` tag - Viewport meta tag - CSS link or inline styles - JavaScript reference - Closing `</html>` tag **Exit codes:** - 0 = HTML structure valid - 1 = Structural issues found --- ### `tools/check/js-syntax.sh` **Purpose:** Check JavaScript syntax using Node.js. ```bash tools/check/js-syntax.sh <site-dir> tools/check/js-syntax.sh sites/example.com-v1 ``` **Actions:** - Finds all .js files in site directory (maxdepth 2) - Runs `node -c` on each file to check syntax - Reports pass/fail for each file **Exit codes:** - 0 = All JavaScript files valid - 1 = Syntax errors found --- ### `tools/check/file-stats.sh` **Purpose:** Show file statistics for a site directory. ```bash tools/check/file-stats.sh <site-dir> tools/check/file-stats.sh sites/example.com-v1 ``` **Output:** - Line counts and file sizes for HTML, CSS, JS files - Total lines and KB **Example:** ``` HTML: index.html 150 lines 5.2 KB CSS: styles.css 200 lines 4.1 KB JavaScript: script.js 100 lines 3.0 KB --- TOTAL: 450 lines, 12.3 KB ``` --- ### `tools/check/design-compliance.sh` **Purpose:** Check implementation compliance against DESIGN.md specifications. ```bash tools/check/design-compliance.sh <site-dir> tools/check/design-compliance.sh sites/example.com-v1 ``` **Checks:** 1. **Color Palette** — Verifies hex colors from DESIGN.md appear in CSS 2. **Typography** — Checks specified fonts are used 3. **CSS Animations** — Counts @keyframes and transitions 4. **Performance Patterns** — Checks for will-change, transforms, requestAnimationFrame, etc. 5. **JavaScript Features** — Counts classes, functions, event listeners 6. **Accessibility** — ARIA attributes, focus styles, keyboard handling 7. **External Dependencies** — External scripts, images, fonts **Output:** - Pass/Warn/Fail counts per category - Summary: FULL COMPLIANCE, PARTIAL COMPLIANCE, or COMPLIANCE ISSUES FOUND **Exit codes:** - 0 = No failures (may have warnings) - 1 = Compliance issues found --- ## Prohibited vs Alternatives | ❌ Prohibited | ✅ Use Instead | |--------------|----------------| | `cat/less/head/tail` file inspection | `uv run python3.12 tools/implement/check-outputs.py <site-dir>` or `tools/implement/status.sh <BATCH>` | | `ls/find/wc/globs` directory listing | `uv run python3.12 tools/design/check-dirs.py --batch-id <ID> --root .` or `tools/check/file-stats.sh <site-dir>` | | `grep "pattern"` searching | `tools/implement/status.sh <BATCH>` | | `for f in *.html; do` loops | `uv run python3.12 tools/implement/run.py --batch <ID>` (handles queue) | | `mkdir -p` directory creation | `uv run python3.12 tools/implement/generate.py <DESIGN.md>` or `tools/prepare/batch.sh` | | `python3 script.py` | `uv run python3.12 tools/.../<script>.py` | | `cat <<EOF` HEREDOC | Write tool or Filesystem MCP | | Creating new scripts | Use existing assist scripts only | | Manual HTML validation | `tools/check/html-check.sh <site-dir>` or `tools/check/verify-site.sh <site-dir>` | | Manual JS validation | `tools/check/js-syntax.sh <site-dir>` | | Manual compliance check | `tools/check/design-compliance.sh <site-dir>` | --- ## Required Outputs - `index.html` matching Design.md layout and tone - `styles.css` implementing palette/typography/motifs - `script.js` for interactions; ensure no console errors - `assets/` for required media/SVGs - No placeholders: deliver complete, production-ready files (LLM coding tools own the final content). --- ## Steps for LLM > **Note:** General Rules (G1-G4) and Claude Code Rules (C1-C5) apply to ALL steps below. ### Step 1: Pick Batch (Main Agent) Execute: Read REGISTRY Tool: Read Path: .smbatcher/REGISTRY.md Background: - If batch number is not provided by user, check `.smbatcher/REGISTRY.md` and choose batches with sites not at `Q`. you can select multiple batches. ### Step 2: Acquire Lock and Open Batch (Main Agent) Execute: Tool: Bash Command: `tools/implement/lock.sh "$BATCH"` Background: - Handles D→O transition, lock + rollback on contention. ### Step 3: Launch Subagents (Main Agent) Launch ~10 Opus subagents to implement sites in parallel. Assign only ONE site to each subagent. When launch a subagent, provide Subagent