Agent-Quest CLAUDE.md

Agent-Quest CLAUDE.md is an instructions file for coding agents from FulAppiOS/Agent-Quest. It costs 851 tokens per session, scanned A, original, MIT.

Project instructions for Agent Quest, a browser dashboard that shows Claude Code and Codex sessions as characters moving through a game-like village. They explain its Bun and Hono server, session monitoring, WebSockets, and project architecture.

In plain words
What is it for?
Use them when developing, running, or troubleshooting Agent Quest's session discovery, log polling, event updates, providers, and visual activity mapping.
Why use it?
They help a coding agent understand where the monitoring data comes from and how the server and browser interface communicate.

Instructions file

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 instructions/fulappios/agent-quest/claude-md
Clone the repo
git clone --depth 1 https://github.com/FulAppiOS/Agent-Quest

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-Quest CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fulappios/agent-quest/claude-md.svg)](https://agentmods.dev/instructions/fulappios/agent-quest/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fulappios/agent-quest/claude-md"><img src="https://agentmods.dev/badge/instructions/fulappios/agent-quest/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 851 This file is loaded in full into every session.
When invoked 851 The same file — it is already loaded in full.
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 $0.00851 $0.00851
Opus 5 $0.00426 $0.00426
Sonnet 5 $0.00170 $0.00170
Haiku 4.5 $0.00085 $0.00085

Measured 4d ago against content hash be479e12e84f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Agent-Quest CLAUDE.md 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 4d 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.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Agent Quest is a browser-based monitoring dashboard that visualizes active Claude Code and Codex agent sessions as fantasy heroes in a 2D WoW-style village. Each agent is represented as a hero character that walks between buildings corresponding to its current activity (Read → Library, Edit → Forge, Bash → Arena, etc.).

Architecture

Two-process monorepo:

  • server/ — Bun + Hono backend. Two providers run in parallel: ClaudeProvider auto-discovers every ~/.claude* directory with a projects/ subdir (e.g. ~/.claude, ~/.claude-work, ~/.claude-personale); CodexProvider watches ~/.codex/sessions/ for Codex rollout files. Both poll their session logs every 2-3s, parse events into AgentState objects, push updates over native Bun WebSocket. Each AgentState carries its configDir and a source field ('claude' | 'codex') so the UI can distinguish installations and providers. Optional Hono endpoint receives Claude Code postToolUse hooks for lower-latency events — Claude Code only; Codex doesn't expose hooks. SessionRegistry (pidfile oracle) is also Claude-only by design; Codex liveness is inferred purely from rollout-file activity.
  • client/ — React 19 + Phaser 4 "Caladan" frontend. Fullscreen Phaser canvas renders the village; React overlay panels (Party Bar, Activity Feed, Detail Panel, Minimap, Top Bar) sit on top via ref-based bridge pattern (useRef + useEffect + EventEmitter).

Data flow: ~/.claude*/projects/**/*.jsonl and ~/.codex/sessions/**/rollout-*.jsonl → ClaudeProvider / CodexProvider → SessionParser (per-format) → AgentStateManager → WebSocket → Browser (React state + Phaser scene).

Commands

bun start              # Start both server and client (concurrently)
bun run dev:server     # Server only on localhost:4444
bun run dev:client     # Client only on localhost:4445
bun run check:assets   # Verify every bundled sprite referenced by the theme exists on disk

Read the full file on GitHub · 53 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. 4d ago First seen · 53 lines · 851 tokens per session scan A be479e12e84f

Subscribe to this mod's changes

Agent-Quest CLAUDE.md is an instructions file published in the GitHub repository FulAppiOS/Agent-Quest (128 stars, last pushed 2mo ago), licensed MIT. It adds 851 tokens to every session, about $0.0043 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.