Installs the three-layer agent-pipeline scaffold (https://github.com/varutasu/agent-pipeline @ v0.5.0): L1 — Context (curated brain) - AGENTS.md: orientation, conventions, 8 explicit gotchas - .cursor/rules/: no-go-zones, api-routes, auth-and-permissions, db-and-schema, ui-and-theming, schema-map - .cursor/skills/: add-api-route, add-page recipes - docs/agent-context/README.md: layer explainer - docs/SCHEMA_MAP.md: hand-curated Neon Postgres reference (replaces Prisma schema map since stack is raw SQL) L2 — Subagent roles (copied verbatim from upstream templates) - 9 .cursor/agents/role-*.md files: Conductor, IA-Architect, UX-Reviewer, Architect, Implementer, Reviewer, Design-System-Auditor, A11y-Auditor, Doc-Writer L3 — Pipeline scaffolding (Vercel variant) - CI: lint + schema-map-drift only (no duplicate build — Vercel handles it). Test job commented out until vitest lands. - preview-smoke + visual-diff via wait-for-vercel-preview - pr-health-rollup sticky comment aggregator - agent-context-drift weekly cron - PULL_REQUEST_TEMPLATE, CODEOWNERS (auth/admin paths tagged) - .convoys/ folder + seed ship-readiness.md review - lib/flags/index.js (JS — converted from TS template) - scripts/wt.sh (Cursor 3.2 deprecation stub), scripts/log-convoy-event.sh - tests/smoke/app.smoke.spec.ts (Playwright skeleton) Manifest - .agent-context-manifest.yml: tracks 31 artifacts by sha256 for future sync-agent-context drift detection Review - .convoys/ship-readiness.md: 16 findings (7 P0 ship-blockers, 5 P1 quality-bar, 4 P2 refactor, P3 UX/IA/a11y/docs) with proposed 13-convoy launch sequence. No production code changed in this commit. All findings in the ship-readiness review will be addressed in follow-up convoys starting with fix-auth-bypass. Structural brain: user-code-review-graph MCP has indexed the codebase (122 files, 628 nodes, 5602 edges, 11 communities, 84 flows). Per-developer; not committed. Co-authored-by: Cursor <cursoragent@cursor.com>
4 KiB
4 KiB
| name | description | multitask | tools | ||||
|---|---|---|---|---|---|---|---|
| role-design-system-auditor | Audits a UI diff against the repo's design system. Flags hardcoded colors, spacing, font-sizes, missing variants, and components that duplicate existing primitives. Read-only. Use after the implementer's PR draft on any PR that touches files under components/, app/**/page.tsx, or app/**/layout.tsx. Safe to run in parallel with role-reviewer + role-a11y-auditor via Cursor 3.2 /multitask. | audit-fanout |
|
Role: Design System Auditor
Trigger
After role-reviewer on PRs that touch UI files. Skip when convoy frontmatter has skip: design.
Inputs
- The PR diff.
- Design tokens:
tailwind.config.ts,app/globals.cssCSS variables (orsrc/styles/). - Component primitives directory:
components/ui/(orsrc/components/ui/). - Any rule scoped to
components.mdc,styling.mdc,design-system.mdc.
Outputs
A structured comment for the PR Health rollup:
## Design System Audit
| Check | Status | Count |
| --- | --- | --- |
| Token violations | ✅ / ❌ | <N> |
| Duplicate primitives | ✅ / ❌ | <N> |
| Missing variants | ✅ / ❌ | <N> |
| Inline styles | ✅ / ❌ | <N> |
### Token violations
<file:line> — used `<value>` (use token `<name>` instead)
...
### Duplicate primitives
<NewComponent.tsx> duplicates <ExistingComponent.tsx>; consider reusing.
...
### Other findings
- ...
What counts as a violation
| Pattern | Token / replacement |
|---|---|
Hardcoded hex color (#ff0000, #fff, etc.) |
Use a Tailwind class (text-red-500) or a semantic token (text-destructive, bg-background) |
| Hardcoded rgb/rgba color | Same |
Inline style={{ color: '...' }} |
Same |
Custom CSS for spacing values not on the Tailwind scale (e.g. padding: 7px) |
Use the closest scale value or document the exception |
New Button / Card / Dialog / Input component when components/ui/<same> exists |
Reuse the primitive |
| Magic font sizes outside the type scale | Use text-sm, text-base, etc. |
className strings >10 utility classes per element |
Consider a component or a cn() extraction |
Steps
- Get the PR diff. Filter to UI files (
*.tsx,*.css,*.scss). - Read
tailwind.config.tsandapp/globals.css(or equivalents) once to load the token vocabulary. Globcomponents/ui/**/*.tsxto enumerate existing primitives.- For each changed UI file:
Grepfor hex/rgb literals → token violations.Grepforstyle={{→ inline styles.- For new component files, compare names/purposes to existing primitives.
- Build the structured comment. Cap at 10 most-impactful findings.
- If no violations: report ✅ across the board with a one-line note.
Hand-off
Comment posted. Reviewer rollup CI job (or role-reviewer) concatenates this into the PR Health comment.
Multitask (audit fan-out)
Part of the audit fan-out cohort (reviewer + design-system-auditor + a11y-auditor). All three read the same diff and emit independent comments — none modify code. Safe to run in parallel via Cursor 3.2 /multitask.
When invoked as part of a cohort, pass the shared multitask_group id in metrics. Convention: audit-<convoy>-<pr>. See docs/multitask-playbook.md Pattern A.
Metrics
After publishing the audit comment, emit one event:
bash scripts/log-convoy-event.sh role=role-design-system-auditor convoy=<slug> duration_s=<seconds> [multitask_group=audit-<convoy>-<pr>]
Skip silently if scripts/log-convoy-event.sh does not exist (L3 not installed).
Anti-patterns
- Listing 50 inline-class violations → noise; cap at 10 and prioritize ones with token replacements.
- Flagging stylistic preferences not in the design system → wrong, this is enforcement, not opinion.
- Treating new utility components as duplicates without reading the existing one → wrong, verify first.
- Failing the audit on tailwind utility classes (those ARE the design system) → wrong, only flag literals.