Launch Template to the subagent **CRITICAL — PARALLEL LAUNCH:** To execute subagents in parallel, you MUST send a **SINGLE message** containing **MULTIPLE Task tool calls**. Example for 10 sites in batch: ``` ONE message with 10 Task tool calls: Task #1: prompt="Implement ONLY site1.com...", subagent_type="general-purpose" Task #2: prompt="Implement ONLY site2.com...", subagent_type="general-purpose" Task #3: prompt="Implement ONLY site3.com...", subagent_type="general-purpose" ... Task #10: prompt="Implement ONLY site10.com...", subagent_type="general-purpose" ``` **DO NOT** launch only one subagent at total, wait for it, then launch the next. Launch only one subagent is sequential, not parallel. **DO** include all Task tool calls in the same response message. ### Step 4: Implement Site (Subagent — Per Site LLM Work) Execute #1: Mark implement start Tool: Bash Command: `uv run python3.12 tools/implement/start.py <domain> --root .` Execute #2: Read design Tool: Bash Command: `uv run python3.12 tools/design/read-design.py sites/<domain-vX>/DESIGN.md` Background: - Extract layout/palette/motifs/interaction directives Build a site (files) After Execution #1~#2, Build a site Write these files via Write tool: - `sites/<domain-vX>/index.html` - `sites/<domain-vX>/styles.css` - `sites/<domain-vX>/script.js` - `sites/<domain-vX>/assets/<filename>` (if needed) - Build `index.html` → `styles.css` → `script.js` - Keep IDs/classes consistent - Add required assets to `assets/` such as SVG, etc. - Avoid console errors - Follow uniqueness notes (avoid overused motifs) Execute #3: Validate Basic file presence check Tool: Bash Command: `uv run python3.12 tools/implement/check-outputs.py sites/<domain-vX>` Execute #4: Validate Comprehensive verification (HTML, JS syntax, file stats) Tool: Bash Command: `tools/check/verify-site.sh sites/<domain-vX>` Execute #5: Validate Design compliance check (colors, fonts, patterns) Tool: Bash Command: `tools/check/design-compliance.sh sites/<domain-vX>` Execute #6: Mark implement complete Tool: Bash Command: `uv run python3.12 tools/implement/complete.py <domain> --root .` ### Step 5: Finalize Batch (Main Agent) After all subagents complete: Execute: Tool: Bash Command: `uv run python3.12 tools/implement/finish.py --batch "$BATCH" --root .` Background: - This transitions all I-status sites to Q (done). --- ## Subagent Launch Template When launching subagents for parallel implementation. **IMPORTANT:** - Launch in **synchronous mode** (C3), assign **ONE site only** (C2) - **Subagents MUST use Opus model** — set `model: "opus"` parameter when launching. NEVER use Sonnet. ``` Implement ONLY the site <domain>. Do NOT implement any other sites. - NEVER TRY to create file(ex: DESIGN.md) via cat/HEREDOC pattern. Use Only Write tool or Filesystem MCP. - NEVER DELETE file which you created. - DO NOT report result ## Step 0: Read instructions Execute: Tool: Read Path: tools/implement/IMPLEMENT_COMMAND.md Motivation: LLMs skipped reading instructions and invented ad-hoc commands. ## Step 1: Mark implement start Execute: Tool: Bash Command: uv run python3.12 tools/implement/start.py <domain> --root . ## Step 2: Read the design Execute: Tool: Bash Command: uv run python3.12 tools/design/read-design.py sites/<domain-vX>/DESIGN.md ## Step 3: Get creative implementation ideas Execute: Tool: Skill Skill: frontend-design Background: Ensures high-quality, distinctive implementations. ## Step 4: Write index.html Execute: Tool: Write Path: sites/<domain-vX>/index.html Background: - Keep IDs/classes consistent - Add required assets to `assets/` such as SVG, etc. - Avoid console errors - Follow uniqueness notes (avoid overused motifs) ## Step 5: Write styles.css Execute: Tool: Write Path: sites/<domain-vX>/styles.css Background: - Keep IDs/classes consistent - Add required assets to `assets/` such as SVG, etc. - Avoid console errors - Follow uniqueness notes (avoid overused motifs) ## Step 6: Write script.js Execute: Tool: Write Path: sites/<domain-vX>/script.js Background: - Keep IDs/classes consistent - Add required assets to `assets/` such as SVG, etc. - Avoid console