mindforge-cc 9.0.0 → 10.0.1

package/.mindforge/ci/ci-mode.md

@@ -1,179 +0,0 @@
-# MindForge CI Mode
-
-## Purpose
-Enable MindForge to run in non-interactive CI/CD environments.
-CI mode is fully automated — no user prompts, no interactive approvals,
-no waiting for human input. All decisions are pre-configured.
-
-## Activating CI mode
-
-CI mode activates automatically when:
-1. `CI=true` environment variable is set (standard in GitHub Actions, GitLab CI, Jenkins)
-2. `MINDFORGE_CI=true` is explicitly set
-3. `process.stdin.isTTY === false` (piped or non-interactive shell)
-
-In CI mode:
-- All interactive prompts are skipped — pre-configured answers are used
-- Approval workflows use the CI approval policy (see below)
-- Progress output is structured JSON (parseable by CI log processors)
-- Exit codes communicate status (0 = success, 1 = failure)
-- Slack/GitHub notifications are sent as configured (integrations still work)
-
-## CI mode configuration
-
-Add to `MINDFORGE.md` for CI-specific settings:
-
-```
-## CI/CD configuration
-
-# Which phases to execute in CI (comma-separated phase numbers, or "all")
-CI_EXECUTE_PHASES=all
-
-# Auto-approve Tier 2 changes in CI (default: false — safer)
-CI_AUTO_APPROVE_TIER2=false
-
-# Block CI on MEDIUM security findings (default: false)
-CI_BLOCK_ON_MEDIUM_SECURITY=false
-
-# Run full security scan in CI (default: true)
-CI_SECURITY_SCAN=true
-
-# Skip human UAT in CI — only run automated verification (default: true)
-CI_SKIP_UAT=true
-
-# Fail CI if test coverage drops below this threshold
-CI_MIN_COVERAGE_PCT=80
-
-# Timeout for entire CI run in minutes (default: 60)
-CI_TIMEOUT_MINUTES=60
-
-# Output format for CI logs: json | text | github-annotations
-CI_OUTPUT_FORMAT=github-annotations
-```
-
-## CI approval policy
-
-Tier 1: always auto-approved (same as interactive mode)
-Tier 2: auto-approved IF `CI_AUTO_APPROVE_TIER2=true` in MINDFORGE.md
-         rejected (build fails) IF `CI_AUTO_APPROVE_TIER2=false`
-Tier 3: ALWAYS fails the build in CI — Tier 3 changes require human review.
-
-The CI build should never be the first time a Tier 3 change is seen.
-Engineers should get Tier 3 changes approved BEFORE pushing to CI.
-
-## CI output format
-
-### JSON format (`CI_OUTPUT_FORMAT=json`)
-```json
-{
-  "mindforge_version": "0.6.0",
-  "phase": 3,
-  "status": "running | success | failure | warning",
-  "timestamp": "ISO-8601",
-  "tasks_completed": 5,
-  "tasks_total": 8,
-  "current_task": "Plan 3-06: Implement auth middleware",
-  "gates": {
-    "secrets_clean": true,
-    "tests_passing": true,
-    "security_findings_critical": 0,
-    "security_findings_high": 0,
-    "coverage_pct": 84
-  },
-  "events": [
-    { "time": "ISO-8601", "type": "task_completed", "plan": "3-01", "commit": "abc1234" },
-    { "time": "ISO-8601", "type": "security_finding", "severity": "MEDIUM", "finding": "..." }
-  ]
-}
-```
-
-### GitHub Annotations format (`CI_OUTPUT_FORMAT=github-annotations`)
-```
-::group::MindForge Phase 3 Execution
-::notice::Task 3-01 completed: Create auth middleware [abc1234]
