web-console

web-console is a skill for Claude Code, Codex from zylos-ai/zylos-core. It costs 32 tokens per session (957 once invoked), scanned A, original, MIT.

A built-in browser interface for communicating with Claude through a local web server. It includes conversation access, message sending, status checks, health checks, and attachment uploads.

In plain words
What is it for?
Use it to set up or configure the web console channel, start its server, send messages and attachments, view recent conversations, check Claude's status, or troubleshoot browser access.
Why use it?
It provides a browser-based communication channel without relying on services such as Telegram, Lark, or Discord. Because it listens locally by default, access is limited to the same computer unless configured otherwise.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/howard/zylos/web-console/media/wc-...png.

Good fit Use it to set up or configure the web console channel, start its server, send messages and attachments, view recent conversations, check Claude's status, or troubleshoot browser access.

Compare 6 skills from other repositories ↓
About the project

Zylos is open-source infrastructure that gives an AI agent persistent memory, scheduled activity, communication channels, and the ability to maintain and extend itself. Individuals and teams use it with Claude Code or Codex through Telegram, Lark, or a web console. Its catalogue add-ons define settings, instructions, and skills for operating the agent.

zylos-ai/zylos-core · 1,151 stars · on GitHub · zylos.ai

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 web-console

README.md
[![agentmods](https://agentmods.dev/badge/skills/zylos-ai/zylos-core/web-console/github.svg)](https://agentmods.dev/skills/zylos-ai/zylos-core/web-console)
Your own site
<a href="https://agentmods.dev/skills/zylos-ai/zylos-core/web-console"><img src="https://agentmods.dev/badge/skills/zylos-ai/zylos-core/web-console/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 web-console

Your own site · 80×15
<a href="https://agentmods.dev/skills/zylos-ai/zylos-core/web-console"><img src="https://agentmods.dev/badge/skills/zylos-ai/zylos-core/web-console.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 957 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 $0.00032 $0.00957
Opus 5 $0.00016 $0.00478
Sonnet 5 $0.00006 $0.00191
Haiku 4.5 $0.00003 $0.00096

Measured 10d ago against content hash 91b704d134f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

web-console 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 10d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (public/app.js, public/markdown-it.min.js, scripts/attachment-utils.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/web-console/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Console (C4 Built-in Channel)

Default communication channel - works without any external service.

Purpose

Allows users to communicate with Claude even without Telegram/Lark/Discord. This is the baseline, always-available interface.

Quick Start

# Install dependencies
cd ~/zylos/.claude/skills/web-console
npm install

# Start server (default port 3456)
node scripts/server.js

# Or with PM2
pm2 start scripts/server.js --name web-console

Access

Local only: http://127.0.0.1:3456

Server binds to 127.0.0.1 by default for security.

Architecture

Browser ──► Web Console Server ──► C4 Bridge ──► Claude
                  │
                  ▼
               SQLite (c4.db)

API Endpoints

Endpoint Method Description
/api/status GET Get Claude's current status
/api/conversations/recent GET Get recent conversation history
/api/upload POST Upload one attachment for the next message
/api/send POST Send message to Claude
/api/media/:messageId GET Download/render an outbound media message
/api/poll?since_id=N GET Poll for new messages
/api/health GET Server health check

Files

~/zylos/.claude/skills/web-console/
├── SKILL.md
├── package.json
├── scripts/
│   ├── server.js      # Express API server
│   └── send.js        # CLI message sender
└── public/
    ├── index.html     # Chat UI
    ├── styles.css     # Styling
    └── app.js         # Frontend logic

Environment Variables

Variable Default Description
WEB_CONSOLE_PORT 3456 Server port
ZYLOS_WEB_PASSWORD (empty) Set to enable password protection (also reads WEB_CONSOLE_PASSWORD as fallback)
WEB_CONSOLE_BIND 127.0.0.1 Bind address
ZYLOS_DIR ~/zylos Data directory
WEB_CONSOLE_MAX_UPLOAD_MB 20 Max size per uploaded attachment

Authentication

By default, no password is required (suitable for local access).

Read the full file on GitHub · 124 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 · 124 lines · 32 tokens per session scan A 91b704d134f3

Subscribe to this mod's changes

web-console is a skill published in the GitHub repository zylos-ai/zylos-core (1,151 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 957 once invoked, about $0.0002 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 2026-08-30.