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.
git clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/visualize)<a href="https://agentmods.dev/commands/atretyak1985/swarmery/visualize"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/visualize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/atretyak1985/swarmery/visualize"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/visualize.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01308 |
| Opus 5.5 | $0.00026 | $0.00523 |
| Sonnet 5.5 | $0.00013 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
visualize 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 15d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/visualize — explain a document or a topic as an interactive page
Usage
/visualize <source…|"topic"> [--out <file.html>] [--lang <code>] [--publish|--no-publish]
Examples:
/visualize docs/design/investigation.md/visualize docs/spec.md docs/adr/0007-storage.md --out docs/storage-explainer.html/visualize "how the release pipeline promotes a build" --lang en/visualize notes/retro.md --publish
The command exists so a headless run or a scheduled routine has a stable entry point that does not depend on the skill being picked from free text.
What it does — and does not do
This is a thin proxy. It parses $ARGUMENTS, checks the shape of the sources and flags, and
delegates everything else to the visual-explainer skill
(plugins/architecture-pack/skills/visual-explainer/SKILL.md), which owns reading the source, the page plan,
building from the shell, verification and delivery.
It does not read the sources' content, choose visuals, write HTML, start a browser or publish anything. If guidance on how a page should look or how to verify it ever appears here, it leaked out of the skill and belongs back there.
Argument parsing failure → print the usage error and stop. Never start the skill on an unparseable argument.
Argument parsing
<source…|"topic">(required, one or more) — each positional is either an existing file (.md,.markdown,.txt,.rst,.adoc,.html) or, when it is a single quoted string that is not a path, a topic to explain from the conversation and the repository. A path that does not exist → error naming it, and stop.--out <file.html>— optional; must end in.html. Omitted → the skill writes<first-source-stem>.explainer.htmlnext to the first source (for a topic: the current directory, slugged from the topic).--lang <code>— optional; must match^[a-z]{2}(-[A-Za-z]{2})?$. Omitted → the language of the source.--publish/--no-publish— optional and mutually exclusive. Omitted → the skill asks whether to publish once the page is verified, and only when a publishing tool is available.
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.
- 15d ago First seen · 113 lines · 64 tokens per session scan A b427fdca54bf
visualize is a command published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed 3d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,308 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-03.
Other commands, from other repositories
excalidraw
Create or modify an editable Excalidraw diagram.
design-import
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…
design-ship
One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…
specialization
Train agents to become experts in specific domains for better performance.
gws-keep
List and read Google Keep notes.
agenda
Show upcoming calendar events.