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/discoverygit clone --depth 1 https://github.com/volomydyr/design-engineer-pluginWrote 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/commands/volomydyr/design-engineer-plugin/discovery)<a href="https://agentmods.dev/commands/volomydyr/design-engineer-plugin/discovery"><img src="https://agentmods.dev/badge/commands/volomydyr/design-engineer-plugin/discovery.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.07223 |
| Opus 5 | $0.00025 | $0.03612 |
| Sonnet 5 | $0.00010 | $0.01445 |
| Haiku 4.5 | $0.00005 | $0.00722 |
Grade A, and why
design-engineer:discovery 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 4d 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 — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Workflow
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 ${DESIGN_ENGINEER_PLUGIN_ROOT}/..., substitute the absolute path from that context line. No shell commands are run from this command body.
Spacer rule (per CLAUDE.md rule #6): Before every
AskUserQuestiontool call this command makes, end the preceding chat message with the canonical 3-horizontal-rule spacer (three lines of─characters). This applies to every option set described in this command body. The spacer prevents the question panel from overlaying substantive content on most clients.
Context
#$ARGUMENTS
Argument routing
If $ARGUMENTS is feature-spec, jump to Step F1: Minimal feature spec below. Otherwise proceed to Step 1.
Step 1: Read project context
- Read
.design-engineer-plugin/config.yamlfor mode (guided/autopilot) and project type - Check for existing deliverables in
design/ - If
.design-engineer-plugin/config.yamlnot found, tell the user to run/design-engineer:launchfirst - Scan the project: what tech stack, what components exist, what design patterns are used
Step 2: Route based on project type
Check project_type in the config:
If project_type: existing → Feature flow (abbreviated)
This project already exists. Do NOT run the full 4-phase from-scratch pipeline. The product has users, positioning, and an established codebase. Run an abbreviated feature-focused flow:
Step 2.1: Spec polish routing (BLOCKING — choose before any work begins)
Before drafting any spec or running any skill, ask the user how polished the spec needs to be. This routes between the minimal one-page spec (which goes to F1) and the full feature flow (which continues to Step 2.2 below). End the preceding chat message with the canonical 3-horizontal-rule spacer per CLAUDE.md rule #6, then call AskUserQuestion:
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.
- 4d ago First seen · 507 lines · 50 tokens per session scan A b3b54cfa198b
design-engineer:discovery is a command published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 7,223 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 2026-08-30.
Other commands, from other repositories
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
template-ui
Design a Sent template-builder interface.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.
4-generate
Run Stage 4 of the design system skill generation pipeline: parallel skill file generation.
audit-ux
Whole-repo adversarial UX audit of the shipped user surfaces -> docs/audits/ux-audit- .md.