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 skills/tykisgod/quick-question/gonpx skills add tykisgod/quick-question --skill gogit clone --depth 1 https://github.com/tykisgod/quick-questionWhat 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 | $0.00020 | $0.03064 |
| Opus 5 | $0.00010 | $0.01532 |
| Sonnet 5 | $0.00004 | $0.00613 |
| Haiku 4.5 | $0.00002 | $0.00306 |
Grade A, and why
go scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Script path fallback: qq scripts are invoked as bare commands (e.g.
unity-test.sh). If "command not found", use${CLAUDE_PLUGIN_ROOT}/bin/<command>instead.
Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).
Entry point for the qq development workflow. Detects your current state and guides you to the right skill.
This skill is a controller, not an implementation engine. It should read real project state first and only fall back to prompt/context heuristics when the state is ambiguous.
Hard Rules
- If
qq-project-state.pyis available, you must run it before inspecting git history, branch divergence, commit counts, or repo-wide document context. - If
qq-project-state.pyreturns valid JSON, treat it as the primary source of truth. - When project state is available, do not summarize branch size, recent commits, or unrelated repo-wide artifacts unless the user explicitly asked for that analysis.
- Keep the answer short and action-oriented:
- current
work_mode - current
policy_profile - current
recommended_next - one-sentence why
- current
- Do not turn
/qq:gointo a repo audit. It is a router. - Do NOT explain the pipeline order (design → plan → execute). The user already knows. Just recommend the next step and ask to proceed.
Arguments: $ARGUMENTS
- A file path (design doc, plan, or code file)
- A brief description of what to build
--auto: mode-aware automation, no prompts--no-worktree: skip automatic worktree creation for this invocation- No arguments: auto-detect from context
Worktree Isolation (before routing) — strict
Before routing to any skill, ensure the session is in an isolated worktree. This runs automatically — the user does not need to pass any flags.
Skip ONLY if one of these is explicitly true:
- Already in a worktree (check
git rev-parse --show-toplevelmatches an entry ingit worktree listother than the main repo root) - User passed literal
--no-worktreetoken in arguments (not "semantically meant" — agent-invented bypass is forbidden) - The recommended next step is a read-only action (
/qq:changes,/qq:deps,/qq:explain,/qq:brief,/qq:full-brief,/qq:timeline)
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.
- 2d ago First seen · 194 lines · 20 tokens per session scan A 50559b42ad4d
go is a skill published in the GitHub repository tykisgod/quick-question (11 stars, last pushed 7d ago), licensed MIT. It adds 20 tokens to every session and 3,064 once invoked, about $0.0001 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 skills, from other repositories
geometry-and-math
Use this skill when using Phaser 4 math and geometry utilities. Covers vectors, rectangles, circles, triangles, polygons, random number generation, angles, distance, interpolation, and snapping. Triggers on: Vector2, Rectangle, Circle, math, distance, angle, random, lerp.
text-and-bitmaptext
Use this skill when displaying text in Phaser 4. Covers Text game objects, BitmapText, web fonts, text styling, word wrap, alignment, padding, and dynamic text content. Triggers on: Text, BitmapText, this.add.text, font, word wrap, text style.
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
assets-create-folder
Create a new folder under a parent folder inside 'Assets/'. The parent path must start with 'Assets/' and every intermediate folder in it must already exist. Refreshes the AssetDatabase at the end and returns the GUID(s) of the created folder(s).
assets-prefab-save
Save the currently opened prefab edit stage back to its prefab asset without exiting the stage. Pair with 'assets-prefab-open' to enter the edit mode first.
mobile-games
Mobile game development principles. Touch input, battery, performance, app stores.