-::notice::Task 3-02 completed: Add JWT validation [def5678]
-::warning file=src/auth/session.ts,line=47::Medium security finding: Verbose error message exposes stack trace
-::notice::Phase 3 complete: 8/8 tasks, all tests passing
-::endgroup::
-```
-
-### Error output
-```
-::error::MindForge CI failed: Task 3-06 verify step failed
-::error file=src/api/users.ts,line=89::TypeScript error: Type 'string' is not assignable to 'number'
-::error::Quality gate failed: test coverage 68% (minimum: 80%)
-```
-
-## CI environment requirements
-
-```bash
-# Required environment variables for full CI functionality:
-ANTHROPIC_API_KEY=     # Claude API access (required for AI features)
-GITHUB_TOKEN=          # For PR creation and status checks
-JIRA_API_TOKEN=        # Optional — for Jira sync
-SLACK_BOT_TOKEN=       # Optional — for notifications
-```
-
-## CI timeout and exit codes
-
-**Exit code policy:**
-| Situation | Exit code | Meaning |
-|---|---|---|
-| All phases complete, gates passed | 0 | Success |
-| Quality gate failed | 1 | Hard failure — fix required |
-| Tier 2/3 governance block | 1 | Hard failure — approval required |
-| CI timeout reached | 0 | Soft stop — work saved, resume next run |
-| No MindForge project found | 1 | Configuration error |
-
-**Important:** GitHub Actions (and most CI systems) treat ANY non-zero exit code
-as failure. Exit code 2 does NOT mean "warning" in CI — it means failure.
-
-**Timeout handling (exit 0 with state preservation):**
-```bash
-# Set up timeout trap
-CI_TIMEOUT_SECONDS=$((${CI_TIMEOUT_MINUTES:-60} * 60))
-timeout_handler() {
-  echo "::warning::MindForge CI timeout reached after ${CI_TIMEOUT_MINUTES} minutes"
-  echo "::warning::Progress saved. Next CI run will resume from: $(cat .planning/HANDOFF.json | python3 -c 'import sys,json; print(json.load(sys.stdin).get("next_task","unknown"))')"
-
-  # Write resume info to GitHub Actions step summary
-  cat >> "${GITHUB_STEP_SUMMARY:-/dev/null}" << 'SUMMARY_EOF'
-## ⏱️ MindForge CI Timeout
-
-CI timeout reached. Progress has been saved.
-
-Next run will resume from:
-$(cat .planning/HANDOFF.json | python3 -c 'import sys,json; d=json.load(sys.stdin); print(d.get("next_task","unknown"))')
-
-Run the CI pipeline again to continue.
-SUMMARY_EOF
-
-  # Commit HANDOFF.json so next run can resume
-  git add .planning/HANDOFF.json .planning/STATE.md
-  git commit -m "ci: save MindForge progress on timeout [skip ci]" || true
-  git push origin HEAD || true
-
-  exit 0  # Exit 0 — timeout is not a failure
-}
-
-trap 'timeout_handler' TERM
-(sleep "${CI_TIMEOUT_SECONDS}"; kill -TERM $$) &
-TIMEOUT_PID=$!
-```
-
-## CI timeout and resource management
-
-```
-Default execution limits per CI run:
-  Maximum tasks per session: 25
-  Maximum parallel subagents: 5 (respect CI runner memory limits)
-  Task timeout: 10 minutes per task
-  Phase timeout: 45 minutes
-  Full CI timeout: 60 minutes
-
-On timeout:
-  1. Write current state to HANDOFF.json
-  2. Exit with code 0 (soft stop)
-  3. The next CI run resumes from HANDOFF.json
-  4. Report: "CI timeout reached. Run will resume from: [next_task]"
-```

