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.
npx agentmods add instructions/fulappios/agent-quest/claude-mdgit clone --depth 1 https://github.com/FulAppiOS/Agent-QuestWrote 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/instructions/fulappios/agent-quest/claude-md)<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>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 | $0.00851 | $0.00851 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
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.
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:
ClaudeProviderauto-discovers every~/.claude*directory with aprojects/subdir (e.g.~/.claude,~/.claude-work,~/.claude-personale);CodexProviderwatches~/.codex/sessions/for Codex rollout files. Both poll their session logs every 2-3s, parse events intoAgentStateobjects, push updates over native Bun WebSocket. EachAgentStatecarries itsconfigDirand asourcefield ('claude' | 'codex') so the UI can distinguish installations and providers. Optional Hono endpoint receives Claude CodepostToolUsehooks 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
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.
- 4d ago First seen · 53 lines · 851 tokens per session scan A be479e12e84f
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.
Other instructions, from other repositories
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
autonomous-os AGENTS.md
AGENTS.md instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
agent-ship CLAUDE.md
Instructions for Agent-Ship/agent-ship, covering claude.md, project overview, commands, docker development (recommended) and local development (no docker).
clawock AGENTS.md
Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.
usage-guard AGENTS.md
Instructions for shirley-xue-2025/usage-guard, covering agent notes — usage-guard repo, before changing code, common setup failure, layout and public vs private.