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 skills add tykisgod/quick-question --skill design-researchgit 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/skills/tykisgod/quick-question/design-research)<a href="https://agentmods.dev/skills/tykisgod/quick-question/design-research"><img src="https://agentmods.dev/badge/skills/tykisgod/quick-question/design-research/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/skills/tykisgod/quick-question/design-research"><img src="https://agentmods.dev/badge/skills/tykisgod/quick-question/design-research.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 | $0.00059 | $0.00444 |
| Opus 5.5 | $0.00024 | $0.00178 |
| Sonnet 5.5 | $0.00012 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
design-research 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 1mo 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.
What it actually says
Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).
Search for game design references to the problem currently being discussed.
Arguments: $ARGUMENTS
Process
- Identify the core design question (e.g., "how trading between cities creates interesting choices")
- Search for game design analyses, GDC talks, postmortems, and design breakdowns using WebSearch
- Organize into a comparison table:
| Game | How they do it | What makes it fun | What we could borrow |
|---|
- Recommend which approach best fits this project's scope and feel, and why
- Save the result, sources included, to
Docs/qq/<branch-name>/<topic>_design-research.md(or wherever the project already keeps research notes; branch name fromgit branch --show-current | tr '/' '_'). If the project's instructions ask for research notes to be committed, commit that file alone, following them; otherwise leave it for/qq:commit-push
Notes
- Focus on the player experience, not implementation — "RimWorld uses a bill queue per workbench that lets players set min/max thresholds" is good; "WorkGiver_DoBill class" is not
- Prefer games the team has likely played or that are well-documented
- Include at least one game from a different genre if it solves the same design problem in an interesting way
- Tag every conclusion with its source: official material (dev blog, GDC talk, postmortem; link it), third-party analysis (link it), game source you actually read (for example, an open-source game), or own knowledge. If searching yields thin results, lean on your own knowledge of game design, tagged as such
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.
- 1mo ago Changed · -2 lines 979aa4fb1704
- 2mo ago First seen · 31 lines · 59 tokens per session scan A 74334e626d9c
design-research is a skill published in the GitHub repository tykisgod/quick-question (13 stars, last pushed 13d ago), licensed MIT. It adds 59 tokens to every session and 444 once invoked, about $0.0002 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.
design-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-researchtykisgod/quick-question | Skill | 13 | 13d ago | MIT | A | 59 | Claude Code |
| gemininowork-studio/notfair-plugin | Skill | 4.1k | 8d ago | MIT | A | 184 | Claude Code |
| auditoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 35 | Claude Code |
| boundariesoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 33 | Claude Code |
| triageoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 32 | Claude Code |
| security-architecture-reviewcbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 78 | Claude Code |
| pr-threads-addressposit-dev/skills | Skill | 554 | 4d ago | MIT | A | 48 | Claude Code |