package/.mindforge/ci/github-actions-adapter.md

@@ -1,224 +0,0 @@
-# MindForge — GitHub Actions Integration
-
-## Purpose
-Define the GitHub Actions workflow that integrates MindForge into CI/CD pipelines.
-
-## Workflow file: `.github/workflows/mindforge-ci.yml`
-
-```yaml
-name: MindForge CI
-
-on:
-  push:
-    branches: [ main, 'feat/**' ]
-  pull_request:
-    branches: [ main ]
-
-env:
-  CI: true
-  MINDFORGE_CI: true
-  NODE_VERSION: '20'
-
-jobs:
-  mindforge-health:
-    name: MindForge Health Check
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0   # Full history for git-based checks
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-          cache: 'npm'
-
-      - name: Install MindForge
-        run: npx mindforge-cc@latest --claude --local
-
-      - name: Validate MINDFORGE.md
-        run: node bin/validate-config.js
-
-      - name: Run MindForge health check
-        run: |
-          # Health check in CI mode — outputs structured JSON
-          echo "::group::MindForge Health Report"
-          node -e "
-            // CI health check simulation
-            // In full implementation: calls mindforge health engine
-            const fs = require('fs');
-            const files = ['.planning/AUDIT.jsonl', '.planning/STATE.md', '.planning/HANDOFF.json'];
-            let allPresent = true;
-            files.forEach(f => {
-              if (!fs.existsSync(f)) {
-                console.log('::warning::Missing state file: ' + f);
-                allPresent = false;
-              }
-            });
-            console.log(allPresent ? '::notice::All state files present' : '::warning::Some state files missing');
-          "
-          echo "::endgroup::"
-
-  mindforge-security:
-    name: Security Scan
-    runs-on: ubuntu-latest
-    needs: mindforge-health
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-          cache: 'npm'
-
-      - name: Install dependencies
-        run: npm ci
-
-      - name: MindForge secret detection
-        run: |
-          echo "::group::Secret Detection"
-          # Secret patterns — exits non-zero if found
-          if grep -rE "(sk-[a-zA-Z0-9]{20,}|ghp_[a-zA-Z0-9]+|xoxb-[a-zA-Z0-9-]+)" \
-            --include="*.ts" --include="*.js" --include="*.json" \
-            --exclude-dir=node_modules --exclude-dir=.git \
-            . 2>/dev/null; then
-            echo "::error::Credentials detected in source files. Remove before merging."
-            exit 1
-          fi
-          echo "::notice::No credentials detected ✅"
-          echo "::endgroup::"
-
-      - name: Dependency audit
-        run: |
-          echo "::group::Dependency Audit"
-          npm audit --audit-level=high 2>&1 || {
-            echo "::error::High/critical vulnerabilities found. Run: npm audit fix"
-            exit 1
-          }
-          echo "::endgroup::"
-
-  mindforge-quality:
-    name: Code Quality Gates
-    runs-on: ubuntu-latest
-    needs: mindforge-health
-    env:
-      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-          cache: 'npm'
-
-      - name: Install dependencies
-        run: npm ci
-
-      - name: Type check
-        run: npx tsc --noEmit 2>&1 | while read line; do
-          echo "::error::$line"
-          done
-
-      - name: Lint
-        run: npx eslint . --ext .ts,.tsx --max-warnings 0
-
-      - name: Test suite with coverage
-        run: npm test -- --coverage
-        env:
-          COVERAGE_THRESHOLD: 80
-
-      - name: Check coverage threshold
-        run: |
-          COVERAGE=$(cat coverage/coverage-summary.json 2>/dev/null | \
-            node -e "const d=JSON.parse(require('fs').readFileSync('/dev/stdin','utf8')); \
-            console.log(Math.floor(d.total.lines.pct))" 2>/dev/null || echo "0")
-          MIN=${CI_MIN_COVERAGE_PCT:-80}
-          if [ "${COVERAGE}" -lt "${MIN}" ]; then
-            echo "::error::Coverage ${COVERAGE}% is below minimum ${MIN}%"
-            exit 1
-          fi
-          echo "::notice::Coverage: ${COVERAGE}% ✅"
-
-      - name: Check governance tier (Tier 3 blocks CI)
-        run: |
-          # Check if any pending Tier 3 approvals exist without approval
-          PENDING_T3=$(find .planning/approvals/ -name "*.json" 2>/dev/null | \
-            xargs grep -l '"tier": 3' 2>/dev/null | \
-            xargs grep -l '"status": "pending"' 2>/dev/null | wc -l)
-
-          if [ "${PENDING_T3}" -gt 0 ]; then
-            echo "::error title=Tier 3 Governance Block::${PENDING_T3} Tier 3 change(s) require compliance review."
-            echo "::error::Tier 3 changes (auth/payment/PII) cannot be auto-approved in CI."
-            echo "::error::To resolve: get human approval with /mindforge:approve [id], then push again."
-            cat >> "${GITHUB_STEP_SUMMARY}" << 'SUMMARY_EOF'
-## 🔴 Governance Block: Tier 3 Approval Required
-
-This PR contains changes that require compliance review (auth, payment, or PII handling).
-
-**Next steps:**
-1. Run `/mindforge:approve` to see pending approval requests
-2. Have your compliance officer approve with `/mindforge:approve [id]`
-3. Push again — CI will pass once the approval is recorded
-
-See `.planning/approvals/` for details.
-SUMMARY_EOF
-            exit 1
-          fi
-
-          echo "::notice::Governance check passed — no pending Tier 3 blocks ✅"
-
-  mindforge-ai-review:
-    name: AI Code Review
-    runs-on: ubuntu-latest
-    needs: [mindforge-security, mindforge-quality]
-    if: github.event_name == 'pull_request'
-    env:
-      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-      GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: ${{ env.NODE_VERSION }}
-          cache: 'npm'
-
-      - name: Install MindForge
-        run: npx mindforge-cc@latest --claude --local
-
-      - name: Run AI PR Review
-        run: |
-          if [ -z "${ANTHROPIC_API_KEY}" ]; then
-            echo "::notice::ANTHROPIC_API_KEY not set — skipping AI review"
-            exit 0
-          fi
-
-          # Get the diff for this PR
-          git diff ${{ github.event.pull_request.base.sha }}...${{ github.event.pull_request.head.sha }} > /tmp/pr.diff
-
-          # Run MindForge AI review (outputs GitHub annotations)
-          node -e "
-            // Placeholder for AI review execution
-            // In full implementation: calls Claude API via the pr-review engine
-            console.log('::notice::AI PR review completed — see review comment on PR');
-          "
-
-      - name: Post review as PR comment
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const fs = require('fs');
-            const review = fs.existsSync('/tmp/mindforge-review.md') ?
-              fs.readFileSync('/tmp/mindforge-review.md', 'utf8') :
-              '✅ MindForge AI review: no significant issues found.';
-
-            await github.rest.pulls.createReview({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              pull_number: context.issue.number,
-              body: review,
-              event: 'COMMENT'
-            });
-```

