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 | $0.00051 | $0.02372 |
| Opus 5 | $0.00026 | $0.01186 |
| Sonnet 5 | $0.00010 | $0.00474 |
| Haiku 4.5 | $0.00005 | $0.00237 |
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 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 — 133 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
用最小必要文档连接项目意图、实施、证据和学习。先读取真实现场，再做最小可验证变更；证据不足时保持候选、未知或未验证。
Swift Cycle 只负责一个项目内部的工程循环。它不负责上层协同、容量、独立验收、Registry、跨部门治理、模型选择或跨项目授权，也不接入 stop-that-shit。
调用与采用
- 系统层保持显式调用；不得把语义相似当成采用。
- 用户首次要求初始化或接管时，执行一次显式
$swift-cycleadoption。 - adoption 获得批准后，在项目
AGENTS.md写入持久绑定：后续项目任务必须加载$swift-cycle，由 Agent 自动维护，不要求用户重复调用或选择模式。 - 一次性显式审查不自动产生持久绑定；只有用户要求采用或初始化时才写入。
- 已绑定项目直接继续当前任务。不要向用户展示 bootstrap、milestone 或 closeout 菜单。
采用、绑定文本和内部阶段判断见 adoption-and-routing.md。
使用项目语言
对话中的普通内容按用户要求，其次按本次调用语言。修改文件中的普通内容优先沿用文件主语言；新建文件中的普通内容优先项目主语言。技术标识不随普通内容翻译：文件名、命令、API、代码标识、标准状态值和品牌名保持准确原文。不要因对话切换而批量翻译。语言判定与图示表达见 zh-CN.md。
读取真实现场
- 读取适用的
AGENTS.md、项目意图权威、README.md、DESIGN.md、相关docs/、忽略规则和可访问的本地维护记录。 - 检查 Git 分支、状态和相关 diff，分开既有用户改动与当前任务。
- 区分已确认事实、观察、推断、候选、限制和未知项。
- 只检查与当前声明相关的源码、制品、运行态或消费者层，不假设不存在或已经验证的层。
后台自动路由
根据现场自动判断当前阶段，不要求用户选择：
| 阶段 | 识别信号 | 默认动作 |
|---|---|---|
| 首次采用或接管 | 尚无持久绑定，或文档职责未建立 | 保留现场，建立绑定和最小职责映射 |
| 普通推进 | 目标与架构边界未实质改变 | 只更新受影响代码、测试和权威文档 |
| 重大结构变化 | 权威、模块职责、合同模型、数据或交付边界发生实质变化 | 建立必要基线并更新设计或详细权威 |
| 里程碑关闭 | 交付与验证已结束 | 自动收敛文档、状态、证据与本地行动记录 |
详细触发、停止条件和授权边界见 adoption-and-routing.md。
自动选择文档档位
选择能覆盖真实职责的最小档位：
minimal：覆盖项目意图基线，并复用 README、简洁设计入口、AGENTS、本地 TODO/DEVLOG 和已有必要文档。standard：仅在长期架构、路线图、评估或重要决策需要独立权威时增加对应文档。runtime_integration：仅在当前任务需要建立、改变或验证多个运维、合同、安全、存储、集成或身份层时增加文档与证据。
档位是后台配置，不是用户模式，也不是固定目录树。读取 document-profiles.md 完成内部 profile_conformance：每项职责记录“复用现有 / 新建 / 不适用”、唯一权威、理由和更新触发。缺少该映射时，不得宣称档位已落地。
文档职责
docs/blueprint.md或等价权威：共享、受跟踪的项目意图基线，说明为什么做、为谁做、可观察结果、范围和非目标、约束与未知、关键边界、启动出口、待决事项和更新触发。README.md：面向用户的介绍、安装或启动、用法和用户可见限制。DESIGN.md：简洁设计总入口、正式边界、候选区分和详细文档索引。AGENTS.md：项目规则、Swift Cycle 持久绑定、安全边界、同步触发与验证要求。- 本地
TODO.md：当前行动、阻塞和下一步；保持短小并由 Git 忽略。 - 本地
DEVLOG.md：失败、拒绝方案、内部判断、维护证据和演进；由 Git 忽略。 docs/：长期共享的需求、架构、路线图、评估、运行手册、证据和 ADR。
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 4.6 KB
- references/document-information-architecture.md 6.1 KB
- references/document-profiles.md 8.2 KB
- references/governance-boundaries.md 4.1 KB
- references/lifecycle-and-closeout.md 3.5 KB
- references/zh-CN.md 2.8 KB
- templates/BLUEPRINT.md 2.9 KB
- templates/DESIGN.md 2.1 KB
- templates/DEVLOG.md 1.6 KB
- templates/docs/adr/ADR-NNN.md 497 B
- templates/docs/adr/README.md 846 B
- templates/docs/architecture.md 1.5 KB
- templates/docs/closeout-packet.md 684 B
- templates/docs/evaluation.md 1.2 KB
- templates/docs/operations.md 1.1 KB
- templates/docs/README.md 1006 B
- templates/docs/review-packet.md 641 B
- templates/TODO.md 1.4 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.
- 5d ago Changed 632b64298c94
- 10d 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 3d ago), licensed MIT. It adds 51 tokens to every session and 2,372 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
spec-kitty-implement-review
Orchestrate the implement-review loop for Spec Kitty work packages using any configured agent. Covers agent dispatch, state transitions, rejection cycles, arbiter escalation, and dependency-aware sequencing across all 13 supported coding agents. Triggers: "implement and review WPs", "run the implement-review loop"…
spec-kitty-mission-system
Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are resolved through the 6-tier chain, and how doctrine artifacts (procedures, tactics, directives) compose mission behavior.…
spec-kitty-program-orchestrate
Orchestrate a multi-repo, multi-mission Spec Kitty program end-to-end: run specify → plan → tasks → implement → review → merge → mission-review → post-merge fixes across several repositories in a defined dependency order, using background sub-agents for parallel work and a pulse-heartbeat safety net for long…
spec-kitty-runtime-review
Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…
spk-run-verdict-capture
Set a Spec Kitty work-package review verdict through the deterministic event-log seam, so every agent harness records approve/reject the same way.
spk-run-implement-review
Orchestrate Spec Kitty work-package implementation and review loops until all packages are done, approved, or correctly rejected.