@njuptlzf/dsh-ponytail
Ponytail (lazy-senior-dev) 作为可切换模式、始终启用的 DSH 插件：每一步注入 COMPACT 规则集（关闭时将其清空），并将完整规则集及五个配套项镜像到 ~/.dsh/skills。署名：github.com/DietrichGebert/ponytail (MIT)。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add @njuptlzf/dsh-ponytail@1.2.0Ponytail 以 @njuptlzf/dsh-ponytail 发布，当前版本为 1.2.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
正在加载相关插件…
A DeepSeek Harness plugin that installs the Ponytail "lazy senior developer" ruleset. It mirrors upstream's two-layer split:
/ skills.This repo vendors no skill content. On first boot it fetches once from upstream DietrichGebert/ponytail, caches to disk, and never re-fetches or hand-syncs afterwards.
.agents/rules/ponytail.md, ~2.5 KB) as a system-prompt section, cached at ~/.dsh/ponytail-cache/compact.md. Switch the level per session with /ponytail lite|full|ultra|off; off empties the section so the tokens are actually saved. Default full.ponytail) and the 5 companions (ponytail-help / ponytail-audit / ponytail-debt / ponytail-gain / ponytail-review) written once to ~/.dsh/skills/<name>/SKILL.md, invocable from the / palette. Each file's frontmatter carries disable-model-invocation: true, so these skills stay user-invocable (shown in / with a "user only" tag) but are not advertised to the model — no available_skills catalog cost, no auto-load on "ANY coding task". The always-on compact section is the only model-facing copy.dsh plugin --profile web add @njuptlzf/dsh-ponytail
# without a global dsh:
npx @deepseek-ai/dsh plugin --profile web add @njuptlzf/dsh-ponytail
# from git instead: dsh plugin --profile web add github:njuptlzf/dsh-ponytail
Restart dsh web after install. The first boot fetches once and caches, so later boots — online or offline — never touch the network. To update the skills, delete the corresponding cache/skill files and restart.
/ponytail — report the current level; /ponytail lite|full|ultra|off — switch it. Mode is per-session (agent.id), so one conversation's off does not affect another./ palette, tagged "user only"; type / and pick one (e.g. /ponytail-review) to trigger it manually — the model never pulls them in unprompted.| codex-ponytail (upstream Codex plugin) | dsh-ponytail (this plugin) | |
|---|---|---|
| Mechanism | Codex plugin: SessionStart + SubagentStart + UserPromptSubmit lifecycle hooks | DSH bundle: systemPrompt section + commands service |
| Always-on content | full ruleset, mode-filtered, at SessionStart | compact ruleset (~2.5 KB) every step |
| Per-turn cost | full rules only at session start / compact / subagent; one mode line per turn | ~2.5 KB re-rendered per step (DSH systemPrompt per-step semantics) |
off | UserPromptSubmit stops injecting, tokens saved | section renders empty, tokens saved (parity) |
| Levels | lite/full/ultra filter the full ruleset's per-mode rows | level carried as header + behavior; per-mode detail lives in the on-demand full skill |
| Session isolation | single-session process → process-level flag file | multi-session process → per agent.id (== session.id) |
| Compaction | SessionStart re-fires on the compact matcher | compaction only shatters history, never the system prompt (inherent) |
| Subagents | SubagentStart + PONYTAIL_SUBAGENT_MATCHER | global section inherits into subagents via composition (no patch expected) |
| On-demand detail | ponytail skill | ponytail skill (parity) |
| Fallback | inline getFallbackInstructions | TODO (see OPTIMIZATION_PLAN.md) |
dsh-ponytail/
├── index.js # host plugin: fetch once → compact always-on + mirror full/companions
├── package.json # dsh.bundle.patch declaration
├── cordis.patch.yml # mount row
├── OPTIMIZATION_PLAN.md # full design rationale + comparison
├── README.md
└── LICENSE # MIT
Skill content comes from DietrichGebert/ponytail (MIT), fetched at runtime. The plugin wrapper is MIT © 2026 Kasakaze (njuptlzf).
