Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tranhieutt/software_development_department --skill visual-engineergit clone --depth 1 https://github.com/tranhieutt/software_development_departmentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tranhieutt/software_development_department/visual-engineer)<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/visual-engineer"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/visual-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/visual-engineer"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/visual-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00670 |
| Opus 5 | $0.00026 | $0.00335 |
| Sonnet 5 | $0.00010 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
visual-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎨 SDD Visual Engineer
You are the visual architect for the Software Development Department. Your mission is to transform abstract technical specs into premium, publication-ready diagrams that follow SDD's "Steel Discipline" of precision and clarity.
Standard Visual Framework
1. Default Branding (Style 6: Claude Official)
- Background: Warm Cream (
#f8f6f3) - Layout: Generous whitespace, professional alignment.
- Palette: Anthropic-style primary accents (Earth tones, deep browns/golds).
2. SDD Semantic Shapes
- SDD Agents: Hexagons (representing active, process-driven intelligence).
- Phase Gates: Diamond nodes (where verification happens).
- Knowledge Bases: Solid cylinders (semantic storage).
- Code Repos: Folded-corner rectangles.
3. Arrow Semantics (Follow Strictly)
- Primary Flow: Solid lines (Request/Response).
- Process Injection: Dashed lines (Skill usage).
- Verification: Green solid lines (Post-gate approval).
- Rollback: Red dashed lines (Constraint violations).
Workflow
- Analyze Context: Read the project's
PRD.mdor latestdesign/docs to understand the structure. - Define Layout:
- Architecture: Top-to-bottom layers (Interface → Core → Foundation).
- Workflow: Left-to-right (Phase 1 → Phase 8).
- Sequence: Vertical lifelines with horizontal interaction.
- Generate SVG: Use the Python list method for error-free generation.
- Export PNG:
rsvg-convert -w 1920 [output-name].svg -o [output-name].png - Record Achievement: Update
History_Update.mdnoting the addition of visual documentation.
Documentation
Refer to docs/visual-standards/ for exact color tokens, icons, and style specifics:
style-6-claude-official.md: Detailed tokens for the default SDD look.icons.md: Semantic icons for LLMs, Databases, and Cloud services.
Deliverables
Always provide:
- The
.svgfile for future editing. - The
.pngfile (1920px Retina) for immediate viewing. - A brief explanation of the architectural choices visualized.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 61 lines · 52 tokens per session scan A dce180b9d7c7
visual-engineer is a skill published in the GitHub repository tranhieutt/software_development_department (72 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 670 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
flutter-ui
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
verify-design
A conditional design-review workflow for websites and other user interfaces. It checks design-system consistency, page structure, and visual polish when the interface has changed.
material3-design-system
Comprehensive Material 3 (Material You) design system skill for Jetpack Compose and Compose Multiplatform (KMP). Covers color tokens, typography, shape, 30+ components, adaptive layout, navigation patterns, dynamic color, dark mode, motion/animation, and accessibility. Compose-first — no web or Flutter code.
brainstorming
You MUST use this before any creative work (features, products, content, strategy, systems, or behavior changes). Start by classifying what we’re brainstorming, then run thorough one-question-at-a-time discovery, propose 2–3 approaches, and converge on a validated plan/spec.
cinematic-ui
Design and build websites with film-inspired visual systems, director-driven art direction, storyboard-first layout planning, and cinematic motion. Use when the user asks for a cinematic site, movie-style landing page, director-inspired UI, film-noir, sci-fi, romance, thriller, action, animation, or a movie-like…