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/tykisgod/quick-question/claude-mdgit clone --depth 1 https://github.com/tykisgod/quick-questionWrote 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/tykisgod/quick-question/claude-md)<a href="https://agentmods.dev/instructions/tykisgod/quick-question/claude-md"><img src="https://agentmods.dev/badge/instructions/tykisgod/quick-question/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 | $0.02812 | $0.02812 |
| Opus 5 | $0.01406 | $0.01406 |
| Sonnet 5 | $0.00562 | $0.00562 |
| Haiku 4.5 | $0.00281 | $0.00281 |
Grade A, and why
quick-question 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 — 132 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
quick-question is the agent control plane for game-dev work. It is a Claude Code plugin and an engine-agnostic runtime: artifact-driven control (/qq:go), auto-compile hooks, test pipelines, deterministic policy checks, dual-mode cross-model / Claude-only code review with a verification loop, and 26 skills (/qq:*). It targets macOS and Windows (Windows requires Git for Windows for bash + core utilities). Engines at runtime parity: Unity 2021.3+, Godot 4.x, Unreal 5.x, S&box. Unity has the deepest integration via tykit (in-process HTTP server); the other three reach parity through Python bridges.
Although Claude Code gets the deepest integration (slash commands, hooks, review gates), the runtime core is agent-agnostic: scripts and bridges are plain shell + Python, and .qq/ state is plain JSON. Codex CLI, Cursor, Continue, and any MCP-compatible host can use the same runtime through qq_mcp.py / tykit_mcp.py / direct HTTP.
Repository Structure
hooks/hooks.json— Hook definitions (PreToolUse, PostToolUse, Stop, SessionStart) loaded by the Claude Code plugin systemscripts/— Bash + Python runtime: compile / test / review dispatchers, hook helpers, MCP bridges, controller, runtime helpersscripts/hooks/— Hook implementations (auto-compile.sh,compile-gate-check.sh,review-gate.sh,pre-push-test.sh,skill-modified-track.sh,auto-sync.sh,session-cleanup.sh,auto-pipeline-*,execute-resume-hint.sh)scripts/platform/— OS detection helpersscripts/qq_engine.py— multi-engine source-file matcher (matches-source)scripts/qq-compile.sh— multi-engine compile dispatcher (delegates tounity-compile-smart.sh/godot-compile.sh/unreal-compile.sh/sbox-compile.sh)scripts/qq-test.sh— multi-engine test dispatcherscripts/qq-project-state.py— artifact-driven controller (preferred path for/qq:go)scripts/qq-policy-check.sh— deterministic policy checks (run before deeper review workflows)scripts/qq-decisions.py— cross-skill decision journal (session-decisions.json)
engines/— Per-engine assets (unreal/,godot/,sbox/); referenced by the install flowshared/— Shared prompt fragments (e.g.verification-prompt.md)bin/— Wrapper executables added to Claude Code's PATH soSKILL.mdcan call commands by bare name.qq/— Runtime data written inside target projects (runs/,state/,telemetry/), not in this reposkills/— 26 skill directories, each with aSKILL.md, invoked as/qq:<name>packages/com.tyk.tykit/— UPM package providing tykit (in-process HTTP server inside Unity Editor).claude-plugin/— Plugin manifest (plugin.json,marketplace.json)templates/—CLAUDE.md.example,AGENTS.md.example,qq.yaml.examplecopied into target projects byinstall.shinstall.sh— Installs scripts, templates, bridges, and tykit into a target project (auto-detects engine; supports--wizard,--preset,--profile,--modules,--without)test.sh— Self-tests: shellcheck, JSON validation, executable bits, README consistency (skill count + per-skill/qq:reference), benchmark suites
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 · 132 lines · 2,812 tokens per session scan A 40689c7ed2db
quick-question CLAUDE.md is an instructions file published in the GitHub repository tykisgod/quick-question (11 stars, last pushed 9d ago), licensed MIT. It adds 2,812 tokens to every session, about $0.0141 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
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
game-design-lenses AGENTS.md
Instructions for EthanM2025/game-design-lenses, covering how to install (codex / generic), integration block (copy this into your project's agents.md), game design lens review (game-design-lenses) and notes.
blabberer CLAUDE.md
Instructions for HistOracle-production/blabberer, covering claude.md — blabberer, what this project is, claude code plugin, plugin structure and skills.
godot-superpowers CLAUDE.md
Instructions for Simone-Tarantino/godot-superpowers, covering claude.md, what this repo is, layout, editing rules for this repo and developing this plugin.
wow-addon-dev CLAUDE.md
Instructions for DennysOliveira/wow-addon-dev, a project described as: WoW addon development skills for Claude Code — Midnight 12.0+ Secret Values, API migration, templates.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).