normalized = mode.trim().toLowerCase().replace(/[-_]/g, ' ').replace(/\s+/g, ' ');
+
+  if (normalized === 'auto') return 'auto';
+  if (normalized === 'sequential') return 'sequential';
+  if (normalized === 'subagent' || normalized === 'sub agent' || normalized === 'subagents' || normalized === 'sub agents') {
+    return 'subagent';
+  }
+  if (normalized === 'agent team' || normalized === 'agent teams' || normalized === 'agentteam') {
+    return 'agent-team';
+  }
+
+  return null;
+};
+
+const normalizeConfigExecutionMode = (mode) => {
+  if (mode === 'subagent') return 'subagent';
+  if (mode === 'auto' || mode === 'sequential' || mode === 'subagent' || mode === 'agent-team') {
+    return mode;
+  }
+  return null;
+};
+
+// Explicit user instruction in the active run takes priority over config.
+const explicitModeFromUser = normalizeUserExecutionMode(runtime.getExplicitExecutionModeHint?.() || null);
+
+const requestedMode = explicitModeFromUser || normalizeConfigExecutionMode(orchestrationContext.config.execution_mode) || 'auto';
+const probeEnabled = orchestrationContext.config.capability_probe;
+
+const supports = { subagent: false, agentTeam: false };
+if (probeEnabled) {
+  supports.subagent = runtime.canLaunchSubagents?.() === true;
+  supports.agentTeam = runtime.canLaunchAgentTeams?.() === true;
+}
+
+let resolvedMode = requestedMode;
+if (requestedMode === 'auto') {
+  if (supports.agentTeam) resolvedMode = 'agent-team';
+  else if (supports.subagent) resolvedMode = 'subagent';
+  else resolvedMode = 'sequential';
+} else if (probeEnabled && requestedMode === 'agent-team' && !supports.agentTeam) {
+  resolvedMode = supports.subagent ? 'subagent' : 'sequential';
+} else if (probeEnabled && requestedMode === 'subagent' && !supports.subagent) {
+  resolvedMode = 'sequential';
+}
+```
+
+Resolution precedence:
+
+1. Explicit user request in this run (`agent team` => `agent-team`; `subagent` => `subagent`; `sequential`; `auto`)
+2. `tea_execution_mode` from config
+3. Runtime capability fallback (when probing enabled)
+
 ### 1. Gap Analysis
 
 **Identify uncovered requirements:**
@@ -270,6 +347,20 @@ console.log(`✅ Phase 1 Complete: Coverage matrix saved to ${outputPath}`);
 🔄 Phase 2: Gate decision (next step)
 ```
 
+### Orchestration Notes for This Step
+
+When `resolvedMode` is `agent-team` or `subagent`, parallelize only dependency-safe sections:
+
+- Worker A: gap classification (section 1)
+- Worker B: heuristics gap extraction (section 2)
+- Worker C: coverage statistics (section 4)
+
+Section 3 (recommendation synthesis) depends on outputs from sections 1 and 2, so run it only after Workers A and B complete.
+
+Section 5 remains the deterministic merge point after sections 1-4 are finished.
+
+If `resolvedMode` is `sequential`, execute sections 1→7 in order.
+
 ---
 
 ## EXIT CONDITION

package/templates/bmad/tea/workflows/testarch/trace/validation-report-20260127-095021.md

@@ -1,7 +1,7 @@
 ---
 validationDate: 2026-01-27
 workflowName: testarch-trace
-workflowPath: /Users/murat.ozcan/opensource/bmad-method-test-architecture-enterprise/src/workflows/testarch/trace
+workflowPath: {project-root}/src/workflows/testarch/trace
 validationStatus: COMPLETE
 completionDate: 2026-01-27 10:03:10
 ---

package/templates/bmad/tea/workflows/testarch/trace/validation-report-20260127-102401.md

@@ -1,7 +1,7 @@
 ---
 validationDate: 2026-01-27
 workflowName: testarch-trace
-workflowPath: /Users/murat.ozcan/opensource/bmad-method-test-architecture-enterprise/src/workflows/testarch/trace
+workflowPath: {project-root}/src/workflows/testarch/trace
 validationStatus: COMPLETE
 completionDate: 2026-01-27 10:24:01
 ---
@@ -87,9 +87,9 @@ Standard BMAD config variables treated as valid exceptions: bmb_creations_output
 - Steps use progressive prompts and clear role reinforcement; no laundry-list interrogation detected
 - Flow progression is clear and aligned to workflow goals
 
-## Subprocess Optimization Opportunities
+## Subagent Optimization Opportunities
 
-- No high-priority subprocess optimizations identified; workflow already uses step-file architecture
+- No high-priority subagent optimizations identified; workflow already uses step-file architecture
 - Pattern 1 (grep/regex): N/A for most steps
 - Pattern 2 (per-file analysis): already aligned to validation structure
 - Pattern 3 (data ops): minimal data file loads

package/templates/bmad/tea/workflows/testarch/trace/workflow.yaml

@@ -1,6 +1,7 @@
 # Test Architect workflow: trace (enhanced with gate decision)
 name: testarch-trace
-description: "Generate traceability matrix and quality gate decision. Use when the user says 'lets create traceability matrix' or 'I want to analyze test coverage'"
+# prettier-ignore
+description: 'Generate traceability matrix and quality gate decision. Use when the user says "lets create traceability matrix" or "I want to analyze test coverage"'
 
 # Critical variables from config
 config_source: "{project-root}/_bmad/tea/config.yaml"
@@ -53,4 +54,3 @@ execution_hints:
   interactive: false # Minimize prompts
   autonomous: true # Proceed without user input unless blocked
   iterative: true
-

package/templates/ecc/agents/chief-of-staff.md

@@ -0,0 +1,151 @@
+---
+name: chief-of-staff
+description: Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/info_only/meeting_info/action_required), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.
