Figma Design

Codex compatibility note:

>

- Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.

- Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.

- User-question prompts mean to ask the user directly in Codex.

- Ignore Claude-specific mode-switch instructions when they appear.

- Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.

- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.

- Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.

- For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.

- If a required step/tool cannot run in this environment, stop and ask the user before adapting.

<!-- CODEX:PROJECT-REFERENCE-LOADING:START -->

Codex Project-Reference Loading (No Hooks)

Codex does not receive Claude hook-based doc injection. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Situation-based docs:

• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec/test-case planning or TC mapping: feature-docs-reference.md
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

<!-- CODEX:PROJECT-REFERENCE-LOADING:END -->

Quick Summary

Goal: Extract structured design context from Figma designs for downstream use by design-spec and planning skills.

Workflow:

1. Detect Input — Parse Figma URL, extract file key + node ID 2. Select Extraction Method — 4-level fallback chain 3. Extract Context — Design tokens, components, layout, typography 4. Output Artifact — Structured markdown for design-spec consumption

Key Rules:

Frontend/UI Context (if applicable)

When this task involves frontend or UI changes,

• Component patterns: docs/project-reference/frontend-patterns-reference.md (read directly when relevant; do not rely on hook-injected conversation text)
• Styling/BEM guide: docs/project-reference/scss-styling-guide.md
• Design system tokens: docs/project-reference/design-system/README.md

• Always try highest-fidelity method first, fallback gracefully
• Output must be consumable by design-spec and ui-wireframe-protocol
• Keep extraction under 5K tokens per design

Extraction Fallback Chain

Level 1: Official Figma MCP (Best Fidelity)

Check if MCP tools available: look for get_design_context in tool list.

If available:

1. get_design_context — structured layout, components, tokens, constraints 2. get_screenshot — visual reference image 3. get_code_connect_map — map Figma components to code components

Level 2: GLips Figma-Context-MCP (Good Fidelity)

Check if GLips MCP tools available (look for figma-context tools).

If available:

1. Extract file metadata, frame structure, component list 2. Limited to read-only operations

Level 3: Figma REST API (Manual)

If FIGMA_ACCESS_TOKEN environment variable exists:

1. Call GET /v1/files/{file_key}/nodes?ids={node_id} via bash script 2. Parse response for: component names, styles, layout properties 3. Limited — no screenshot, no Code Connect

Level 4: Screenshot + ai-multimodal (Always Available)

If no MCP and no API token:

1. Ask user via a direct user question: "Please screenshot the Figma frame and paste here" 2. Analyze via ai-multimodal skill with design extraction prompts 3. Extract: approximate colors, fonts, spacing, layout, components

Output Format

Save to team-artifacts/design-specs/{YYMMDD}-figma-extract-{slug}.md:

# Figma Design Extract: {Name}

**Source:** {Figma URL}
**Method:** {MCP Level 1 | MCP Level 2 | REST API | Screenshot}
**Date:** {YYMMDD}

## Design Tokens

| Category   | Token     | Value                |
| ---------- | --------- | -------------------- |
| Color      | Primary   | {hex}                |
| Color      | Secondary | {hex}                |
| Typography | Heading   | {font, size, weight} |
| Spacing    | Base      | {px}                 |

## Component Inventory

- **{ComponentName}** — {description}, variants: {list}

## Layout

{ASCII wireframe per ui-wireframe-protocol}

## Responsive

{Breakpoint behavior if detectable}

When to Use

• Figma URL detected in PBI, design-spec, or user prompt
• Called by design-spec when Figma URL is present
• Called by planning skill during Design Context Extraction step

When NOT to Use

• No Figma URL present — skip, proceed to design-spec directly
• Hand-drawn wireframe — use wireframe-to-spec instead
• Screenshot of existing app — use design-screenshot instead

See Also

• references/figma-mcp-setup.md — MCP server setup guide (created in Phase 09)
• .claude/skills/planning/references/figma-integration.md — integration protocol
• .claude/hooks/figma-context-extractor.cjs — URL detection hook

---

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting.

<!-- SYNC:ui-system-context -->

UI System Context — For ANY task touching .ts, .html, .scss, or .css files:

>

MUST ATTENTION READ before implementing:

>

1. docs/project-reference/frontend-patterns-reference.md — component base classes, stores, forms

2. docs/project-reference/scss-styling-guide.md — BEM methodology, SCSS variables, mixins, responsive

3. docs/project-reference/design-system/README.md — design tokens, component inventory, icons

>

Reference docs/project-config.json for project-specific paths.

