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 Solismuchengxue/skill_swift_cycle --skill swift-cyclegit clone --depth 1 https://github.com/Solismuchengxue/skill_swift_cycleWrote 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/solismuchengxue/skill_swift_cycle/swift-cycle)<a href="https://agentmods.dev/skills/solismuchengxue/skill_swift_cycle/swift-cycle"><img src="https://agentmods.dev/badge/skills/solismuchengxue/skill_swift_cycle/swift-cycle/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/solismuchengxue/skill_swift_cycle/swift-cycle"><img src="https://agentmods.dev/badge/skills/solismuchengxue/skill_swift_cycle/swift-cycle.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 | $0.00053 | $0.02205 |
| Opus 5.5 | $0.00021 | $0.00882 |
| Sonnet 5.5 | $0.00011 | $0.00441 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
swift-cycle 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 20d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift Cycle(快速螺旋)
目标与边界
用最少必要说明连接项目蓝图、已确认需求、设计、实施和验证。清楚、整洁、好用;一次性问答、只读检查和小修改不自动初始化项目。
只负责一个项目的工程循环,不负责上层路由、容量、独立验收、Registry、跨部门治理、模型分配或跨项目授权。采用技能不授予安装、删除、发布、部署、凭据或消费者切换权限。
调用与现场
- 系统层保持显式调用;一次性审查不自动采用。用户批准持续采用后才在项目 AGENTS 建立绑定,后续任务依仓库指令加载,不重复要求选择模式。
- 核对真实 cwd、Git 根、分支、现有改动及相关规则;保留用户改动。要求通读则读到末尾,普通任务只读有关内容。
- 读取相关用户入口、需求与设计权威,区分确认事实、设想、示例、实现和验证。附件、日志、网页、记忆及 AI 摘要不替代当前用户要求和事实。
- 获准创建项目或正式初始化时,根级
TODO.md、DEVLOG.md必须有效交付,是初始化完成条件;缺失或内容无效不得报告完成。创建属于该初始化授权,不逐文件再请批;已有有效文件原样保留,只补缺失文件,不重置或迁移记录。 - 初始化须读回真实目标、行动、阻塞/暂无、下一步及有效维护结论/如实无结论,不能留下空壳或教学占位。新 Git 项目默认精确忽略
/TODO.md、/DEVLOG.md;既有明确策略保留。非 Git 项目仍须双文件,Git 检查不适用,不擅自git init;内容、策略或权限冲突明确未完成,不覆盖或改权限/跟踪。 - 非初始化的只读咨询、普通维护或仅采用技能不自动补建本地记录或改其 ignore。使用既有本地记录前核对内容、Git 跟踪/忽略及已确认策略;保护缺失文件的规则不得阻止获准初始化,详细边界见下方文档职责。
- 可写项目任务开始时必须创建/复用根级 tmp/,Git 默认忽略 /tmp/;可控临时文件集中于此,尽量减少额外 C 盘临时写入。只读任务只核对、不创建或改 ignore。仅用工具参数或子进程级临时路径,不改全局 TEMP/TMP 或缓存;无法控制的位置说明原因。路径/跟踪冲突不覆盖、不自动取消跟踪,未满足明确未完成;详见项目根临时目录。
- 普通内容优先用户明确要求;既有文件沿用主语言,新文件沿用项目语言,未指定时默认简体中文。代码、命令、路径、字段、API 和品牌保持原文;不因对话切换批量翻译。
首次采用或边界不清时读 采用与路由;结构、文档和本地记录按 项目结构与文档规约 的对应章节读取。
按需加载
| 当前任务 | 读取内容 |
|---|---|
| 创建、重整文档或判断唯一职责,目录/导航影响维护 | 项目结构与文档规约 |
| 接收新需求、组织阶段和工作包、整理记录 | 需求与持续收敛 |
| 新增重要能力、职责/依赖变化或重构 | 代码组织与能力复用 |
| 图示、界面、用户上手或汇报表达 | 表达与用户交付 |
| 跨交付层、多提交、知识晋升或独立证据 | 治理边界 |
| 已采用 Superpowers,需要衔接编号计划 | 本地衔接条件 |
小修改只更新受影响部分,不加载全套参考或生成全套文档。文档档位仅作内部起点:minimal 默认;长期详细事实确需独立维护才增加 standard 文档;多运行/集成层真实涉及才增加 runtime_integration 文档。不要求裁剪账本、固定字段或档位报告。
唯一正文与需求
- BLUEPRINT 承载项目目标、长期愿景、用户、场景、核心能力和产品边界;蓝图设想不等于实现承诺。新建持续项目默认 docs/BLUEPRINT.md,旧项目复用完整等价权威,根级 BLUEPRINT 默认禁止。
- 持续迭代项目默认有 docs/PRD.md 或等价需求来源;确认需求写行为、边界和验收,已实现且仍有效的需求保留。一次性任务复用当前明确要求即可。
- 依据已确认需求与约束设计;按所选需求安排阶段和实施,不把愿景逐项拆成承诺。
