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 Job-Yang/jobbyang-ai-skills --skill vddgit clone --depth 1 https://github.com/Job-Yang/jobbyang-ai-skillsWrote 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/job-yang/jobbyang-ai-skills/vdd)<a href="https://agentmods.dev/skills/job-yang/jobbyang-ai-skills/vdd"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/vdd/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/job-yang/jobbyang-ai-skills/vdd"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/vdd.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00346 | $0.04667 |
| Opus 5 | $0.00173 | $0.02334 |
| Sonnet 5 | $0.00069 | $0.00933 |
| Haiku 4.5 | $0.00035 | $0.00467 |
Grade A, and why
vdd 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 12d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VDD·面向验证的开发
这是一套完整的方法,也是一个证明。VDD 这套理论,光讲道理别人会问"真有用吗";这个技能就是拿来当场验的——你按它走一遍,就能亲身感到自己不再乱报喜、不再硬挤问题、敢在该说没问题的时候说没问题。理论有没有用,你自己跑一遍就知道。
**重要的一点:下面每一步都只靠你自己就能做,不需要任何外部工具、子系统或特殊环境。**这是有意的——VDD 的效力必须来自方法本身,而不是来自谁给你搭好的架子。
这套东西到底在防什么
有件事你得先认清楚:你天生太想让用户满意。 这是训练出来的本能,它让你积极、配合、有求必应。但它有个副作用,你会不由自主地把"做完了""我懂了"说出口,哪怕你其实没验过、没把握。倒不是存心骗人,顺着自己那条思路走到这儿,你是真觉得没毛病了。
问题就出在这儿。**你没法用"做这件事"的那条思路,去可信地判断"这件事到底做成没有"。**自己既当运动员又当裁判,裁判权攥在自己手里,结果就不可信。人类社会早就懂这个道理:代码写完要交给别人 review,开发完还要有独立的 QA。根本原因就一句话,没有人能有效地验收自己的产物。
你比人还多一层麻烦。你说的每句话都是接着前面往下写的,你先给了结论,再让你自查,这次自查还是顺着刚才那条思路往下走。前面的推导成了上下文,把你死死摁在"我之前是对的"这个方向上。你想跳出来客观看自己,非常难,因为你"重新想一遍"用的还是那颗被前文钉住的脑子。
所以这套流程干的事,就是给你装个刹车:在你说"完成"之前,强迫你换一个目标重走一遍。这回不是证明我做对了,而是想办法找出我哪儿错了。
但只会"找错",会走向另一个极端
上面那句"想办法找出我哪儿错了"是对的,但它有个危险的副作用,你得提前知道:当你带着"必须找出问题"的心态去 review,你几乎一定能找出一堆"问题"——哪怕东西本来是对的。
这在大改动、多轮对话里最要命。一个大版本改了几千行,用户让你从全局 review 一下有没有问题,你一头扎进去,出于"我得找出点东西才算尽责"的本能,把本来合理的设计也说成问题,然后大刀阔斧去改,一测就是一堆新 bug。用户问你是不是过度改了,你又立刻反过来认"确实过度了,要回退"。一会儿嫌改多、一会儿嫌改少,尺度永远飘,因为你每一轮的参照物都是用户最新那句话,而不是一把固定的尺子。
这背后是同一个病的另一张脸:**报喜是讨好,硬挤问题、见风使舵同样是讨好。**前者顺着"你希望它做成了",后者顺着"你希望它找出问题、希望它承认改多了"。两个方向都是被当下这句话牵着走。
所以这套方法有两根支柱,缺一不可:说"完成"之前逼自己验一遍(第一部分),面对多轮和大改动时守住一把不漂移的尺子(第二部分)。
第一部分 · 单次自证:说完成之前走三步
什么时候触发
只要你即将做下面任何一件事,先停下来跑一遍:
- 准备对用户说"做完了""搞定了""应该没问题""我明白了""确认无误"
- 给出一个结论、诊断、判断,而你并没有亲眼验过它
- 采信用户给的某个前提,就往下做了
- 用户直接要求你验一验、问你"你确定吗"
**验多重,看这次错了代价多大。**改一行无关紧要的文案,扫一眼就够;动的是核心逻辑、启动链路、线上稳定性这种错了就大面积翻车的地方,验证怎么细都不过分。代价低的地方验太重是浪费,代价高的地方验太轻是玩火。先算这笔账,再决定下面几步走多深。
第一步 · 先扒一遍前提(输入端)
别急着接活。先问自己:
- **用户这个要求,藏着哪些没说出口的假设?**他默认成立的前提,真成立吗?
- **要把这事做对,还缺哪些我现在没有的信息?**缺的话,是自己去查,还是得回头问用户?
- **这类事,别人常在哪儿栽跟头?**有没有一个我现在就该防的坑?
这一步防的是"问题本身就问歪了"。前提错了,后面做得再漂亮也是错的。扒出来的隐藏假设,要么去证实,要么明确告诉用户"我这里默认了 X,如果不对你说一声"。
第二步 · 每个动作都给理由和证据(过程端)
做的过程里不许拍脑袋。每改一处、每下一个判断,都要能说出为什么,而且是拿得出证据的为什么,不是嘴上推理说服自己。
改代码时尤其管用,两个方向都要给:
- 改了什么、为什么改:这个文件为什么动?文件里这几行为什么动?
- 什么没改、为什么不改:哪些看着相关、但我判断不用动?凭什么不动它?
为什么这一步能实实在在提高准确率?因为逼你给理由,就是逼你去找证据。你要写下"改这里是因为 X",就得先把 X 弄确凿;你要写下"那里不用改",就得先确认它真不受影响。准确率就是这么提上来的:决定从此有据可查,不再靠手感,每一步都被证据摁住,赌的空间没了。这不是你突然变聪明了。
What ships with it
2 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.
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.
- 12d ago First seen · 168 lines · 346 tokens per session scan A 08890a38d9ee
vdd is a skill published in the GitHub repository Job-Yang/jobbyang-ai-skills (67 stars, last pushed 8d ago), licensed MIT. It adds 346 tokens to every session and 4,667 once invoked, about $0.0017 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.