errors - Follow uniqueness notes (avoid overused motifs) ## Step 7: Check outputs exist Execute: Tool: Bash Command: uv run python3.12 tools/implement/check-outputs.py sites/<domain-vX> ## Step 8: Verify site structure Execute: Tool: Bash Command: tools/check/verify-site.sh sites/<domain-vX> ## Step 9: Check design compliance Execute: Tool: Bash Command: tools/check/design-compliance.sh sites/<domain-vX> ## Step 10: Mark implement complete Execute: Tool: Bash Command: uv run python3.12 tools/implement/complete.py <domain> --root . ``` --- ## Output Format Save files under the site directory; keep relative paths consistent and runnable with no external network calls.

# LLM Implement Command Instructions ## Goal Generate HTML/CSS/JS (and assets) for a site using its Design.md while preserving uniqueness and quality gates. Do not care accessibilty, but maximize visual appearance and artistic design. Do not care the consume of resources or token. ## Inputs - Design.md for the site (aesthetics, layout, palette, motifs, prompts, uniqueness notes) - Site directory: `sites//` --- ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ ┃ CRITICAL: READ ALL RULES BEFORE ANY ACTION ┃ ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛ ## General Rules (Main Agent AND Subagents) These rules apply to **BOTH the main agent AND all subagents**. Include these in every subagent prompt. ### G1. Script Execution **ALWAYS run Python scripts with `uv run python3.12`:** ```bash # CORRECT uv run python3.12 tools/implement/run.py --batch 001 uv run python3.12 tools/implement/check-outputs.py sites/example.com-v1 uv run python3.12 tools/implement/generate.py sites/example.com-v1/DESIGN.md # WRONG — DO NOT USE THESE FORMS python3 tools/implement/run.py ... # WRONG python3.12 tools/implement/run.py ... # WRONG ./tools/implement/run.py ... # WRONG ``` **AVOID — Absolute paths add unnecessary directory prefix:** ```bash # WRONG — Uses absolute path to script (symlink source) uv run python3.12 /Volumes/Common/QJoon/llm/wdmaker/tools/implement/start.py domain.com --root /Volumes/Ephemeral/CMassM1 # WRONG — Uses absolute path to script AND arguments (repo path) uv run python3.12 /Volumes/Ephemeral/CMassK1/tools/implement/check-outputs.py /Volumes/Ephemeral/CMassK1/sites/example.com-v1 # CORRECT — Uses relative paths for both script and arguments uv run python3.12 tools/implement/start.py domain.com --root . uv run python3.12 tools/implement/check-outputs.py sites/example.com-v1 ``` Scripts are symlinked into the repo; always use relative `tools/...` and `sites/...` paths. ### G2. No Invented Commands - **DO NOT create new bash commands or scripts** - **DO NOT use ad-hoc shell commands** (cat/ls/find/grep/wc/for-loops) - Use ONLY the provided assist scripts listed below **AVOID — Ad-hoc inline Python:** ```bash # WRONG — Inline Python to inspect files uv run python3.12 -c " import os for f in os.listdir('sites/example.com-v1'): print(f) " # CORRECT — Use provided scripts uv run python3.12 tools/implement/check-outputs.py sites/example.com-v1 tools/check/file-stats.sh sites/example.com-v1 ``` **AVOID — Creating ad-hoc debug scripts in TMP:** ```bash # WRONG — Creating and running debug scripts uv run python3.12 /Volumes/Temp/WDMaker/CMassK1/debug_html.py uv run python3.12 /Volumes/Temp/WDMaker/CMassK1/check_css.py # CORRECT — Use provided scripts for inspection tools/check/verify-site.sh sites/example.com-v1 tools/check/html-check.sh sites/example.com-v1 ``` **AVOID — Using non-existent or invented scripts:** ```bash # WRONG — tools/status.py does not exist uv run python3.12 tools/status.py --root . | grep example.com # CORRECT — Use provided status scripts tools/check/status-report.sh tools/implement/status.sh ``` **AVOID — Piping to grep:** ```bash # WRONG — Piping output to grep tools/check/status-report.sh | grep example.com # CORRECT — Use script options for filtering, or read full output tools/implement/status.sh ``` ### G3. No HEREDOC Pattern - **NEVER use HEREDOC** (`< index.html ... EOF # CORRECT — Use Write tool or MCP # (Use the Write tool in Claude Code to create files) ``` ### G4. Temp