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 Minokun/xdev --skill xdev-full-devgit clone --depth 1 https://github.com/Minokun/xdevWrote 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/minokun/xdev/xdev-full-dev)<a href="https://agentmods.dev/skills/minokun/xdev/xdev-full-dev"><img src="https://agentmods.dev/badge/skills/minokun/xdev/xdev-full-dev.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00011 | $0.04663 |
| Opus 5 | $0.00005 | $0.02331 |
| Sonnet 5 | $0.00002 | $0.00933 |
| Haiku 4.5 | $0.00001 | $0.00466 |
Grade A, and why
xdev-full-dev scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
推导不出的标 HIGH（注意 curl 不加 -i/-w 时状态码不出现在输出中、 How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/xdev-full-dev — 端到端开发工作流 v2
设计原则（本文件的存在理由）：
- 只保留信息提取型机制——制造模型自身上下文里拿不到的信息（fresh 独立审核、diff 对照设计、真实执行的测试输出）。模型再强，这三类信息也不会免费出现。
- 其余一切规则都是默认值，不是枷锁。模型可按情境偏离，偏离时一句话说明即可。
- 零外部依赖：不引用 gstack / superpowers / 任何外部 skill 库。所有审核 prompt 内置。
实验依据：三省模式 N1–N5 对照实验（
docs/experiments/sansheng/PROPOSAL.mdv2.4）证明 强模型互有结构性盲区（反思漏覆盖缺口、Gate 漏 BDD 缺陷），独立视角 + 客观执行不可互相替代。
使用
/xdev-full-dev <需求描述> [--no-menxia] [--skip-design]
- 门下门（阶段 2 的计划放行裁决）默认开启；
--no-menxia跳过（如复用已审过的计划） --skip-design：需求已含完整设计文档时跳过阶段 1
硬规则（仅 5 条，违反任何一条即为流程失败）
- 验证必须真实执行。测试、构建、检查命令必须实际运行并以真实输出作为通过依据。 禁止以"应该会通过"推进。后台命令必须轮询到终态。
- fresh 审核的裁决必须执行。门下门/反思/drift 的 reject 必须返工或升级用户， 不得以任何理由绕过或软化（"其实问题不大"不是理由）。
- 不向 base 分支提交。在
main/master上时，先建 feature 分支 （可选括号：git worktree，位置随意，能隔离即可）。 - 不可逆动作须用户确认：部署生产、删除数据、强制推送、对外发布。
- 其余均为默认值：阶段划分、文档结构、输出格式都可按任务规模伸缩—— 单行 bugfix 不需要设计文档，大功能不要跳过。唯一不可伸缩的是硬规则 1-4。
阶段 1：设计
产出一份设计文档（docs/plans/<date>-<slug>-design.md），包含：
- 功能点 F1..Fn：每条一句话、可判定是否完成
- Must Not：明确不做什么（防扩散）
- 验收标准：可客观核验的判据（状态码/行为/输出）。每个用户可感知交互通道 （按键/点击/输入/路由）必须有"输入→可观察效果"的可断言判据；豁免须逐条列出并记一句理由， 不得以某层"无法断言"豁免整个层（如以"渲染无法断言"连带豁免输入绑定）。
- 涉及 UI 时附视觉要点；涉及高风险（auth/支付/schema）时附风险与回滚思路
Intent Contract = 上面三项（F1..Fn + Must Not + 验收标准）经用户确认后的定稿。 它是阶段 3 drift check 与阶段 4 对抗审查的唯一对照基准；改它必须显式回到阶段 1。
规模自适应：小功能（<1 天）可在对话中直接口述设计要点并确认，不必落盘长文档。
🔴 门禁：跨模块 / 不可逆 / 影响生产数据的功能，设计须经用户确认后继续；其余直接过。
澄清优先：需求含糊时先问，不要靠猜（一问抵三轮返工）。
阶段 2：计划与门
产出实现计划（docs/plans/<date>-<slug>.md），按任务拆分：
## task-NNN-<slug>
**BDD：** Given（具体输入）/ When / Then（可断言输出：状态码/字段/数值，禁止"系统正常"式表述）
**涉及文件：** ...
**验证命令：** ...（能真实执行；断言文本必须能从命令实际输出中推导；
交互通道的验收判据不得以人工目测充当——纯渲染/视觉观感目测不受此限）
**depends-on：** ...（只标真实技术前提）
**risk：** L0-L3 + 一句理由
审查编排（查表即可，不是仪式）：默认阵容即下表 A1–A3 + 门下门，标准功能不动。 命中触发时按附录 E 加挂条件审查员：不可逆操作 / 生产数据 / 资金 / 多租户 → E1 红队； 验收涉及多交互通道 / 多用户角色 / 多端 → E2 场景推衍。每加一个审查员必须能写出一句 "它看什么，是已选审查员看不到的"——写不出就不加（编排完整规则见附录 E）。
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.
- 2d ago Changed · +52 lines 0efd0b8254bc
- 3d ago Changed · +6 lines 70ee8ee7cf07
- 4d ago First seen · 216 lines · 11 tokens per session scan A f5452f38b691
xdev-full-dev is a skill published in the GitHub repository Minokun/xdev (24 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 4,663 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.