Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/atretyak1985/swarmerynpx agentmods add commands/atretyak1985/swarmery/design-implementWrote 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/atretyak1985/swarmery/design-implement)<a href="https://agentmods.dev/commands/atretyak1985/swarmery/design-implement"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/design-implement.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 | $0.00064 | $0.02043 |
| Opus 5 | $0.00032 | $0.01022 |
| Sonnet 5 | $0.00013 | $0.00409 |
| Haiku 4.5 | $0.00006 | $0.00204 |
Grade A, and why
design-implement 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 3d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-implement — turn a design handoff into an implemented screen
Usage
/design-implement <export-path|url> [--route <path>] [--viewport WxH] [--from-screenshots] [--dry-run]
Examples:
/design-implement ./handoff/checkout.html --route /checkout/design-implement ./handoff/checkout.zip --route /checkout --viewport 1440x900/design-implement https://<design-host>/share/<id> --route /checkout --dry-run/design-implement ./handoff/shots/ --route /checkout --from-screenshots
This command is invoked the same way from an interactive session and from the
ai-prompt step of a scheduled routine, where the prompt arrives on a headless
session's stdin and nobody is there to address an agent by name. That is the
whole reason a command exists alongside @design-implementer: a stable entry
point that does not depend on an agent being named correctly in free text (the
same rationale as plugins/jira-pack/commands/jira-fix.md:21-25).
What it does — and does not do
This is a thin proxy. It parses $ARGUMENTS, validates the shape of the
positional argument and the flags, and delegates everything else to the
design-implement skill (plugins/design-pack/skills/design-implement/SKILL.md),
which owns all of Phases 0-6: prerequisites, acquire, ground truth, recon, plan,
implement, verify.
In particular, this command does not:
- read, unzip, or parse the export — the skill's Phase 1 (
design-acquire) does; - check that
.claude/project.jsoncarries adesignblock, or that itstokensFile/componentsRoot/routesRootpaths exist — the skill's Phase 0 does, and prints the paste-ready fragment when they are missing; - start
design.devCommand, screenshot anything, compute a diff, or decide what to change — the skill's Phases 3-6 and@design-implementerown that.
If an explanation of how to diff, which region to fix first, or what counts as a passing screen ever appears in this file, it leaked out of the skill and belongs back there.
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.
- 3d ago First seen · 161 lines · 64 tokens per session scan A 4b6c2ddbabe0
design-implement is a command published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 2,043 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 2026-09-03.
Other commands, from other repositories
design-tokens
Définition Design Tokens.
frankx-ai-components
Create and update UI components for FrankX.AI with glassmorphic design system.
prototype
Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery.
designer
UI/UX design with Memory coordination for consistent experiences.
ui-ux-behaviour-block
When this command is used, use the following block. Acknowledge your understanding and then await the user's request.
polish
Run visual quality pass — states, skeletons, empty states, meta tags.