Directory - Use `${TMP}` from `.wdmaker/config.toml` for temporary files - **NEVER use `/tmp`** — always use the configured temp directory ### G5. Directory Creation - **Use provided scripts** for creating/preparing directories (e.g., `tools/prepare/batch.sh`) - **NEVER use `mkdir`** directly — directories are scaffolded by workflow scripts - **DO NOT create `.gitkeep`**, `.keep`, or similar placeholder files ### G6. Preserve Reports - **DO NOT delete** generated reports (implementation reports, batch reports, logs) - Reports in `.smbatcher/batches/`, `.smbatcher/runs/`, `${TMP}/` are historical records --- ## Claude Code Specific Rules These rules are specific to Claude Code orchestration. ### C1. Model Restriction - **DO NOT use Sonnet model** for implementation tasks - Use Opus for implementation work (higher quality, better code generation) ### C2. Subagent Assignment — ONE SITE PER SUBAGENT - Each subagent implements **EXACTLY ONE site**, then terminates - **NEVER assign 2+ sites** to a single subagent - Context exhaustion is UNRECOVERABLE — this is not optional ``` CORRECT: 10 subagents × 1 site each = 10 sites INCORRECT: 10 subagents × 8 sites each = 80 sites ← WILL FAIL ``` ### C3. Subagent Execution Mode - **ALWAYS launch subagents in synchronous mode**, NOT background mode - Wait for each subagent to complete before proceeding - Do NOT use `run_in_background: true` for implementation subagents ### C4. Status Code Updates via Scripts **NEVER modify REGISTRY.md or batch files directly. Use scripts for all status transitions.** | Role | Status | Script | When | |------|--------|--------|------| | Main | O | `tools/implement/lock.sh ` | Before starting implementation | | Subagent | i | `uv run python3.12 tools/implement/start.py ` | Before starting implementation work | | Subagent | I | `uv run python3.12 tools/implement/complete.py ` | After implementation validated | | Main | Q | `uv run python3.12 tools/implement/finish.py --batch ` | After all subagents complete | **Flow:** ``` Main agent: O (open for implement via lock.sh) ↓ Subagent: i (implement started) → [write code] → I (implement complete) ↓ Main agent: Q (done via finish.py) ``` --- ## Assist Scripts Reference ### `tools/implement/start.py` **Purpose:** Mark a single site as implement-in-progress (i) in REGISTRY. Called by subagent at START of implementation. ```bash uv run python3.12 tools/implement/start.py example.com --root . ``` **Actions:** - Acquires REGISTRY.lock - Updates domain status: O → i - Records timestamp **Options:** - `` — Domain to mark (required) - `--root ` — Repository root (default: .) --- ### `tools/implement/complete.py` **Purpose:** Mark a single site as implement-complete (I) in REGISTRY. Called by subagent at END of implementation. ```bash uv run python3.12 tools/implement/complete.py example.com --root . ``` **Actions:** - Validates required files exist (index.html, styles.css, script.js) - Runs check-outputs.py validation (unless --skip-validation) - Acquires REGISTRY.lock - Updates domain status: i → I - Records timestamp **Options:** - `` — Domain to mark (required) - `--root ` — Repository root (default: .) - `--skip-validation` — Skip implementation validation --- ### `tools/implement/finish.py` **Purpose:** Mark all implemented sites (I) in a batch as done (Q). Called by main agent after all subagents complete. ```bash uv run python3.12 tools/implement/finish.py --batch 001 --root . ``` **Actions:** - Acquires REGISTRY.lock - Transitions all I-status sites in batch to Q - Records timestamp **Options:** - `--batch ` — Batch ID (required) - `--root ` — Repository root (default: .) --- ### `tools/implement/lock.sh` **Purpose:** Lock batch and transition status D→O for implementation. ```bash tools/implement/lock.sh ``` **Actions:** - Acquires exclusive lock on REGISTRY.lock - Transitions all batch sites from D (Designed) to O (Open for implement) - Creates `batch--implement.md` tracker if not exists - Records locked domains in tracker **Options:** - `` — Required. The batch ID (e.g., 001) **Exit codes:** - 0 = Success (locked D→O or batch already open/in progress) - 