Borrowing it
Nothing to install: this file belongs to tykisgod/quick-question. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tykisgod/quick-question/main/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/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.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.03797 | $0.03797 |
| Opus 5.5 | $0.01519 | $0.01519 |
| Sonnet 5.5 | $0.00759 | $0.00759 |
| Haiku 4.5 | $0.00380 | $0.00380 |
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 5d 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 — 150 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 28 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: compile and test drive the open Editor through the official Unity CLI (unity command / unity job), with tykit only as a fallback in projects that still have it; 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 (MCP) or by calling the scripts directly.
Repository Structure
hooks/hooks.json— Hook definitions (PreToolUse, PostToolUse, Stop, SessionStart, SessionEnd) 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)scripts/qq-frames-to-mp4.py,scripts/qq-contact-sheet.py,scripts/qq-review-page.py(shared helpers inscripts/qq_media.py) —/qq:recordmedia pipeline: frames or video → captioned web-ready mp4, contact sheets for self-check, review page
engines/— Per-engine assets (unreal/,godot/,sbox/); referenced by the install flowshared/— Shared prompt fragments (e.g.verification-prompt.md)bin/— Wrapper executables. Skills call them as${CLAUDE_PLUGIN_ROOT}/bin/<name>; Claude Code does not put them on PATH, so a bare name exits 127.qq/— Runtime data written inside target projects (runs/,state/,telemetry/), not in this reposkills/— 28 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). qq no longer installs it; it stays for standalone use and for projects that still depend on it.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, and engine bridges into a target project (auto-detects engine; supports--wizard,--preset,--profile,--modules,--without); the module list lives inscripts/qq_internal_install.pytest.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.
- 5d ago Changed · +1 lines · +70 tokens per session 48134ba60fdc
- 7d ago Changed · +6 lines · +419 tokens per session f58b7486ccc6
- 9d ago Changed · +11 lines · +295 tokens per session 6a3e5d38368b
- 13d ago Changed · +15 tokens per session 06ba0174f2d0
- 15d ago Changed · +186 tokens per session e3ce37473e4a
- 1mo 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 (12 stars, last pushed 3d ago), licensed MIT. It adds 3,797 tokens to every session, about $0.0152 per session on Opus 5.5. 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
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.