Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add gopherguides/gopher-ai/plugin install tailwindWrote 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/gopherguides/gopher-ai/optimize)<a href="https://agentmods.dev/commands/gopherguides/gopher-ai/optimize"><img src="https://agentmods.dev/badge/commands/gopherguides/gopher-ai/optimize/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/gopherguides/gopher-ai/optimize"><img src="https://agentmods.dev/badge/commands/gopherguides/gopher-ai/optimize.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 | $0.00007 | $0.03898 |
| Opus 5.5 | $0.00003 | $0.01559 |
| Sonnet 5.5 | $0.00001 | $0.00780 |
| Haiku 4.5 | $0.00001 | $0.00390 |
Grade A, and why
optimize 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 1mo 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize Tailwind CSS
If $ARGUMENTS is empty or not provided:
Analyze Tailwind CSS output and provide optimization recommendations.
Usage: /tailwind-optimize [path] [options]
/tailwind-optimize— quick analysis/tailwind-optimize ./apps/storefront— analyze one project or subtree/tailwind-optimize ./src/app.css— analyze a specific Tailwind entry/tailwind-optimize --report— detailed report/tailwind-optimize --fix— apply safe optimizations
Analyzes: bundle size (dev vs prod, gzipped) · source coverage (@source paths cover all templates) · unused classes (in CSS but not templates) · CSS variable bloat · build performance.
Proceed with optimization analysis.
If $ARGUMENTS is provided:
Parse arguments:
- Path — directory or file (default: current directory)
--report— detailed markdown report--fix— apply safe optimizations--verbose— show all findings
Bind the requested or implicitly derived path to <OPTIMIZE_TARGET> as a
concrete normalized path. If no path was supplied, bind the current directory.
Stop with a clear error when the target does not exist. Resolve the containing
project or package root to <PROJECT_ROOT> for build configuration and local
dependency lookup, but never use <PROJECT_ROOT> as a replacement discovery
target.
Bind <SUPPORTED_SOURCE_EXTENSIONS> once to the project's complete source set
and use it for target validation, directory discovery, @source verification,
<TEMPLATE_FILES>, class inventory, reporting, and fixes. The baseline set is:
js, jsx, ts, tsx, html, htm, templ, vue, svelte, astro,
php, blade.php, erb, hbs, md, mdx, ejs, twig, liquid, njk,
nunjucks, pug, jade, haml, slim, razor, and cshtml.
This baseline is not an allowlist. Tailwind scans non-ignored plain-text source
files, so add every other text source selected by an @source rule or the
chosen build integration. Exclude CSS, binary files, lockfiles,
node_modules, and ignored paths using Tailwind's source-detection rules.
Never omit a target-associated source merely because its extension is absent
from the baseline.
When <OPTIMIZE_TARGET> is a directory, limit CSS entries, generated
artifacts, and templates to that subtree. When it is a CSS file, bind that file
directly to <CSS_ENTRY> and derive <TEMPLATE_FILES> only from its @source
rules and the selected integration's content scope. When it is a supported
template file, use that file as the complete <TEMPLATE_FILES> set and locate
only the Tailwind entry associated with its containing integration. For any
other file type, stop with a clear unsupported-target error.
Retain the complete <TEMPLATE_FILES> set for every later analysis and fix;
do not widen discovery to ..
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.
- 1mo ago Changed 9ddd3c13e0bd
- 1mo ago First seen · 375 lines · 7 tokens per session scan A 24e9a44779cc
optimize is a command published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed yesterday), licensed MIT. It adds 7 tokens to every session and 3,898 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
/a11y-audit
Auditoría de accesibilidad WCAG 2.2 completa con escaneo de HTML/componentes. Detecta: alt text faltante, problemas de contraste, navegación por teclado, etiquetas ARIA, gestión de focus, jerarquía de encabezados, etiquetas de formularios. Genera reporte accionable con instrucciones de remediación.
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
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.
wcag-audit
Accessibility audit based on WCAG 2.1/2.2 and the axe-core reference.
revisar-ui
Auditoria visual retroativa de 6 pilares do código frontend implementado.
frontend-design
Read and follow the instructions in agents/frontend-design/design-all.md. Also read all referenced files in agents/frontend-design/reference/ as needed for the task.