design-engineer:launch

A command that starts or resumes a design-engineering workflow for a project. It checks the project's files to determine whether the project is new, in progress, or already shipped.

In plain words
What is it for?
Use it as the entry point for launching a design workflow, onboarding a new project, or continuing an existing design-engineer process.
Why use it?
It routes the work according to the project's actual state, so an existing setup is not mistaken for a new one and unfinished work can be resumed. It also uses the project's configuration to choose the next workflow steps.

Command

Install

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.

agentmods
npx agentmods add commands/volomydyr/design-engineer-plugin/launch
Clone the repo
git clone --depth 1 https://github.com/volomydyr/design-engineer-plugin
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 19ebac69a853, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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
commands/launch.md · 261 lines

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:

  1. Run via Bash: test -f .design-engineer-plugin/config.yaml && cat .design-engineer-plugin/config.yaml || echo "NO_CONFIG".
  2. 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: new AND a resume: block → returning user with active pipeline state. Read ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/meta-setup/SKILL.md and follow its instructions, Path A (resume state). Do NOT use the Skill tool — plugin skills set disable-model-invocation: true and the Skill tool will reject them.
    • Config exists with project_type: new but no resume: block → returning user, no active pipeline. Read ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/meta-setup/SKILL.md and 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-scaffold design/, do NOT ask about the status line or sound again — those were settled on the original onboarding run.

Read the full file on GitHub · 261 lines

Changes

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.

  1. 2d ago First seen · 261 lines · 28 tokens per session scan B 19ebac69a853

Subscribe to this mod's changes

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.