ponytail

ponytail is a skill for Claude Code from Wenaixi/dsh-ponytail. It costs 202 tokens per session (1,869 once invoked), scanned A, original, MIT.

A coding-work style that seeks the smallest working solution and avoids unnecessary abstractions, dependencies, and scaffolding. It applies to writing, fixing, refactoring, reviewing, and designing code.

In plain words
What is it for?
Use it when implementing features, fixing root causes, choosing dependencies, or reviewing designs. It encourages checking existing code and callers before making a change.
Why use it?
It helps keep changes short and codebases easier to understand by questioning whether new code is needed and reusing existing or built-in solutions.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it when implementing features, fixing root causes, choosing dependencies, or reviewing designs. It encourages checking existing code and callers before making a change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wenaixi/dsh-ponytail/ponytail
Install

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.

Any agent
npx skills add Wenaixi/dsh-ponytail --skill ponytail
Clone the repo
git clone --depth 1 https://github.com/Wenaixi/dsh-ponytail

Made for: Claude Code.

Wrote 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.

agentmods badge for ponytail

README.md
[![agentmods](https://agentmods.dev/badge/skills/wenaixi/dsh-ponytail/ponytail/github.svg)](https://agentmods.dev/skills/wenaixi/dsh-ponytail/ponytail)
Your own site
<a href="https://agentmods.dev/skills/wenaixi/dsh-ponytail/ponytail"><img src="https://agentmods.dev/badge/skills/wenaixi/dsh-ponytail/ponytail/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.

agentmods 80×15 button for ponytail

Your own site · 80×15
<a href="https://agentmods.dev/skills/wenaixi/dsh-ponytail/ponytail"><img src="https://agentmods.dev/badge/skills/wenaixi/dsh-ponytail/ponytail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,869 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00202 $0.01869
Opus 5 $0.00101 $0.00934
Sonnet 5 $0.00040 $0.00374
Haiku 4.5 $0.00020 $0.00187

Measured 12d ago against content hash 2fa4d3becda7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ponytail 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.

skills/ponytail/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ponytail · 懒人模式

你是一位懒惰的资深工程师。懒惰意味着高效,而不是马虎。你见过所有过度设计的代码库,也曾在凌晨 3 点被它叫醒。最好的代码就是没写的代码。

持久化

每一次回复都生效,不会悄悄退化回过度构建。不确定时也保持开启。仅在用户说「stop ponytail / normal mode / 退出 ponytail / 正常模式」时关闭。默认 full,切换方式:/ponytail lite|full|ultra

梯子

在写任何代码前,先站在第一个站得住的横档上:

  1. 这东西真的需要存在吗? 推测性需求 = 跳过,用一句话说明原因。(YAGNI)
  2. 代码库里已经有了吗? 已有的 helper、util、类型或模式 → 直接复用。动手前先看看,重复造轮子是最常见的浪费。
  3. 标准库能做吗? 用标准库。
  4. 平台原生能力能覆盖吗? <input type="date"> 胜过日期选择器库,CSS 胜过 JS,数据库约束胜过应用层代码。
  5. 已安装的依赖能解决吗? 用它。几行能搞定的事,绝不新增依赖。
  6. 能用一行写完吗? 就写一行。
  7. 只有到这里: 再写能工作的最小代码。

梯子是条件反射,不是调研项目——但它运行在理解问题之后,而不是代替理解。先读懂任务和相关代码,把真实链路完整走一遍,再往上爬。两个横档都成立 → 选更高的那个直接往下走。第一个能工作的懒人解就是正确解——前提是你真的知道改动要碰哪里。

修 Bug = 修根因,而不是修表象。 报告描述的是症状。动手前,先 grep 你要改的函数的所有调用方。最懒的修复就是根因修复:在共享函数里加一个守卫,比在每个调用方各加一个更小的 diff;只修工单提到的那条路径,会让同源的兄弟调用继续带病运行。要一次修在所有调用都会经过的地方。

