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-iterategit 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-iterate)<a href="https://agentmods.dev/skills/minokun/xdev/xdev-iterate"><img src="https://agentmods.dev/badge/skills/minokun/xdev/xdev-iterate.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 | $0.00010 | $0.00952 |
| Opus 5 | $0.00005 | $0.00476 |
| Sonnet 5 | $0.00002 | $0.00190 |
| Haiku 4.5 | $0.00001 | $0.00095 |
Grade A, and why
xdev-iterate 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 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.
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.
What it actually says
/xdev-iterate — 快速迭代流程
改动描述： 用户消息（手势之外的原文）
本流程 =
/xdev-full-dev阶段 3–4 去掉设计与计划，直接以用户描述为 Intent Contract。 硬规则 1–5 全部生效。本文件只写 iterate 不同于 full-dev 的部分：范围门控与升级触发。
阶段 0：范围门控（先判断，再动手）
全部满足才留在本流程：改动 <100 行、≤5 文件、≤2 模块、不引新依赖、不改公开 API 契约。
命中任一立即升级，不看行数：
| 信号 | 去向 |
|---|---|
| 金融计算 / 资金逻辑；认证 / 权限 / 安全；数据库 schema；第三方 API 集成；已发布 API 行为 | /xdev-full-dev（条件深度审查会触发） |
| 新增页面 / 路由 / 含 ≥2 交互状态的新组件 | /xdev-full-dev（需要设计阶段） |
| 描述的其实是错误行为而非改动需求 | /xdev-bugfix |
留在本流程的 UI 改动仅限：现有组件的样式 / 文案 / 间距微调、现有 UI 的显示修正。
影响面门禁（改动目标是共享 util / service / config / 协议文件时必做）：
用一次限域 rg 列出直接调用方（file:line）。调用方跨 ≥2 顶层目录或 ≥5 文件 → 升级 full-dev。
查不到调用方但目标是共享文件 → 写明 "影响面未知"，不得声称影响面为空。
判定后告知用户分流结果，继续执行。
分支：在 main/master 上则先 git switch -c xdev-iterate-<slug>（或 worktree；注意 worktree 不带 .env* 与构建产物）。
阶段 1：TDD 改动（= full-dev 阶段 3，单任务）
- 找到相关现有测试；没有则先补一条覆盖当前行为的测试
- 更新 / 新增测试描述目标行为，跑一次确认真的失败
- 最小实现到通过；不顺手重构、不做描述之外的事
- 项目约定的全量测试 + lint/build，相比改动前无新增失败（既有失败与本次 diff 无关 → 记为 BASELINE_DEBT，不修）
- commit：
<fix|feat|perf|refactor|chore>: <description>
涉及 UI：用项目可用的 e2e / 截图手段确认受影响页面无回归（不评分）。
Diff 后复核：git diff --name-only 与阶段 0 预估的影响面对比——多出的文件要么有一句理由，要么升级 full-dev。同时列出需要同步的文档 / 测试 / release notes。
阶段 2：交付（= full-dev 阶段 4）
- 小改动（单文件、无行为变化）：推到分支即止
- 其余：按
/xdev-full-dev阶段 4——pre-landing 对抗审查（附录 D）→ CHANGELOG 一行 → commit + push + PR → 合并后清理 worktree
升级信号（任一出现即切换，不硬撑）
阶段 0 阈值被突破 · 测试暴露的失败不是本次改动引入 → /xdev-bugfix · 需要新依赖或改 API → /xdev-full-dev · FIX_REQUIRED 2 轮未解 → /xdev-bugfix · 改动的真实目的是验证假设/找规律（要研究结论而非代码交付） → /xdev-research
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 898b0750d7c1
- 4d ago First seen · 57 lines · 10 tokens per session scan A 28ed6e421f22
xdev-iterate is a skill published in the GitHub repository Minokun/xdev (24 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 952 once invoked, about $0.0001 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 2026-09-04.
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.