contextcortex: Skill for Claude Code

.agents/skills/caddy-preview/SKILL.md

agent-preview is a skill for Claude Code, Codex from spelech/contextcortex. It costs 43 tokens per session (690 once invoked), scanned A, original, MIT.

A way to present generated visual work, interactive HTML or JavaScript apps, web mockups, charts, images, and reports through a live browser preview over a remote SSH connection.

In plain words
What is it for?
Use it when creating visual artifacts or browser-based demos that need to be shown during a remote SSH session.
Why use it?
It gives users a browser view of work produced on a remote machine instead of leaving them with files or terminal output alone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is spelech/contextcortex's own configuration. It tells Claude Code and Codex how to work on contextcortex 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 contextcortex configures →

Reuse

Borrowing it

Nothing to install: this file belongs to spelech/contextcortex. 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/spelech/contextcortex/main/.agents/skills/caddy-preview/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/spelech/contextcortex

Made for: Claude Code, Codex.

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 agent-preview

README.md
[![agentmods](https://agentmods.dev/badge/skills/spelech/contextcortex/caddy-preview/github.svg)](https://agentmods.dev/skills/spelech/contextcortex/caddy-preview)
Your own site
<a href="https://agentmods.dev/skills/spelech/contextcortex/caddy-preview"><img src="https://agentmods.dev/badge/skills/spelech/contextcortex/caddy-preview/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 agent-preview

Your own site · 80×15
<a href="https://agentmods.dev/skills/spelech/contextcortex/caddy-preview"><img src="https://agentmods.dev/badge/skills/spelech/contextcortex/caddy-preview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 690 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00043 $0.00690
Opus 5.5 $0.00017 $0.00276
Sonnet 5.5 $0.00009 $0.00138
Haiku 4.5 $0.00004 $0.00069

Measured 2mo ago against content hash 302b572760bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-preview 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 2mo 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.

.agents/skills/caddy-preview/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Preview Hub (agent-preview)

The Agent Preview Hub provides a persistent, zero-friction preview subdomain (https://preview.wileyriley.com/<id>/ and http://preview.lan/<id>/) where agents can instantly host and share visual artifacts, web applications, charts, diagrams, or HTML reports without restarting Caddy.

When to Use

Use agent-preview whenever:

  • You create an HTML mockup, single-page app (React/Vue/Vite), or interactive web component for the user to inspect.
  • You generate visual diagrams, charts (Chart.js/D3/Plotly), or images that are hard to view over remote SSH terminals.
  • You produce test coverage reports, Playwright traces, or benchmark dashboards.
  • The user asks to "show me", "preview this", or "render this".

CLI Commands

The CLI utility is available globally as agent-preview (or publish-preview):

1. Publish a Directory / Built Webapp

agent-preview publish <slot-id> <source_dir> --title "My App Title" --category "Web App" --tags "React,Vite"

Copies the directory into the preview engine and generates the live URL.

2. Publish Inline HTML / Markdown Text

agent-preview text <slot-id> "<div class='p-6'><h1>Report Title</h1><p>Status: All checks passed.</p></div>" --title "Status Report"

Instantly creates an index.html with Tailwind styling.

3. Publish a Standalone Image / Diagram

agent-preview publish <slot-id> /path/to/diagram.png --title "Architecture Diagram v2"

Copies the image and generates a viewer wrapper.

4. Register a Live Dev Server / Container Port

agent-preview port <slot-id> <port_number> --title "FastAPI Live Demo"

Creates a live bridge to https://p-<port>.wileyriley.com (or https://preview.wileyriley.com/port/<port>/) without modifying Caddy.

5. Pin / Retention Control

By default, preview slots have a 7-day auto-TTL. Pass --keep or run pin to make it permanent:

agent-preview publish <slot-id> <path> --keep
# Or pin existing:
agent-preview pin <slot-id>

Read the full file on GitHub · 68 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. 2mo ago First seen · 68 lines · 43 tokens per session scan A 302b572760bb

Subscribe to this mod's changes

agent-preview is a skill published in the GitHub repository spelech/contextcortex (0 stars, last pushed 9d ago), licensed MIT. It adds 43 tokens to every session and 690 once invoked, about $0.0002 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 2026-08-31.

Related

agent-preview compared with skills from other repositories

agent-preview next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agent-previewspelech/contextcortexSkill09d agoMITA43Claude Code, Codex
swagjmagar/swag-mcpSkill74d agoMITA118Claude Code
@elad12390/web-research-assistantelad12390/web-research-assistantSkill99d agoMITA150Claude Code, Codex
scrape-batchn24q02m/wet-mcpSkill171mo agoApache-2.0A84Claude Code
genpark-vision-coderalphaparkinc/genpark-vision-coderSkill97d agoMITA28Claude Code, Codex
archivebox-web-archivingKnuckles-Team/archivebox-apiSkill1yesterdayMITA127Claude Code, Codex
genpark-magic-uialphaparkinc/genpark-magic-uiSkill97d agoMITA12Claude Code, Codex