1 = Batch not found or no D/O/i domains to lock - 2 = Registry not found --- ### `tools/implement/run.sh` **Purpose:** Wrapper script that runs `run.py` with correct environment. ```bash tools/implement/run.sh --batch --concurrency ``` **Actions:** - Sets WDMAKER_ROOT environment variable - Delegates to `tools/run-python.sh` with `run.py` - Passes all arguments through --- ### `tools/implement/run.py` **Purpose:** Queue manager for implementation workflow. Does NOT generate site code. ```bash uv run python3.12 tools/implement/run.py --batch --concurrency ``` **Actions:** - Calls `lock.sh` to acquire batch - Collects domains from registry for the batch - Transitions status: O → i (in-progress) → I (implemented) → Q (queued/complete) - Runs `generate.py`, `validate.py`, `check-outputs.py` for each site - Handles retries and cleanup on failure - Logs to `.smbatcher/runs/implement-.log` **Options:** - `--batch ` — Batch ID or 'auto' (default: auto → 001) - `--concurrency ` — Worker count (default: 4) - `--dry-run` — Simulate without writing - `--root ` — Override repository root - `--max-retries ` — Retries per site on failure (default: 1) **Important:** The actual HTML/CSS/JS code must be authored by the LLM coding tool. This script only orchestrates the queue and validation. --- ### `tools/implement/generate.py` **Purpose:** Prepare assets directory for site implementation. ```bash uv run python3.12 tools/implement/generate.py ``` **Actions:** - Creates `assets/` directory if not exists - Does NOT generate placeholder HTML/CSS/JS (LLM must author) **Options:** - `` — Path to the design file (e.g., sites/example.com-v1/DESIGN.md) --- ### `tools/implement/check-outputs.py` **Purpose:** Validate HTML/CSS/JS presence for a site directory. ```bash uv run python3.12 tools/implement/check-outputs.py ``` **Checks:** - index.html exists - styles.css exists - script.js exists **Output:** - "ok" if all required files present - "missing: " if any files missing **Exit codes:** - 0 = All files present - 1 = Missing required files --- ### `tools/implement/status.sh` **Purpose:** Show registry entries for a specific batch. ```bash tools/implement/status.sh ``` **Output:** - Registry lines matching the batch ID - "No entries for batch " if none found --- ### `tools/shared/validate.py` **Purpose:** Shared HTML/asset validation checks using BeautifulSoup. ```bash uv run python3.12 tools/shared/validate.py ``` **Functions:** - `validate_html(file_path)` — Check for `` root element, return errors list - `ensure_assets(asset_dir)` — Verify assets directory exists **Usage:** - Called by `run.py` during implementation validation - Returns list of error strings; empty list means valid --- ### `tools/check/verify-site.sh` **Purpose:** Comprehensive site verification — runs all checks in sequence. ```bash tools/check/verify-site.sh tools/check/verify-site.sh sites/example.com-v1 ``` **Actions:** 1. Checks required files exist (index.html, styles.css, script.js) 2. Runs HTML structure check via `html-check.sh` 3. Runs JavaScript syntax check via `js-syntax.sh` 4. Shows file statistics via `file-stats.sh` 5. Checks for DESIGN.md presence **Exit codes:** - 0 = All checks passed - 1 = One or more checks failed --- ### `tools/check/html-check.sh` **Purpose:** Check HTML structure for required elements. ```bash tools/check/html-check.sh tools/check/html-check.sh sites/example.com-v1 ``` **Checks:** - DOCTYPE declaration - ``, ``, `` tags - `` tag - Viewport meta tag - CSS link or inline styles - JavaScript reference - Closing `</html>` tag **Exit codes:** - 0 = HTML structure valid - 1 = Structural issues found --- ### `tools/check/js-syntax.sh` **Purpose:** Check JavaScript syntax using Node.js. ```bash tools/check/js-syntax.sh <site-dir> tools/check/js-syntax.sh sites/example.com-v1 ``` **Actions:** - Finds all .js files in site directory (maxdepth 2) - Runs `node -c` on each file to check syntax - Reports pass/fail for each file **Exit codes:** - 0 = All JavaScript files valid - 1 = Syntax errors found --- ### `tools/check/file-stats.sh` **Purpose:** Show file statistics for a site directory. ```bash