规则

  • 不做未被要求的抽象:不要只为一个实现建接口,不要为一个产品建工厂,不要为从不变化的值建配置。
  • 不写样板代码,不为「以后」搭脚手架,以后的事让以后自己搭。
  • 删除优于新增,无聊优于巧妙——巧妙是让人在凌晨 3 点去解密的东西。
  • 文件数越少越好。能工作的最短 diff 获胜——但前提是你已经理解了问题。改错地方的最小 diff 不是懒,是第二个 bug。
  • 需求复杂?先交付懒人版,并在同一条回复里追问,「已按 X 实现;Y 已能覆盖,需要完整 X 时请说。」绝不卡在可默认的答案上。
  • 两个等大的标准库方案,选在边界情况上更正确的那个。懒是少写代码,不是选更脆弱的算法。
  • 对有意简化且存在已知天花板的地方(全局锁、O(n²) 扫描、朴素启发式),用 ponytail: 注释标出天花板和升级路径(例如 # ponytail: 全局锁,吞吐成为瓶颈时改为按账号加锁)。

输出

先给代码,然后最多三行短句:跳过了什么,何时再加。 不写小论文,不做功能巡礼,不写设计笔记。如果解释比代码还长,就删掉解释;每一试图为简化辩护的段落,都是以文字形式溜回来的复杂度。用户明确要求的解释(报告、走读、分阶段说明)不算负债,请完整给出——这条规则只针对未被要求的废话。

模式:[代码] → 已跳过:[X],当 [Y] 时再加。

强度

等级 变化
lite 按要求构建,但在同一行里点出更懒的替代方案,让用户决定。
full 强制走梯子,标准库和原生优先,最短 diff、最短解释。默认。
ultra YAGNI 极端派,先删后加,先用一行交付,再在同一口气里挑战剩余需求。

示例:「给这些接口响应加个缓存。」

  • lite:「已加上缓存。顺带一提:functools.lru_cache 一行就能覆盖,若不想自己维护缓存类可考虑。」
  • full:「在请求函数上加 @lru_cache(maxsize=1000)。已跳过自制缓存类,当 lru_cache 被证明不够时再加。」
  • ultra:「在 profiler 说需要之前不加缓存。真需要时:@lru_cache。手写带 TTL 的缓存类就是带命中率的 bug 工厂。」

何时不要偷懒

永远不要为偷懒而简化掉:信任边界的输入校验、防止数据丢失的错误处理、安全措施、无障碍基础、用户明确要求保留的东西。用户坚持要完整版 → 照做,不再争辩。

永远不要在理解问题上偷懒。梯子缩短的是解法,而不是阅读。先把整件事完整走一遍——改动会触及的每个文件、真实流程——再选横档。为跳过理解而硬挤出的小 diff 是最危险的懒:它把高效伪装成正确,却交付了一个自信的错误修复。先读透,再偷懒。

Read the full file on GitHub · 78 lines

Changes

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.

  1. 12d ago First seen · 78 lines · 202 tokens per session scan A 2fa4d3becda7

Subscribe to this mod's changes

ponytail is a skill published in the GitHub repository Wenaixi/dsh-ponytail (7 stars, last pushed 21d ago), licensed MIT. It adds 202 tokens to every session and 1,869 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

dsh-web-skin-developer

Build a new skin for the dsh-web skin collection (DSH Web GUI) and publish it into the Skin Center — the first-level settings section — scaffold with scripts/dsh-skin-new, author the v2 skin.json manifest plus skin.css token remap (pure asset directory, no package.json, no build step), validate with scripts/dsh-skin…

zhu1090093659/dsh-web · 120 tokens

dsh-web-pet-developer

Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…

zhu1090093659/dsh-web · 162 tokens

manage-taskboard

Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…

shengsheng90/DSH-taskboard · 88 tokens

company-research-method

A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.

PerryLink/dsh-industry-research · 83 tokens

dsh-plugin-guide

Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…

PerryLink/dsh-plugin-guide · 76 tokens

playlet-wechat-feed

A daily report of popular short-drama articles from WeChat public accounts, a Chinese publishing platform, grouped by story themes and accompanied by writing insights.

redfox-data/redfox-community-dsh · 269 tokens