swarm: Command for Claude Code

.claude/commands/deploy_blog.md

deploy_blog is a command for Claude Code from swarm-ai-research/swarm. It costs 0 tokens per session (1,111 once invoked), scanned A, original, MIT.

A command that builds and publishes the SWARM blog and documentation site to Vercel. Vercel is a hosting service for websites and web applications.

In plain words
What is it for?
Use it for a production deployment, optionally checking specified URLs and confirming that interactive pages render correctly.
Why use it?
It checks that the site builds before publishing and verifies pages that depend on browser-run JavaScript, which a basic HTTP check cannot test.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is swarm-ai-research/swarm's own configuration. It tells Claude Code how to work on swarm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything swarm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to swarm-ai-research/swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/swarm-ai-research/swarm/main/.claude/commands/deploy_blog.md
Clone the repo
git clone --depth 1 https://github.com/swarm-ai-research/swarm

Made for: Claude Code.

Wrote 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.

agentmods badge for deploy_blog

README.md
[![agentmods](https://agentmods.dev/badge/commands/swarm-ai-research/swarm/deploy_blog/github.svg)](https://agentmods.dev/commands/swarm-ai-research/swarm/deploy_blog)
Your own site
<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/deploy_blog"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/deploy_blog/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.

agentmods 80×15 button for deploy_blog

Your own site · 80×15
<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/deploy_blog"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/deploy_blog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01111
Opus 5 $0.00000 $0.00556
Sonnet 5 $0.00000 $0.00222
Haiku 4.5 $0.00000 $0.00111

Measured 10d ago against content hash 38dc3960a8d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deploy_blog 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 10d 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.

page renders — `curl`/WebFetch do not execute JS, so a deploy can report
.claude/commands/deploy_blog.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/deploy_blog

Build and deploy the SWARM blog/docs site to Vercel production.

Usage

/deploy_blog or /deploy_blog --verify [URL ...]

Behavior

  1. Run mkdocs build locally to verify the site builds without errors.

    • Warnings about missing image targets are acceptable (pre-existing).
    • Actual build errors (syntax, missing plugins) must be fixed before deploying.
  2. Deploy to Vercel production:

    vercel --prod
    
  3. Verify deployment succeeded by checking the output for Production: URL.

  4. Render-verify any page that has client-side JavaScript (charts, live dashboards, anything that fetches data after load). HTTP 200 is NOT proof a page renders — curl/WebFetch do not execute JS, so a deploy can report READY while the page is visually broken. Use the headless-Chrome verifier:

    scripts/render-verify.sh "https://www.swarm-ai.org/bridges/gitlawb/" \
      --id-nonempty gl-count \
      --expect-text "Quality Distribution"
    

    The script renders the page in headless Chrome (running its JS), then:

    • flags any runaway <canvas> (backing dims past a sane cap) — the failure mode that silently blanked the Gitlawb dashboard in May 2026;
    • asserts JS-driven elements left their placeholder (--id-nonempty ID fails if text is empty / 0 / -- / Connecting...);
    • asserts expected/forbidden text (--expect-text / --reject-text);
    • saves a screenshot for a human to eyeball.

    Run it for every JS-bearing page touched by the deploy. A non-zero exit means the page is broken even though the deploy "succeeded" — investigate before declaring the deploy done. Pure static Markdown pages don't need it.

  5. Print the production URL, timestamp, and the render-verify summary.

--verify mode

/deploy_blog --verify [URL ...] runs only step 4 against the given URLs (or the dashboard pages under docs/bridges/ if none are given) without rebuilding or redeploying. Use it to re-check an already-live page, or after someone else deploys.

Read the full file on GitHub · 95 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. 10d ago First seen · 95 lines · 0 tokens per session scan A 38dc3960a8d9

Subscribe to this mod's changes

deploy_blog is a command published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,111 tokens. 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 2026-08-30.