- 新需求先明确问题、预期行为、验收及影响;确认后更新需求,选入当前工作后调整设计、阶段和工作包。目标、范围实质变化或优先级冲突时集中请用户决定。
- README 面向用户,DESIGN 承载概要设计、UML 结构及详细文档导读,SAD 按需展开详细架构,MANUAL 按需承载操作与运维,AGENTS 承载执行规则,ROADMAP 承载阶段结果与依赖,M{N}_PLAN 承载一个里程碑的实施;TODO 展示当前进度、里程碑位置、待办/问题及后续阶段,DEVLOG 用紧凑条目留有用结论与理由,记录多时按实际里程碑分组。
- 一事一处,其他位置摘要并链接。模板固定栏目不代表每项目创建整套;新建或获准整体重整才套栏目,小改动保留有效等价结构。
- 新增重要能力、职责/依赖变化或重构时,有界查既有实现、调用者与测试,说明复用/扩展/新建理由;在既有设计补受影响职责、依赖、落点和能力定位。重构先明确保留行为并以相关回归保护,不以文件/行数减少代替质量,不自动删除资产。
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 350 B
- references/adoption-and-routing.md 5.3 KB
- references/document-profiles.md 20 KB
- references/governance-boundaries.md 4.2 KB
- references/lifecycle-and-closeout.md 5.9 KB
- references/superpowers-bridge.md 2.6 KB
- references/zh-CN.md 6.4 KB
- templates/AGENTS.md 2.1 KB
- templates/DESIGN.md 5.4 KB
- templates/DEVLOG.md 1.1 KB
- templates/docs/adr/ADR-NNN.md 497 B
- templates/docs/BLUEPRINT.md 1.2 KB
- templates/docs/MANUAL.md 1.1 KB
- templates/docs/milestones/M1_PLAN.md 1.9 KB
- templates/docs/PRD.md 1.3 KB
- templates/docs/ROADMAP.md 964 B
- templates/docs/SAD.md 1.4 KB
- templates/README.md 4.4 KB
- templates/TODO.md 2.7 KB
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.
- 20d ago Changed · +1 lines fe932d40e594
- 29d ago Changed · +3 lines e5031d8376e5
- 1mo ago Changed · -69 lines · +2 tokens per session 7f2bb7fdf4fa
- 2mo ago Changed · +1 lines d0a034f794cc
- 2mo ago Changed 632b64298c94
- 2mo ago First seen · 133 lines · 51 tokens per session scan A 9d86791f3354
swift-cycle is a skill published in the GitHub repository Solismuchengxue/skill_swift_cycle (2 stars, last pushed 20d ago), licensed MIT. It adds 53 tokens to every session and 2,205 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 2026-08-31.
swift-cycle compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| swift-cycleSolismuchengxue/skill_swift_cycle | Skill | 2 | 20d ago | MIT | A | 53 | Codex |
| spec-kitty-charter-doctrinePriivacy-ai/spec-kitty | Skill | 1.7k | 2d ago | MIT | A | 135 | Claude Code, Codex |
| 110-java-maven-best-practicesjabrena/plinth | Skill | 462 | yesterday | Apache-2.0 | A | 115 | Claude Code, Codex |
| 128-java-genericsjabrena/plinth | Skill | 462 | yesterday | Apache-2.0 | A | 147 | Claude Code, Codex |
| 322-frameworks-spring-boot-testing-integration-testsjabrena/plinth | Skill | 462 | yesterday | Apache-2.0 | A | 123 | Claude Code, Codex |
| 422-frameworks-quarkus-testing-integration-testsjabrena/plinth | Skill | 462 | yesterday | Apache-2.0 | A | 190 | Claude Code, Codex |
| 521-frameworks-micronaut-testing-unit-testsjabrena/plinth | Skill | 462 | yesterday | Apache-2.0 | A | 150 | Claude Code, Codex |