agentmods.dev

quick-question AGENTS.md

Repository instructions for Quick Question, a game-development agent control plane that coordinates tasks, tests, reviews, and policy checks. They define when large refactors are allowed and how trust levels limit access to source files and command interfaces.

In plain words
What is it for?
Use them to guide refactoring decisions and configure work mode, verification requirements, and trust boundaries when developing with the Quick Question system.
Why use it?
They help agents choose clear end states while keeping permissions and the amount of automatic access appropriate to the task.

Instructions file for CodexOpenCode

11 7d ago A scan 793 tokens original MIT
View the source file tykisgod/quick-question
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/tykisgod/quick-question/agents-md
Clone the repo
git clone --depth 1 https://github.com/tykisgod/quick-question

Made for: Codex, OpenCode.

Per session 793 This file is loaded in full into every session.
When invoked 793 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 $0.00793 $0.00793
Opus 5 $0.00396 $0.00396
Sonnet 5 $0.00159 $0.00159
Haiku 4.5 $0.00079 $0.00079

Measured 2d ago against content hash 8f1791046da8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quick-question AGENTS.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 2d 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.

AGENTS.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Refactoring Authority

This repository explicitly allows aggressive refactoring when it improves the design.

  • Large-scale refactors, full rewrites, file moves, and architectural cleanup are allowed.
  • Backward compatibility is not required unless a task explicitly asks for it.
  • Prefer the cleanest end-state over incremental compatibility layers.
  • Remove obsolete code paths instead of preserving them out of habit.

Default Engineering Bias

  • Optimize for clarity, fewer layers, and stronger core abstractions.
  • If the current shape is fighting the design, rewrite it instead of patching around it.
  • Keep migration logic only when there is a real user or release requirement.

Trust Levels

qq.yaml supports a separate trust_level knob:

  • trusted: current internal-team default
  • balanced: only widen Codex into the source worktree for closeout-like flows
  • strict: require explicit --allow-source-worktree and keep raw engine commands off the standard MCP surface

When touching host wrappers or MCP exposure, preserve this split:

  • work_mode = task stage
  • policy_profile = verification floor
  • trust_level = automatic permission boundary

Historical note: earlier versions had a "Context Capsule" consumption mechanism that the balanced level disabled. Context Capsule was removed in v1.10.0 — the trust-level split above reflects the current shape.

Execution Environment Split

When developing this repository, treat execution environments as a hard split:

  • Use worktrees to isolate tasks.
  • Use Docker / Dev Container for repository-side development:
    • scripts/*.sh
    • scripts/*.py
    • README
    • docs
    • install.sh
    • test.sh
    • policy / doctor / controller / runtime-core changes
  • Use the host machine for engine-specific validation:
    • tykit and other engine bridges
    • engine compile / test routing (Unity, Godot, Unreal, S&box)
    • real project install flow
    • Editor-backed Claude / Codex E2E
    • any check that depends on a live engine Editor

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 793 tokens per session scan A 8f1791046da8

Subscribe to this mod's changes

quick-question AGENTS.md is an instructions file published in the GitHub repository tykisgod/quick-question (11 stars, last pushed 7d ago), licensed MIT. It adds 793 tokens to every session, about $0.0040 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.

Code reviewGame developmentTestingauto-compileclaude-codeclaude-code-pluginclaude-skillscodex
Related

Other instructions, from other repositories

Claw3D AGENTS.md

Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.

iamlukethedev/Claw3D · 608 tokens

GameDesignOS AGENTS.md

Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.

DY-2026/GameDesignOS · 972 tokens

Hermes3D AGENTS.md

Instructions for iamlukethedev/Hermes3D, covering agent instructions, development environment instructions, service overview, running the app and lint, typecheck, and tests.

iamlukethedev/Hermes3D · 577 tokens

awesome-defold AGENTS.md

Instructions for astrochili/awesome-defold: When asked to process the resource inbox, use GitHub issue #16 unless another issue is named.

astrochili/awesome-defold · 271 tokens

unity-code-style-guide AGENTS.md

Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.

krogh-jacobsen/unity-code-style-guide · 4,528 tokens

unreal-mcp CLAUDE.md

Instructions for GenOrca/unreal-mcp, covering claude.md, what this is, architecture (the non-obvious parts), commands and all run from mcp-server/.

GenOrca/unreal-mcp · 2,258 tokens