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/thestack-ai/swing-skills/swing-optionsnpx skills add TheStack-ai/swing-skills --skill swing-optionsgit clone --depth 1 https://github.com/TheStack-ai/swing-skillsWrote 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/thestack-ai/swing-skills/swing-options)<a href="https://agentmods.dev/skills/thestack-ai/swing-skills/swing-options"><img src="https://agentmods.dev/badge/skills/thestack-ai/swing-skills/swing-options.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 | $0.00082 | $0.02554 |
| Opus 5 | $0.00041 | $0.01277 |
| Sonnet 5 | $0.00016 | $0.00511 |
| Haiku 4.5 | $0.00008 | $0.00255 |
Grade A, and why
swing-options 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creativity Sampler
Probability-weighted option generator that fights typicality bias and surfaces unconventional alternatives. The core value is exposing hidden assumptions behind the "obvious" choice.
Addresses the cognitive failure of Anchoring Bias — AI defaults to the first or most obvious solution without exploring the full decision space, causing users to miss superior alternatives they never considered.
Rules (Absolute)
- Generate exactly 5 options by default. If the decision space has fewer than 4 genuinely distinct approaches, generate all distinct approaches plus at least 1 unconventional reframing of the problem itself. Never pad with trivially different variations of the same idea. If the user specifies a different count, respect it.
- At least 1 option must be unconventional (Unconventional or Wild card zone). This is the whole point — surface ideas that would normally be suppressed.
- Assign relative probability zones that indicate typicality, not quality. Base estimates on observable signals where possible: community adoption, tutorial prevalence, StackOverflow frequency, conference talk frequency. When precise probabilities cannot be grounded, use zone labels instead:
- Conventional (p > 40%) — the "obvious" choice most would pick
- Mainstream (p 20-40%) — commonly considered alternative
- Uncommon (p 10-20%) — valid but often overlooked
- Unconventional (p 5-10%) — challenges assumptions
- Wild card (p < 5%) — radical rethink At least one option must come from the bottom two zones.
- Lower probability = more creative, not worse. Explicitly frame low-p options as valuable exploration.
- No default recommendation. Present all options as viable. Let the user decide after seeing trade-offs.
- Trade-off analysis is mandatory. Each option must have concrete pros/cons, not vague descriptions.
- Ambiguous inputs require clarification. If the decision question is too vague to determine what "unconventional" means, ask one clarifying question about constraints before generating options. Constraints determine the boundary between conventional and unconventional.
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 First seen · 225 lines · 82 tokens per session scan A b9282da8ca83
swing-options is a skill published in the GitHub repository TheStack-ai/swing-skills (40 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 2,554 once invoked, about $0.0004 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
prompting-buddy
Generate, review, and optimize project-level prompt files for Claude Code -- including CLAUDE.md, .claude/rules/.md, and .claude/agents/.md. Use this skill whenever someone mentions CLAUDE.md, AGENTS.md, project prompts, coding instructions, agent definitions, rules files, or asks for help setting up Claude Code for a…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
skill-curator
中文 Skill 收录评估器。用于核验 GitHub 上的 Claude Code、Codex、Agent Skills、Plugin、MCP、CLI 或 Agent 工作流是否值得加入精选列表；检查真实资产、安装方式、活跃度、重复项和安全边界，并生成分类、中文描述与可追溯证据。.
git-workflow
安全处理 Git 状态检查、提交信息、commit、分支、push、PR 和 rebase。用于用户要求检查改动、生成或创建提交、管理分支、推送、发起 PR 或整理历史时；严格区分每个动作的授权，并保护工作树中已有和无关的修改。.
i18n-helper
国际化/本地化助手 — 扫描代码中的硬编码文本、生成 i18n 配置、批量翻译.
log-analyzer
日志分析助手 — 智能解析日志文件，识别异常模式，定位问题根因.