<!-- /SYNC:ui-system-context -->

<!-- SYNC:critical-thinking-mindset -->

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.

Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

<!-- /SYNC:critical-thinking-mindset -->

<!-- SYNC:ai-mistake-prevention -->

AI Mistake Prevention — Failure modes to avoid on every task: Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

<!-- /SYNC:ai-mistake-prevention -->

<!-- SYNC:ui-system-context:reminder -->

IMPORTANT MUST ATTENTION read frontend-patterns-reference, scss-styling-guide, design-system/README before any UI change.

<!-- /SYNC:ui-system-context:reminder -->

<!-- SYNC:critical-thinking-mindset:reminder -->

MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

<!-- /SYNC:critical-thinking-mindset:reminder -->

<!-- SYNC:ai-mistake-prevention:reminder -->

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

<!-- /SYNC:ai-mistake-prevention:reminder -->

Closing Reminders

IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act) IMPORTANT MUST ATTENTION add a final review todo task to verify work quality MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

<!-- CODEX:SYNC-PROMPT-PROTOCOLS:START -->

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there. Any supported AI tool may execute when this shared context and local docs are available.

1. DETECT: Match prompt against workflow catalog 2. ANALYZE: Find best-match workflow AND evaluate if a custom step combination would fit better 3. ASK (REQUIRED FORMAT): Use a direct user question with this structure unless the user explicitly invoked a workflow/skill and the local protocol treats explicit invocation as confirmation:

• Question: "Which workflow do you want to activate?"
• Option 1: "Activate [BestMatch Workflow] (Recommended)"
• Option 2: "Activate custom workflow: [step1 → step2 → ...]" (include one-line rationale)

4. ACTIVATE (if confirmed): Call $workflow-start <workflowId> for standard; sequence custom steps manually 5. CREATE TASKS: task tracking for ALL workflow steps 6. EXECUTE: Follow each step in sequence [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value". 2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up. 3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase. 4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson. 5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn. 6. Auto-fix gate: "Could $code-review/$code-simplifier/$security/$lint catch this?" — Yes → improve review skill instead. 7. BOTH gates pass → ask user to run $learn. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.

<!-- CODEX:SYNC-PROMPT-PROTOCOLS:END -->

Figma MCP Setup Guide

Referenced by: figma-design skill

Option 1: Official Figma MCP (Recommended for paid Figma plans)

Remote Server (no local app needed)

Install as Claude Code plugin:

claude plugin install figma@claude-plugins-official

• Authenticates via OAuth browser flow (no API key needed)
• Works on all Figma plans: free = 6 calls/month, paid = 200-600 calls/day
• 13 tools: read, write, screenshot, Code Connect, FigJam, variables
• Bidirectional: can generate designs back into Figma

Desktop Server (requires Figma Desktop app)

• Requires Dev or Full seat on paid plan (Pro/Org/Enterprise)
• Better performance for high-volume usage
• Dev Mode required

Option 2: GLips Figma-Context-MCP (Free tier friendly)

Add to .claude/settings.json or project MCP config:

{
    "mcpServers": {
        "figma-context": {
            "command": "npx",
            "args": ["-y", "figma-context-mcp"],
            "env": {
                "FIGMA_ACCESS_TOKEN": "${FIGMA_ACCESS_TOKEN}"
            }
        }
    }
}

Generate token: Figma Settings -> Personal Access Tokens

• Read-only (no write/screenshot)
• No MCP-specific rate limits -- only standard Figma API limits
• 13.2K GitHub stars, actively maintained
• Works with free Figma accounts

Option 3: No MCP (Screenshot Fallback)

If neither MCP is configured, the figma-design skill falls back to:

1. Ask user to screenshot the Figma frame 2. Analyze via ai-multimodal skill 3. Extract approximate design context (colors, fonts, spacing, layout)

This always works but produces lower-fidelity results.

Verification

After setup, verify MCP is working:

claude mcp list

Should show figma or figma-context server in the list.

Security Note

• FIGMA_ACCESS_TOKEN should be set as an environment variable, NOT committed to git
• Add .env to .gitignore if using dotenv files