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/eveiljuice/claude-plugin-design-md/creategit clone --depth 1 https://github.com/eveiljuice/claude-plugin-design-mdWrote 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/eveiljuice/claude-plugin-design-md/create)<a href="https://agentmods.dev/commands/eveiljuice/claude-plugin-design-md/create"><img src="https://agentmods.dev/badge/commands/eveiljuice/claude-plugin-design-md/create.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 5.1 | $0.00019 | $0.00718 |
| Opus 5 | $0.00010 | $0.00359 |
| Sonnet 5 | $0.00004 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
create scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Write, Bash(curl:*), WebFetch How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a DESIGN.md
You are scaffolding a DESIGN.md file for the user's project. The file follows the google-labs-code/design.md specification: YAML front matter with design tokens plus markdown prose that explains the rationale. An AI coding agent that reads the finished file should be able to build a UI that matches the intended visual identity without further briefing.
Resolving the source
Read $ARGUMENTS. Trim whitespace and lower-case it.
| Argument | Source |
|---|---|
empty string or blank |
local template at ${CLAUDE_PLUGIN_ROOT}/templates/DESIGN.md |
atmospheric-glass |
https://raw.githubusercontent.com/google-labs-code/design.md/main/examples/atmospheric-glass/DESIGN.md |
paws-and-paths |
https://raw.githubusercontent.com/google-labs-code/design.md/main/examples/paws-and-paths/DESIGN.md |
totality-festival |
https://raw.githubusercontent.com/google-labs-code/design.md/main/examples/totality-festival/DESIGN.md |
Any other value: stop, tell the user which arguments are valid, and do nothing else.
Steps
-
Check for an existing file. Try reading
DESIGN.mdin the current working directory. If it exists, stop and ask the user whether to overwrite. Do not proceed until they confirm. -
Load the source content.
- Local template: use the Read tool on
${CLAUDE_PLUGIN_ROOT}/templates/DESIGN.md. - Remote example: use WebFetch on the URL from the table. Prompt:
Return the full raw file content verbatim, including the YAML front matter between --- fences and every markdown section. Do not summarize, paraphrase, reformat, or add commentary. - If WebFetch returns a summarised or truncated response, retry once. If it still will not return the raw bytes, fall back to Bash:
curl -fsSL <url>and capture stdout. Treat stdout as the verbatim content.
- Local template: use the Read tool on
-
Write
DESIGN.mdin the current working directory via the Write tool. Content must be byte-identical to what you loaded in step 2 — do not edit tokens, renumber sections, or add comments.
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.
- 5d ago First seen · 45 lines · 19 tokens per session scan A f7eb0eca0741
create is a command published in the GitHub repository eveiljuice/claude-plugin-design-md (8 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 718 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
commands-deprecated-directory
Commands directory is deprecated, migrate to Skills.
make
Create structured implementation plan in docs/plans/.
init
First-time Archcore setup — detect the repo, compose the full first-day seed in one preview, create it on one confirm, and wire host configs.
document
Record a decision as an ADR or RFC, or document existing code as a spec, doc, guide, or rule; routes to the right document type.
review
Review branch changes against Archcore docs, or report project health; --drift runs staleness detection, --deep a full documentation audit.
re-start
리버스 엔지니어링 분석을 안전하게 시작합니다 (동의 → 분석 → 한국어 보고서).