tools/check/file-stats.sh <site-dir> tools/check/file-stats.sh sites/example.com-v1 ``` **Output:** - Line counts and file sizes for HTML, CSS, JS files - Total lines and KB **Example:** ``` HTML: index.html 150 lines 5.2 KB CSS: styles.css 200 lines 4.1 KB JavaScript: script.js 100 lines 3.0 KB --- TOTAL: 450 lines, 12.3 KB ``` --- ### `tools/check/design-compliance.sh` **Purpose:** Check implementation compliance against DESIGN.md specifications. ```bash tools/check/design-compliance.sh <site-dir> tools/check/design-compliance.sh sites/example.com-v1 ``` **Checks:** 1. **Color Palette** — Verifies hex colors from DESIGN.md appear in CSS 2. **Typography** — Checks specified fonts are used 3. **CSS Animations** — Counts @keyframes and transitions 4. **Performance Patterns** — Checks for will-change, transforms, requestAnimationFrame, etc. 5. **JavaScript Features** — Counts classes, functions, event listeners 6. **Accessibility** — ARIA attributes, focus styles, keyboard handling 7. **External Dependencies** — External scripts, images, fonts **Output:** - Pass/Warn/Fail counts per category - Summary: FULL COMPLIANCE, PARTIAL COMPLIANCE, or COMPLIANCE ISSUES FOUND **Exit codes:** - 0 = No failures (may have warnings) - 1 = Compliance issues found --- ## Prohibited vs Alternatives | ❌ Prohibited | ✅ Use Instead | |--------------|----------------| | `cat/less/head/tail` file inspection | `uv run python3.12 tools/implement/check-outputs.py <site-dir>` or `tools/implement/status.sh <BATCH>` | | `ls/find/wc/globs` directory listing | `uv run python3.12 tools/design/check-dirs.py --batch-id <ID> --root .` or `tools/check/file-stats.sh <site-dir>` | | `grep "pattern"` searching | `tools/implement/status.sh <BATCH>` | | `for f in *.html; do` loops | `uv run python3.12 tools/implement/run.py --batch <ID>` (handles queue) | | `mkdir -p` directory creation | `uv run python3.12 tools/implement/generate.py <DESIGN.md>` or `tools/prepare/batch.sh` | | `python3 script.py` | `uv run python3.12 tools/.../<script>.py` | | `cat <<EOF` HEREDOC | Write tool or Filesystem MCP | | Creating new scripts | Use existing assist scripts only | | Manual HTML validation | `tools/check/html-check.sh <site-dir>` or `tools/check/verify-site.sh <site-dir>` | | Manual JS validation | `tools/check/js-syntax.sh <site-dir>` | | Manual compliance check | `tools/check/design-compliance.sh <site-dir>` | --- ## Required Outputs - `index.html` matching Design.md layout and tone - `styles.css` implementing palette/typography/motifs - `script.js` for interactions; ensure no console errors - `assets/` for required media/SVGs - No placeholders: deliver complete, production-ready files (LLM coding tools own the final content). --- ## Steps for LLM > **Note:** General Rules (G1-G4) and Claude Code Rules (C1-C5) apply to ALL steps below. ### Step 1: Pick Batch (Main Agent) Execute: Read REGISTRY Tool: Read Path: .smbatcher/REGISTRY.md Background: - If batch number is not provided by user, check `.smbatcher/REGISTRY.md` and choose batches with sites not at `Q`. you can select multiple batches. ### Step 2: Acquire Lock and Open Batch (Main Agent) Execute: Tool: Bash Command: `tools/implement/lock.sh "$BATCH"` Background: - Handles D→O transition, lock + rollback on contention. ### Step 3: Launch Subagents (Main Agent) Launch ~10 Opus subagents to implement sites in parallel. Assign only ONE site to each subagent. When launch a subagent, provide Subagent Launch Template to the subagent **CRITICAL — PARALLEL LAUNCH:** To execute subagents in parallel, you MUST send a **SINGLE message** containing **MULTIPLE Task tool calls**. Example for 10 sites in batch: ``` ONE message with 10 Task tool calls: Task #1: prompt="Implement ONLY site1.com...", subagent_type="general-purpose" Task #2: prompt="Implement ONLY site2.com...", subagent_type="general-purpose" Task #3: prompt="Implement ONLY site3.com...", subagent_type="general-purpose" ... Task #10: prompt="Implement ONLY site10.com...", subagent_type="general-purpose" ``` **DO NOT** launch only one subagent at total, wait for it, then launch the next. Launch only one subagent is sequential, not parallel. **DO** include all Task tool calls in the same response message. ### Step 4: Implement Site (Subagent — Per Site LLM Work) Execute #1: Mark implement start Tool: Bash Command: `uv run python3.12 tools/implement/start.py <domain> --root .