package/.mindforge/ci/gitlab-ci-adapter.md

@@ -1,31 +0,0 @@
-# MindForge — GitLab CI Integration
-
-## Purpose
-Define a GitLab CI template that runs MindForge in CI mode.
-
-## Example `.gitlab-ci.yml`
-
-```yaml
-stages:
-  - mindforge
-
-mindforge:
-  stage: mindforge
-  image: node:20
-  variables:
-    CI: "true"
-    MINDFORGE_CI: "true"
-  script:
-    - npx mindforge-cc@latest --claude --local
-    - node bin/validate-config.js
-    - node tests/ci-mode.test.js
-  artifacts:
-    when: always
-    paths:
-      - .planning/HANDOFF.json
-      - .planning/STATE.md
-```
-
-## Notes
-- Add secrets (ANTHROPIC_API_KEY, SLACK_BOT_TOKEN, etc.) to GitLab CI variables.
-- If CI times out, MindForge exits 0 and preserves HANDOFF.json for the next run.

package/.mindforge/ci/jenkins-adapter.md

@@ -1,44 +0,0 @@
-# MindForge — Jenkins Integration
-
-## Purpose
-Provide a Jenkins pipeline snippet for MindForge CI mode.
-
-## Example Jenkinsfile
-
-```groovy
-pipeline {
-  agent any
-  environment {
-    CI = 'true'
-    MINDFORGE_CI = 'true'
-    ANTHROPIC_API_KEY = credentials('anthropic-api-key')
-  }
-  stages {
-    stage('Install') {
-      steps {
-        sh 'npm ci'
-        sh 'npx mindforge-cc@latest --claude --local'
-      }
-    }
-    stage('Validate') {
-      steps {
-        sh 'node bin/validate-config.js'
-      }
-    }
-    stage('MindForge CI') {
-      steps {
-        sh 'node tests/ci-mode.test.js'
-      }
-    }
-  }
-  post {
-    always {
-      archiveArtifacts artifacts: '.planning/HANDOFF.json,.planning/STATE.md', fingerprint: true
-    }
-  }
-}
-```
-
-## Notes
-- Jenkins treats any non-zero exit code as failure, so timeouts should exit 0.
-- Use Jenkins credentials store for API keys.