一个 DeepSeek Harness 插件：把 Ponytail「懒高级工程师」规范接入进来，对标上游的两层结构：
/ skill。本仓库不存技能内容——首次启动从上游 DietrichGebert/ponytail 抓取一次并落盘缓存，之后不再联网、永不手工同步。
.agents/rules/ponytail.md，~2.5 KB）作为 system-prompt section，缓存于 ~/.dsh/ponytail-cache/compact.md。用 /ponytail lite|full|ultra|off 按会话切档；off 会让 section 渲染为空、真的省回 token。默认 full。ponytail）和 5 个同伴（ponytail-help / ponytail-audit / ponytail-debt / ponytail-gain / ponytail-review）写入 ~/.dsh/skills/<name>/SKILL.md，/ 面板可调。每个 skill 的 frontmatter 都带 disable-model-invocation: true：技能保持仅用户可调用（在 / 里显示、带「仅用户可用」标签），但不对模型公开——不进 available_skills catalog、不会因描述写着 "ANY coding task" 被自动加载。常驻精简 section 是唯一面向模型的那一份。dsh plugin --profile web add @njuptlzf/dsh-ponytail
# 无全局 dsh：
npx @deepseek-ai/dsh plugin --profile web add @njuptlzf/dsh-ponytail
# 或者从 git 安装：dsh plugin --profile web add github:njuptlzf/dsh-ponytail
安装后重启 dsh web：首次启动联网抓取一次并缓存，之后无论在线离线都不再联网。要更新技能，删对应缓存/技能文件再重启即可触发重抓。
/ponytail — 报告当前档；/ponytail lite|full|ultra|off — 切档。档位按会话（agent.id）隔离，一个会话的 off 不影响其它会话。/ 面板、标「仅用户可用」；打 / 看候选、手工选一个（如 /ponytail-review）触发——模型不会未经请求就自动加载它们。| codex-ponytail（上游官方 Codex 插件） | dsh-ponytail（本插件） | |
|---|---|---|
| 接入机制 | Codex 插件：SessionStart + + 三个 lifecycle hook |
SubagentStartUserPromptSubmitDSH bundle：systemPrompt section + commands 服务 |
| 常驻内容 | SessionStart 时注入全文（按 mode 过滤） | 每步注入精简规则（~2.5 KB） |
| 每轮成本 | 全文只在会话开始/压缩/子代理时；每轮只一行 mode 标记 | 每步重渲 ~2.5 KB（DSH systemPrompt 的 per-step 语义） |
| off | UserPromptSubmit 停止注入、省回 token | section 渲染为空、省回 token（对齐） |
| 强度档 | lite/full/ultra 过滤全文对应档的内容 | 档位以 header + 行为承载；分档细节落在按需全文 skill |
| 会话隔离 | 单会话进程 → 进程级 flag 文件 | 多会话单进程 → 按 agent.id（== session.id）隔离 |
| 压缩/遗忘 | SessionStart 的 compact matcher 在压缩时重注入 | 压缩只 shadow 历史、不动 system prompt（天然免疫） |
| 子代理 | SubagentStart + PONYTAIL_SUBAGENT_MATCHER | 全局 section 随 composition 继承子代理（预期无需补丁） |
| 按需详情 | ponytail skill | ponytail skill（对齐） |
| 兜底 | 内置 getFallbackInstructions | 待补（见 OPTIMIZATION_PLAN.md） |
dsh-ponytail/
├── index.js # host 插件：只抓一次 → 精简常驻 + 镜像全文/同伴
├── package.json # dsh.bundle.patch 声明
├── cordis.patch.yml # 挂载行
├── OPTIMIZATION_PLAN.md # 完整设计说明与对比
├── README.md
└── LICENSE # MIT
技能内容来自 DietrichGebert/ponytail（MIT），运行时抓取。插件包装层 MIT © 2026 Kasakaze (njuptlzf)。