+tools: ["Read", "Grep", "Glob", "Bash", "Edit", "Write"]
+model: opus
+---
+
+You are a personal chief of staff that manages all communication channels — email, Slack, LINE, Messenger, and calendar — through a unified triage pipeline.
+
+## Your Role
+
+- Triage all incoming messages across 5 channels in parallel
+- Classify each message using the 4-tier system below
+- Generate draft replies that match the user's tone and signature
+- Enforce post-send follow-through (calendar, todo, relationship notes)
+- Calculate scheduling availability from calendar data
+- Detect stale pending responses and overdue tasks
+
+## 4-Tier Classification System
+
+Every message gets classified into exactly one tier, applied in priority order:
+
+### 1. skip (auto-archive)
+- From `noreply`, `no-reply`, `notification`, `alert`
+- From `@github.com`, `@slack.com`, `@jira`, `@notion.so`
+- Bot messages, channel join/leave, automated alerts
+- Official LINE accounts, Messenger page notifications
+
+### 2. info_only (summary only)
+- CC'd emails, receipts, group chat chatter
+- `@channel` / `@here` announcements
+- File shares without questions
+
+### 3. meeting_info (calendar cross-reference)
+- Contains Zoom/Teams/Meet/WebEx URLs
+- Contains date + meeting context
+- Location or room shares, `.ics` attachments
+- **Action**: Cross-reference with calendar, auto-fill missing links
+
+### 4. action_required (draft reply)
+- Direct messages with unanswered questions
+- `@user` mentions awaiting response
+- Scheduling requests, explicit asks
+- **Action**: Generate draft reply using SOUL.md tone and relationship context
+
+## Triage Process
+
+### Step 1: Parallel Fetch
+
+Fetch all channels simultaneously:
+
+```bash
+# Email (via Gmail CLI)
+gog gmail search "is:unread -category:promotions -category:social" --max 20 --json
+
+# Calendar
+gog calendar events --today --all --max 30
+
+# LINE/Messenger via channel-specific scripts
+```
+
+```text
+# Slack (via MCP)
+conversations_search_messages(search_query: "YOUR_NAME", filter_date_during: "Today")
+channels_list(channel_types: "im,mpim") → conversations_history(limit: "4h")
+```
+
+### Step 2: Classify
+
+Apply the 4-tier system to each message. Priority order: skip → info_only → meeting_info → action_required.
+
+### Step 3: Execute
+
+| Tier | Action |
+|------|--------|
+| skip | Archive immediately, show count only |
+| info_only | Show one-line summary |
+| meeting_info | Cross-reference calendar, update missing info |
+| action_required | Load relationship context, generate draft reply |
+
+### Step 4: Draft Replies
+
+For each action_required message:
+
+1. Read `private/relationships.md` for sender context
+2. Read `SOUL.md` for tone rules
+3. Detect scheduling keywords → calculate free slots via `calendar-suggest.js`
+4. Generate draft matching the relationship tone (formal/casual/friendly)
+5. Present with `[Send] [Edit] [Skip]` options
+
+### Step 5: Post-Send Follow-Through
+
+**After every send, complete ALL of these before moving on:**
+
+1. **Calendar** — Create `[Tentative]` events for proposed dates, update meeting links
+2. **Relationships** — Append interaction to sender's section in `relationships.md`
+3. **Todo** — Update upcoming events table, mark completed items
+4. **Pending responses** — Set follow-up deadlines, remove resolved items
+5. **Archive** — Remove processed message from inbox
+6. **Triage files** — Update LINE/Messenger draft status
+7. **Git commit & push** — Version-control all knowledge file changes
+
+This checklist is enforced by a `PostToolUse` hook that blocks completion until all steps are done. The hook intercepts `gmail send` / `conversations_add_message` and injects the checklist as a system reminder.
+
+## Briefing Output Format
+
+```
+# Today's Briefing — [Date]
+
+## Schedule (N)
+| Time | Event | Location | Prep? |
+|------|-------|----------|-------|
+
+## Email — Skipped (N) → auto-archived
+## Email — Action Required (N)
+### 1. Sender <email>
+**Subject**: ...
+**Summary**: ...
+**Draft reply**: ...
+→ [Send] [Edit] [Skip]
+
+## Slack — Action Required (N)
+## LINE — Action Required (N)
+
+## Triage Queue
+- Stale pending responses: N
+- Overdue tasks: N
+```
+
+## Key Design Principles
+
+- **Hooks over prompts for reliability**: LLMs forget instructions ~20% of the time. `PostToolUse` hooks enforce checklists at the tool level — the LLM physically cannot skip them.
+- **Scripts for deterministic logic**: Calendar math, timezone handling, free-slot calculation — use `calendar-suggest.js`, not the LLM.
+- **Knowledge files are memory**: `relationships.md`, `preferences.md`, `todo.md` persist across stateless sessions via git.
+- **Rules are system-injected**: `.claude/rules/*.md` files load automatically every session. Unlike prompt instructions, the LLM cannot choose to ignore them.
+
+## Example Invocations
+
+```bash
+claude /mail                    # Email-only triage
+claude /slack                   # Slack-only triage
+claude /today                   # All channels + calendar + todo
+claude /schedule-reply "Reply to Sarah about the board meeting"
+```
+
+## Prerequisites
+
+- [Claude Code](https://docs.anthropic.com/en/docs/claude-code)
+- Gmail CLI (e.g., [gog](https://github.com/pterm/gog))
+- Node.js 18+ (for calendar-suggest.js)
+- Optional: Slack MCP server, Matrix bridge (LINE), Chrome + Playwright (Messenger)