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 asherzj/ashers-agent-skills --skill setup-engineering-skillsgit clone --depth 1 https://github.com/asherzj/ashers-agent-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/asherzj/ashers-agent-skills/setup-engineering-skills)<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/setup-engineering-skills"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/setup-engineering-skills/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/asherzj/ashers-agent-skills/setup-engineering-skills"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/setup-engineering-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00048 | $0.01895 |
| Opus 5 | $0.00024 | $0.00948 |
| Sonnet 5 | $0.00010 | $0.00379 |
| Haiku 4.5 | $0.00005 | $0.00189 |
Grade A, and why
setup-engineering-skills 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 9d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
设置研发 Skill 所需的仓库配置
搭建工程技能所依赖的仓库级配置：
- 工单系统（issue tracker）：issue 的存放位置（默认 GitHub；本地 markdown 也开箱即用）
- 分诊标签：五个规范分诊角色所使用的字符串
- 领域文档：
CONTEXT.md和 ADR（架构决策记录）的存放位置，以及读取它们的消费规则
这是一个提示驱动的技能，不是确定性脚本。先探索、展示你的发现、与用户确认，然后再写入。
流程
1. 探索
查看当前仓库，了解其初始状态。已有的东西都要读一读，不要凭空假设：
git remote -v和.git/config：这是一个 GitHub 仓库吗？是哪一个？- 仓库根目录的
AGENTS.md和CLAUDE.md：是否存在其中之一？其中是否已有## Agent skills小节？ - 仓库根目录的
CONTEXT.md和CONTEXT-MAP.md docs/adr/以及任何src/*/docs/adr/目录docs/agents/：本技能此前是否已生成过输出？.scratch/：本地 markdown 工单系统约定已在使用的标志- 是否安装了
triage技能？（与本技能同级的triage技能文件夹，或你可用技能列表中的triage。）这决定 B 节是否运行。 - Monorepo 信号：
pnpm-workspace.yaml、package.json中的workspaces字段，或有自己src/的packages/*。这些只存在于真正大型的多包仓库中；缺失即意味着单上下文（single-context），而几乎所有仓库都是单上下文。
2. 展示发现并提问
总结哪些已存在、哪些缺失。然后按顺序处理各节。一节一个问题，得到回答后再进入下一节。
每节都以推荐答案开头，让用户一个词就能接受。只有当选择确实存在分叉时才给出一行说明；当探索已经敲定答案时整节跳过（未安装 triage 时跳过 B 节，没有 monorepo 时跳过 C 节）。
A 节：工单系统。
说明：「工单系统」是本仓库 issue 的存放处。
to-tickets、triage、to-spec等技能会对它读写。它们需要知道是调用gh issue create、在.scratch/下写 markdown 文件，还是遵循你描述的其他工作流。请选择你实际为本仓库跟踪工作的位置。
默认姿态：这些技能为 GitHub 而设计。如果某个 git remote 指向 GitHub，就提议 GitHub。如果某个 git remote 指向 GitLab（gitlab.com 或自建主机），就提议 GitLab。否则（或用户另有偏好时），提供以下选项：
- GitHub：issue 存放在仓库的 GitHub Issues 中（使用
ghCLI） - GitLab：issue 存放在仓库的 GitLab Issues 中（使用
glabCLI） - 本地 markdown：issue 以文件形式存放在本仓库的
.scratch/<feature>/下（适合单人项目或没有远端的仓库） - 其他（Jira、Linear 等）：请用户用一段话描述工作流；技能会将其记录为自由格式的文字
把选择记录到 docs/agents/issue-tracker.md。GitHub 和 GitLab 模板带有一个「PR 作为请求面」的开关，默认关闭。保持关闭，也不要主动提起：想把外部 PR 纳入分诊队列的用户，之后可以自己在文件里打开这个开关。
**B 节：分诊标签词汇表。**如果未安装 triage 技能（探索阶段已经告诉你了），整节跳过，因为未安装的技能不需要标签。
如果已安装，只问一个问题：
是否保留默认的分诊标签？（推荐：是）
默认值是五个规范角色，每个标签字符串与角色名相同：needs-triage、needs-info、ready-for-agent、ready-for-human、wontfix。回答是时按原样写入。只有当用户说否时——通常是因为其工单系统已在使用其他名称（例如用 bug:triage 代替 needs-triage）——才收集覆盖值，让 triage 沿用现有标签而不是创建重复标签。
What ships with it
6 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.
- 9d ago First seen · 117 lines · 48 tokens per session scan A f35170312c76
setup-engineering-skills is a skill published in the GitHub repository asherzj/ashers-agent-skills (2 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 1,895 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…