design-engineer:development

A command that sets up and runs the Design Engineer development workflow. It reads the project configuration, checks the technology stack and build tools, and uses the configured operating mode.

In plain words
What is it for?
Use it to start development after the design workflow, or to run development on its own. It can inspect project files, configuration, build tools, and agent setup before implementation.
Why use it?
It gives the plugin the project context needed to guide implementation and AI-assisted building correctly. It also identifies when the required Design Engineer setup has not been created.

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/development
Clone the repo
git clone --depth 1 https://github.com/volomydyr/design-engineer-plugin
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,427 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00024 $0.07427
Opus 5 $0.00012 $0.03714
Sonnet 5 $0.00005 $0.01485
Haiku 4.5 $0.00002 $0.00743

Measured 2d ago against content hash d91d51f06edd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-engineer:development 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 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.

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.

commands/development.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Pipeline

Plugin paths

Your conversation context contains a line DESIGN_ENGINEER_PLUGIN_ROOT: <absolute path> injected by the plugin's UserPromptSubmit hook. Whenever this command references ${DESIGN_ENGINEER_PLUGIN_ROOT}/..., substitute the absolute path from that context line. No shell commands are run from this command body.

Spacer rule (per CLAUDE.md rule #6): Before every AskUserQuestion tool call this command makes, end the preceding chat message with the canonical 3-horizontal-rule spacer (three lines of characters). This applies to every option set described in this command body.

Context

#$ARGUMENTS

Sets up and runs the development workflow. Use after the design pipeline or standalone.

Step 1: Read project context

  1. Read .design-engineer-plugin/config.yaml for mode (guided/autopilot), project type, and environment
  2. Scan the project: what tech stack, what build tools, does CLAUDE.md exist, are agents configured?
  3. If .design-engineer-plugin/config.yaml not found, tell the user to run /design-engineer:launch first

Step 1.5: Apply UX/psych depth from feature options

If the user came from /design-engineer:discovery (existing-project feature flow), they may have selected optional depth steps in design.md Step 2.5. Surface those insights HERE — before plan generation in Step 2 — so the implementation plan reflects them. Application is inline (Reads + analysis); do not produce separate deliverable files unless the underlying skill prescribes one.

  1. Read .design-engineer-plugin/config.yaml. Look for project.feature_options: (a list of strings).
  2. If the key is missing or the list is empty, skip this step entirely.
  3. For each option in the list, perform the corresponding skill load and apply it inline. Do NOT use the Skill tool — plugin skills set disable-model-invocation: true and the Skill tool will reject them. Always Read SKILL.md and follow its instructions inline.
Selected option What to do
Psychology audit Read ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/psych-decision-fundamentals/SKILL.md and follow it inline against the planned feature, then Read ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/psych-cognitive-load/SKILL.md and follow it inline.
Figma comparison Read ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/ui-figma-guide/SKILL.md and follow it inline to pull structured Figma data and compare to the plan.
Design-system check Read ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/ui-design-system/SKILL.md and follow it inline against the project's existing tokens and components.
Brief problem statement Read ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/ux-problem-statement/SKILL.md and follow it inline. Rare in dev.md context but supported when the feature was ambiguous and the design step skipped it.

Read the full file on GitHub · 374 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 · 374 lines · 24 tokens per session scan A d91d51f06edd

Subscribe to this mod's changes

design-engineer:development is a command published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 7,427 once invoked, about $0.0001 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 2026-08-30.