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 agentmods add commands/volomydyr/design-engineer-plugin/launchgit clone --depth 1 https://github.com/volomydyr/design-engineer-pluginWhat 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 | $0.00028 | $0.04023 |
| Opus 5 | $0.00014 | $0.02011 |
| Sonnet 5 | $0.00006 | $0.00805 |
| Haiku 4.5 | $0.00003 | $0.00402 |
Grade B, and why
design-engineer:launch scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
f) Ask status line question. Do NOT use the built-in `statusline-setup` agent, and do NOT write to `~/.claude/settings.json` or copy files to `~/.claude/hooks/` yourself — Auto mode's permission classifier blocks writes How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Engineer – Launch
#$ARGUMENTS
Plugin paths
Your conversation context contains a line DESIGN_ENGINEER_PLUGIN_ROOT: <absolute path> injected by the plugin's UserPromptSubmit hook. Whenever this command body references ${DESIGN_ENGINEER_PLUGIN_ROOT}/..., substitute the absolute path from that context line. No shell commands are run from this command body.
Routing
Step 0 (BLOCKING — run before anything else): re-detect state from disk. The DESIGN_ENGINEER_PROJECT_STATE value injected by the start hook can lag behind disk reality (cached old hook version, hook fired before config was created, hook ran in a different cwd, etc.). Trust the disk, not the injected value:
- Run via Bash:
test -f .design-engineer-plugin/config.yaml && cat .design-engineer-plugin/config.yaml || echo "NO_CONFIG". - Branch on what you read:
NO_CONFIG→ user is genuinely new in this directory. Follow the Onboarding sequence below in this file. Do not skip any step.- Config exists with
project_type: newAND aresume:block → returning user with active pipeline state. Read${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/meta-setup/SKILL.mdand follow its instructions, Path A (resume state). Do NOT use theSkilltool — plugin skills setdisable-model-invocation: trueand the Skill tool will reject them. - Config exists with
project_type: newbut noresume:block → returning user, no active pipeline. Read${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/meta-setup/SKILL.mdand follow its instructions, Path A (config summary). - Config exists with
project_type: existing→ existing-project user is returning. Acknowledge in one sentence what you found in their config (mode, last goal, any in-progress feature folder under.design-engineer-plugin/design/features/), then ask via AskUserQuestion (with spacer):- question: "Welcome back. What would you like to do?"
- header: "Goal"
- options match the Step 2 Question 1 set below (Review my project / Implement from Figma / Design a new feature / Prepare project for AI coding).
- multiSelect: false
- After the answer, route directly to the matching
/design-engineer:command. Do NOT re-run the project-type question, do NOT re-scaffolddesign/, do NOT ask about the status line or sound again — those were settled on the original onboarding run.
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.
- 2d ago First seen · 261 lines · 28 tokens per session scan B 19ebac69a853
design-engineer:launch is a command published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 4,023 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
buildable-design
Create a UI/UX design brief from a prompt or the current Buildable app spec.
mockup-analyze
Extract design specifications from HTML mockups using AI vision.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
overlay
The spatial overlay — a click-through canvas floating over every window that both you and agents can draw on. /overlay shows status; /overlay open launches it (⌃⌥⌘D toggles draw mode, esc leaves); /overlay post --rel X,Y,W,H puts an arrow / box / highlight / spotlight / label / callout / sticker on the screen from an…
excalidraw-export
Export the current Excalidraw canvas scene, element set, library, or theme by retrieving the live resource snapshot.