package/.mindforge/dashboard/api-reference.md

@@ -1,122 +0,0 @@
-# MindForge Dashboard API Reference
-
-## Base URL: http://localhost:7339
-
-## GET /api/status
-Current execution state.
-```json
-{
-  "project_name": "saas-app",
-  "phase": 3,
-  "phase_description": "Authentication System",
-  "auto_mode": true,
-  "auto_status": "running|paused|escalated|idle",
-  "current_task": "Plan 3-05 — JWT middleware",
-  "wave_current": 2,
-  "wave_total": 3,
-  "tasks_completed": 5,
-  "tasks_total": 8,
-  "elapsed_ms": 1083000,
-  "node_repairs": 1,
-  "escalations": 0,
-  "last_commit": "abc1234",
-  "last_event_at": "ISO-8601"
-}
-```
-
-## GET /api/audit?limit=50&offset=0&event=task_completed
-Recent AUDIT.jsonl entries (newest first).
-Query params: limit (default 50, max 200), offset, event (filter by event type)
-
-## GET /api/metrics
-Session quality and cost summary.
-```json
-{
-  "sessions": [{ "id": "...", "quality_score": 0.87, "cost_usd": 0.42, "verify_pass_rate": 0.95 }],
-  "avg_quality": 0.85,
-  "avg_cost_usd": 0.38,
-  "security_findings": { "CRITICAL": 0, "HIGH": 2, "MEDIUM": 5, "LOW": 8 },
-  "node_repair_rate": 0.08
-}
-```
-
-## GET /api/approvals
-Pending governance approvals.
-```json
-{
-  "pending": [
-    {
-      "id": "uuid",
-      "tier": 2,
-      "phase": 3,
-      "plan": "04",
-      "description": "Add user RBAC model",
-      "requested_at": "ISO-8601",
-      "expires_at": "ISO-8601",
-      "hours_remaining": 21.3,
-      "diff_preview": "src/models/user.ts +48 lines..."
-    }
-  ],
-  "approved": [...],
-  "rejected": [...],
-  "expired": [...]
-}
-```
-
-## POST /api/approve/:id
-```json
-Request:  { "decision": "approve|reject", "comment": "optional", "approver": "email" }
-Response: { "success": true, "decision": "approve", "approval_id": "uuid" }
-```
-
-## GET /api/team
-Active developer activity.
-```json
-{
-  "active": [
-    { "email": "john@company.com", "current_task": "Plan 3-05", "last_seen_mins": 0 }
-  ],
-  "conflicts": [
-    { "file": "src/auth/session.ts", "developers": ["john@...", "jane@..."] }
-  ]
-}
-```
-
-## GET /api/memory?q=jwt&limit=10
-Knowledge base query.
-```json
-{
-  "entries": [
-    { "id": "kb-uuid", "type": "architectural_decision", "topic": "JWT tokens", "confidence": 0.90 }
-  ],
-  "total": 47
-}
-```
-
-## GET /api/costs?window=7d
-Cost summary from token-usage.jsonl.
-```json
-{
-  "total_usd": 3.84,
-  "today_usd": 1.21,
-  "by_model": { "claude-sonnet-4-6": 1.92, "gpt-4o": 0.98 },
-  "daily_limit_usd": 10.00,
-  "limit_used_pct": 12.1
-}
-```
-
-## POST /api/steer
-Inject steering guidance (requires auto mode running).
-```json
-Request:  { "instruction": "Use Redis for session storage", "priority": "normal" }
-Response: { "success": true, "queued": true }
-```
-
-## GET /events
-SSE stream. Events emitted:
-- `audit:new` — new AUDIT.jsonl entry
-- `status:update` — auto-state.json changed
-- `approval:new` — new approval request
-- `approval:resolved` — approval approved or rejected
-- `conflict:detected` — two developers touching same file
-- `ping` — keepalive every 15 seconds