` Execute #2: Read design Tool: Bash Command: `uv run python3.12 tools/design/read-design.py sites/<domain-vX>/DESIGN.md` Background: - Extract layout/palette/motifs/interaction directives Build a site (files) After Execution #1~#2, Build a site Write these files via Write tool: - `sites/<domain-vX>/index.html` - `sites/<domain-vX>/styles.css` - `sites/<domain-vX>/script.js` - `sites/<domain-vX>/assets/<filename>` (if needed) - Build `index.html` → `styles.css` → `script.js` - Keep IDs/classes consistent - Add required assets to `assets/` such as SVG, etc. - Avoid console errors - Follow uniqueness notes (avoid overused motifs) Execute #3: Validate Basic file presence check Tool: Bash Command: `uv run python3.12 tools/implement/check-outputs.py sites/<domain-vX>` Execute #4: Validate Comprehensive verification (HTML, JS syntax, file stats) Tool: Bash Command: `tools/check/verify-site.sh sites/<domain-vX>` Execute #5: Validate Design compliance check (colors, fonts, patterns) Tool: Bash Command: `tools/check/design-compliance.sh sites/<domain-vX>` Execute #6: Mark implement complete Tool: Bash Command: `uv run python3.12 tools/implement/complete.py <domain> --root .` ### Step 5: Finalize Batch (Main Agent) After all subagents complete: Execute: Tool: Bash Command: `uv run python3.12 tools/implement/finish.py --batch "$BATCH" --root .` Background: - This transitions all I-status sites to Q (done). --- ## Subagent Launch Template When launching subagents for parallel implementation. **IMPORTANT:** - Launch in **synchronous mode** (C3), assign **ONE site only** (C2) - **Subagents MUST use Opus model** — set `model: "opus"` parameter when launching. NEVER use Sonnet. ``` Implement ONLY the site <domain>. Do NOT implement any other sites. - NEVER TRY to create file(ex: DESIGN.md) via cat/HEREDOC pattern. Use Only Write tool or Filesystem MCP. - NEVER DELETE file which you created. - DO NOT report result ## Step 0: Read instructions Execute: Tool: Read Path: tools/implement/IMPLEMENT_COMMAND.md Motivation: LLMs skipped reading instructions and invented ad-hoc commands. ## Step 1: Mark implement start Execute: Tool: Bash Command: uv run python3.12 tools/implement/start.py <domain> --root . ## Step 2: Read the design Execute: Tool: Bash Command: uv run python3.12 tools/design/read-design.py sites/<domain-vX>/DESIGN.md ## Step 3: Get creative implementation ideas Execute: Tool: Skill Skill: frontend-design Background: Ensures high-quality, distinctive implementations. ## Step 4: Write index.html Execute: Tool: Write Path: sites/<domain-vX>/index.html Background: - Keep IDs/classes consistent - Add required assets to `assets/` such as SVG, etc. - Avoid console errors - Follow uniqueness notes (avoid overused motifs) ## Step 5: Write styles.css Execute: Tool: Write Path: sites/<domain-vX>/styles.css Background: - Keep IDs/classes consistent - Add required assets to `assets/` such as SVG, etc. - Avoid console errors - Follow uniqueness notes (avoid overused motifs) ## Step 6: Write script.js Execute: Tool: Write Path: sites/<domain-vX>/script.js Background: - Keep IDs/classes consistent - Add required assets to `assets/` such as SVG, etc. - Avoid console errors - Follow uniqueness notes (avoid overused motifs) ## Step 7: Check outputs exist Execute: Tool: Bash Command: uv run python3.12 tools/implement/check-outputs.py sites/<domain-vX> ## Step 8: Verify site structure Execute: Tool: Bash Command: tools/check/verify-site.sh sites/<domain-vX> ## Step 9: Check design compliance Execute: Tool: Bash Command: tools/check/design-compliance.sh sites/<domain-vX> ## Step 10: Mark implement complete Execute: Tool: Bash Command: uv run python3.12 tools/implement/complete.py <domain> --root . ``` --- ## Output Format Save files under the site directory; keep relative paths consistent and runnable with no external network calls.