plugin-first-web-dashboard

plugin-first-web-dashboard is a skill for Claude Code, Codex from ggg123124/vrchat-assistant. It costs 15 tokens per session (1,414 once invoked), scanned A, original, MIT.

A development guide for adding a web dashboard to a remote, plugin-based service that communicates through MCP. MCP is a standard way for an AI agent to call tools provided by another service.

In plain words
What is it for?
Building monitoring and operating screens for service health, authentication connections, online users, recent events, and plugin or backup status.
Why use it?
It helps keep the dashboard connected to existing data and service interfaces instead of duplicating core logic.

Skill for Claude CodeCodex

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

Install

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.

agentmods
npx agentmods add skills/ggg123124/vrchat-assistant/plugin-first-web-dashboard
Any agent
npx skills add ggg123124/vrchat-assistant --skill plugin-first-web-dashboard
Clone the repo
git clone --depth 1 https://github.com/ggg123124/vrchat-assistant

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 plugin-first-web-dashboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/plugin-first-web-dashboard.svg)](https://agentmods.dev/skills/ggg123124/vrchat-assistant/plugin-first-web-dashboard)
Your own site
<a href="https://agentmods.dev/skills/ggg123124/vrchat-assistant/plugin-first-web-dashboard"><img src="https://agentmods.dev/badge/skills/ggg123124/vrchat-assistant/plugin-first-web-dashboard.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.01414
Opus 5 $0.00008 $0.00707
Sonnet 5 $0.00003 $0.00283
Haiku 4.5 $0.00002 $0.00141

Measured yesterday against content hash 4a21de5bf1ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

plugin-first-web-dashboard 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 yesterday.

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/plugin-first-web-dashboard/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin-First Web Dashboard

Use when adding a web UI to a headless, MCP-first, plugin-oriented service—especially a service deployed remotely in Docker, NAS, or a router and expected to remain online without a local game/client process.

Core approach

Treat the dashboard as a Monitor / Operate surface, not a marketing page. Start from the existing repository contracts, then build a small vertical slice that proves the data path before adding visual breadth.

  1. Read the project README, agent/development rules, architecture docs, plugin API/loader docs, HTTP server, runtime context, storage API, and deployment manifest.
  2. Trace the existing data sources and tool handlers to their definitions. Reuse established read-only services instead of duplicating SQL or authentication logic.
  3. Keep concrete UI and dashboard routes in a plugin. Add only generic core infrastructure: route registration, authenticated dispatch, lifecycle cleanup, and narrowly scoped read-only service adapters.
  4. Define an MVP around the always-on advantage: service health, authentication/WebSocket state, online friends, recent events, and plugin/backup status. Exclude local-client features such as launching VRChat, SteamVR detection, game logs, tray behavior, and desktop memory tools unless the deployment explicitly supports them.
  5. Use a dark, dense, glanceable visual system with strong status hierarchy. Raycast/Linear-like precision is a useful reference, but transform the principles into an original UI rather than cloning a proprietary surface.
  6. Verify the implementation with syntax checks, repository smoke tests, diff checks, and an actual authenticated endpoint probe when a running deployment is available. Report skipped checks honestly.

Core/plugin boundary

The core should expose a minimal, explicit mechanism such as:

  • ctx.httpRoutes: a route registry owned by the core;
  • api.http.registerRoute({ method, path, handler }): plugin-only route registration;
  • authenticated dispatch before route execution;
  • route cleanup on unload and hot reload;
  • read-only services such as dashboard.snapshot, dashboard.friends, and dashboard.events.

Read the full file on GitHub · 99 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. yesterday First seen · 99 lines · 15 tokens per session scan A 4a21de5bf1ff

Subscribe to this mod's changes

plugin-first-web-dashboard is a skill published in the GitHub repository ggg123124/vrchat-assistant (21 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 1,414 once invoked, about $0.0001 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 2026-09-04.

Related

Other skills, from other repositories

no-mistakes

Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach upstream. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push safely, asks you to do a task and then validate it, or invokes /no-mistakes.

mnemosyne-oss/mnemosyne · 81 tokens

mnemosyne-context

Load this when working on the mnemosyne memory system — its repo, sync server, memory databases, or CI. Covers architecture, the surface/sync data model, dev workflow (tests/ruff/CI matrix), release policy, and known gotchas that are easy to get wrong. Use for any "mnemosyne" dev or devops task, or when a…

mnemosyne-oss/mnemosyne · 88 tokens

hermes-memory-providers

Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.

mnemosyne-oss/mnemosyne · 34 tokens

mnemosyne

Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.

mnemosyne-oss/mnemosyne · 22 tokens

mnemosyne-memory-override

Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.

mnemosyne-oss/mnemosyne · 46 tokens

hermes-self-evaluation

Use this skill when the user asks to audit, review, or optimize Hermes's own performance — analyzing session data, skills, configuration, costs, and usage patterns to identify improvements, automation opportunities, and system optimizations.

AtlasOmnia/donna-starter · 69 tokens