package/.mindforge/dashboard/dashboard-spec.md

@@ -1,96 +0,0 @@
-# MindForge v2 — Dashboard Specification
-
-## Overview
-
-The MindForge dashboard is a real-time web UI that reflects the live state of
-the MindForge agent and all project artifacts. It serves as the team's window
-into what the agent is doing — designed for standup visibility, not agent control
-(though it does support approval actions for Tier 2/3 governance).
-
-## Architecture
-
-```
-Browser clients
-     ↑ SSE (push)     ↑ REST (pull on load)
-     │                │
-  bin/dashboard/server.js  (Express.js, localhost:7339)
-     │                │
-  sse-bridge.js       api-router.js
-     │ (tails files)  │ (reads files)
-     │                │
-  AUDIT.jsonl         HANDOFF.json
-  auto-state.json     session-quality.jsonl
-  APPROVAL-*.json     token-usage.jsonl
-  HANDOFF.json        knowledge-base.jsonl
-  TEAM-STATE.jsonl    .planning/phases/
-```
-
-## Port and binding
-
-- **Port:** 7339 (Dashboard = 7337+2, after SSE at 7337 and Browser Daemon at 7338)
-- **Binding:** 127.0.0.1 ONLY — never 0.0.0.0 (ADR-017 policy)
-- **Protocol:** HTTP/1.1 with SSE for live events
-- **Process lifecycle:**
-  - Started by: `/mindforge:dashboard` command or `bin/dashboard/server.js`
-  - Stopped by: `CTRL+C`, `/mindforge:dashboard --stop`, or SIGTERM
-  - Auto-stop: when MindForge session ends (watches for HANDOFF.json inactivity)
-
-## Dashboard pages (5 tabs)
-
-### Page 1 — Live Activity (default view)
-Shows real-time execution state:
-- Project name and current phase description
-- Auto mode status indicator (RUNNING/PAUSED/ESCALATED/IDLE)
-- Wave progress bar (current wave / total waves)
-- Current task name and elapsed time
-- Live AUDIT event feed (last 50 events, newest at top)
-- Steering input box (sends to steering queue if auto mode active)
-
-### Page 2 — Quality Metrics
-Charts powered by session-quality.jsonl and token-usage.jsonl:
-- Session quality score trend (last 20 sessions, sparkline)
-- Verify pass rate over time (last 20 sessions)
-- Security findings by severity (bar chart: CRITICAL/HIGH/MEDIUM/LOW)
-- Token cost per session trend
-- Node repair frequency (auto mode health signal)
-
-### Page 3 — Pending Approvals
-Governance queue visible to the whole team:
-- Shows all APPROVAL-*.json files with status: pending
-- For each: tier, phase/plan, change description, time since requested, expiry
-- [Approve] and [Reject] buttons that call POST /api/approve/:id
-- Expired approvals shown separately with red indicator
-
-### Page 4 — Knowledge Graph
-Visual representation of the knowledge base:
-- Force-directed graph: nodes = knowledge entries, edges = ADR links
-- Color by type: blue=decision, green=preference, red=bug_pattern, yellow=domain
-- Node size = confidence × 30px radius
-- Click node → side panel with full content
-- Filter by type, tags, or confidence threshold
-
-### Page 5 — Team Activity
-Multi-developer visibility:
-- Active developers (git email → last AUDIT event timestamp)
-- What each developer is working on (last task from AUDIT.jsonl)
-- File conflict detection (two developers recently touching the same file)
-- Session history (list of sessions, quality scores, costs)
-
-## Security model
-
-1. Localhost-only binding (127.0.0.1) — consistent with all MindForge servers
-2. No authentication — local dev tool, not exposed to network
-3. CORS policy: only allow requests from localhost
-4. Approval actions (POST /api/approve/:id) require the approval file to exist
-   in `.planning/approvals/` — cannot fabricate approvals from browser
-5. Steering (POST /api/steer) only works when auto-state.json shows `status: running`
-6. All file reads are restricted to `.planning/` and `.mindforge/` directories —
-   no arbitrary filesystem access from the API
-
-## SCREENSHARE MODE (recommended team use)
-The dashboard is designed to be screenshared during standups:
-- Product managers see live progress without CLI access
-- Designers see when their UI implementation tasks are running
-- Stakeholders see real estimates of completion time
-- On-call engineers see security findings as they're detected
-Never expose the dashboard URL externally — it contains project details.