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 KtKID/x-dev-pipeline --skill x-qdevgit clone --depth 1 https://github.com/KtKID/x-dev-pipelineWrote 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/ktkid/x-dev-pipeline/x-qdev)<a href="https://agentmods.dev/skills/ktkid/x-dev-pipeline/x-qdev"><img src="https://agentmods.dev/badge/skills/ktkid/x-dev-pipeline/x-qdev/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/ktkid/x-dev-pipeline/x-qdev"><img src="https://agentmods.dev/badge/skills/ktkid/x-dev-pipeline/x-qdev.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 | $0.00116 | $0.02403 |
| Opus 5 | $0.00058 | $0.01202 |
| Sonnet 5 | $0.00023 | $0.00481 |
| Haiku 4.5 | $0.00012 | $0.00240 |
Grade A, and why
x-qdev 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 today.
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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
x-qdev
小任务的快速开发流程。把"需求 → 测试 → 实现 → 验证"四步组合进一份 task 文档,一次性闭环。
核心原则
- 一份文档。 需求、测试、实现、验证结果都在同一个 md 文件里,不拆多个文件。
- 先测试后实现。 测试用例先写(此刻是失败的),实现让测试变绿。顺序不能反。
- 需求段用功能性语言。 ①需求章节是用户能看懂的(继承 x-spec 原则:不写技术词汇);②③④章节是开发者能执行的技术内容。
- 验证结果只填真实输出。 不写"应该会通过",粘贴实际运行的输出。
- 自检即 gate。 交付前对 task 文档自身做一致性对账(见第 4 步),不依赖其他 skill 做验证。
工作流
第 1 步:找 spec 文档
按优先级查找:
- 扫
docs/spec/*/spec.md,找当前任务相关的 spec(按 spec 标题和 feat 内容判断相关性)。 - 找到 → task 文档建在
docs/spec/<spec-name>/tasks/task-<task-name>.md,并在文档头部标注对应的 feat(如feat: feat02;实现多个 feat 就写feat: feat02, feat03)。 - 找不到 → 告诉用户:"没找到对应的 spec 文档。建议先用 x-spec 整理需求;如果任务确实简单不需要 spec,我直接建独立 task 文档。"用户确认简单后,建在
docs/task/task-<task-name>.md。
任务超出小任务范围时(跨多模块、需要重新讨论需求、涉及数据迁移或鉴权等高风险),停下来提示:"这个任务超出 x-qdev 范围,建议走 x-spec + x-req 完整流程。"不要硬干。
第 2 步:写 task 文档(①②两段)
先填 ①需求 和 ②测试用例 两段(此刻测试还没写实现,应当是失败的):
①需求(功能性语言,用户视角):
- 功能方向:这个任务要实现什么,1-3 句。
- 功能边界:做什么、不做什么,明确排除项。
- 不能破坏的不变量:既有功能中必须持续成立的规则(如"已有用户仍能正常登录")。
②测试用例(技术语言):
- 从①的每个功能点和不变量推导测试:unit(逻辑单元)+ smoke(最小真实调用链)+ e2e(按需,用户链路风险高时才写)。
- 必须覆盖边界:空输入、极值、错误输入。
- 每个测试标注对应的需求点或不变量。
第 3 步:执行 TDD 循环
按 ②→③ 的顺序实际动手:
- 写测试代码,跑一遍,确认失败(红)。失败原因应该是"功能还没实现",而不是测试本身写错。
- 写实现代码(填③的实现步骤和涉及文件),跑测试(绿)。
- 失败时:改实现再跑;发现测试写错就改测试并在文档里记录修正原因。这个循环的每次返工不需要逐条记录,但重大方向调整要记进③。
- 全绿后,把真实测试输出粘进 ④验证结果,并跑一遍既有测试确认不变量没被破坏(结果也粘进④)。
第 4 步:文档自检并交付
交付前对自己刚产出的 task 文档做一次完整对账。自检只用 task 文档本身(有 spec 时加上头部指针指向的 spec)作为核对材料,不调用 x-spec / x-req / x-verify 等任何其他 skill,也不改判它们的产物。 按顺序检查,先结构后内容:
- 结构:四段齐全且顺序为 ①需求 → ②测试用例 → ③技术实现 → ④验证结果;头部
spec:、feat:、创建:三行完整(无 spec 的独立任务按第 1 步约定处理)。 - 回指有效:头部
feat:标注的每个 feat 号都真实存在于 spec;②里每条测试标注的需求点/不变量编号都能在①里找到定义。悬空标注在这一步修正。 - 覆盖闭合:①的每个功能点、每个"不能破坏的不变量"都至少被②一条测试回指;②不存在标注不到①任何条目的测试。
- 结论一致:④的测试输出真实存在(不是"应该会通过"之类的占位)、通过的测试数量与②列出的数量对得上;不变量回归有真实结果;结论四个勾选与④的实际内容一致——有测试没过就不许勾"所有测试真实跑过且通过"。
- 边界核对:③涉及文件列表与实际改动一致,没有超出①"功能边界"声明范围的"顺便"改动。
发现问题直接修自己的 task 文档后再重查;修不了(比如需求本身有歧义)就停下来问用户。全部通过才交付。
What ships with it
1 file 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.
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.
- today First seen · 192 lines · 116 tokens per session scan A 6da62730334b
x-qdev is a skill published in the GitHub repository KtKID/x-dev-pipeline (12 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 2,403 once invoked, about $0.0006 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 2026-09-09.
Other skills, from other repositories
test-driven-development
Enforces TDD discipline with RED-GREEN-REFACTOR cycle. Use when writing new features, fixing bugs, or refactoring code. Ensures tests genuinely verify behavior.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
Test Writer
Use this skill when you’re adding features or fixing bugs and you want tests that lock in behavior, are easy to read, and fail with useful diagnostics.
orchestrate
A workflow manager for a full test-driven development cycle, where tests are written before implementation and code is then improved and reviewed. It coordinates planning, failing tests, implementation, refactoring, review, and committing changes.