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 yunshu0909/yunshu_skillshub --skill github-repo-searchgit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/github-repo-search)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/github-repo-search"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/github-repo-search/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/yunshu0909/yunshu_skillshub/github-repo-search"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/github-repo-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00073 | $0.02277 |
| Opus 5 | $0.00036 | $0.01138 |
| Sonnet 5 | $0.00015 | $0.00455 |
| Haiku 4.5 | $0.00007 | $0.00228 |
Grade A, and why
github-repo-search 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub 开源项目搜索助手
用途
从用户自然语言需求出发,经过需求挖掘、检索词拆解、GitHub 检索、过滤分类、深度解读,最终产出结构化推荐结果。
目标不是"给很多链接",而是"给用户可理解、可比较、可决策、可直接行动的候选仓库列表"。
适用范围(V1.1)
- 数据源:GitHub 公开仓库。
- 默认不授权(不使用用户 Token)。
- 默认硬过滤:
stars >= 100、archived=false、is:public。 - 默认输出:单榜单(Top N),榜单内按"仓库归属类型"标注。
- 本流程默认不包含安装与落地实施(除非用户单独提出)。
配额说明(必须知晓)
- 未授权 Core API:
60 次/小时。 - Search API:
10 次/分钟(独立于 Core 额度)。 - 需要在报告中注明检索时间与配额状态,避免结果不可复现。
工作流程
环节一:需求收敛(必须完成,不可跳过)
硬性门控:环节一是整个流程的前置条件。无论用户的需求描述多么清晰,都必须走完本环节并获得用户明确确认后,才能进入环节二。禁止根据用户的初始描述直接推断需求并开始检索。即使用户说"直接搜就行",也要先输出需求摘要让用户确认。
第一步:需求挖掘与对齐
目标:把"我想看看 XX"转成可执行、可排序、可解释的检索目标。
需确认信息(最少):
- 主题(如:agent 记忆、RAG、浏览器自动化)
- 数量(Top 10 / Top 20)
- 最低 stars(默认 100)
- 排序模式(必须二选一):
相关性优先/星标优先(默认:相关性优先) - 目标形态(必须二选一或多选):
可直接使用的产品/可二次开发的框架/资料清单/方法论
建议补充信息(可选):
- 偏好技术栈(Python/TS/Go 等)
- 使用场景(学习、生产、对标)
- 排除项(教程仓库、归档仓库、纯论文复现等)
- 部署偏好(本地优先/云端优先/混合)
阶段输出(固定格式):
核心诉求:
- 主题:xxx
- 数量:Top N
- 最低 stars:>= 100
- 排序模式:相关性优先 / 星标优先(默认:相关性优先)
- 目标形态:xxx
- 偏好:xxx(可空)
- 排除:xxx(可空)
向用户确认以上信息。用户明确确认后才能进入环节二,否则停在这里继续对齐。
环节二:检索执行(以下环节由模型自主执行,无需用户介入,直到环节四交付报告)
第二步:检索词拆解(5-10 组)
目标:平衡"召回率"和"相关性",避免只靠单词硬搜导致偏题。
拆词规则:
每组 query 由以下维度组合:
- 核心词:用户目标词
- 同义词:替代表达(如 long-term memory / stateful memory)
- 场景词:coding、mcp、tool、platform、awesome、curated
- 技术词:agent、sdk、framework、database、os
- 排除思路:不在 query 里硬写过多负例,放到后续过滤阶段
产出格式:
Query-1: "xxx"
目的:高召回核心主题
Query-2: "xxx"
目的:补同义词盲区
第三步:执行检索与候选召回
执行原则:
- 每组 query 都执行检索(建议每组 30-50 条)。
- 合并结果形成候选池。
- 按
owner/repo去重。 - 记录检索时间与 API 额度信息。
候选池字段(最少):
owner/repostarsdescriptionrepo_urlarchivedlanguageupdated_attopicslicense
第四步:去重与硬过滤
硬过滤(默认):
stars >= 100archived = falseis:public
可选硬过滤(按需):
fork = false- 指定语言:
language:xxx - 更新时效:最近 6-12 个月
环节三:质量精炼
第五步:噪音剔除与相关性重排
目标:解决"命中 memory 但其实不是 agent memory"的噪音问题。
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 · 254 lines · 73 tokens per session scan A 61693206df37
github-repo-search is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,277 once invoked, about $0.0004 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
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…