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 lishuangqiang/backend-agent-resume-scout --skill backend-agent-project-selectorgit clone --depth 1 https://github.com/lishuangqiang/backend-agent-resume-scoutWrote 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/lishuangqiang/backend-agent-resume-scout/backend-agent-project-selector)<a href="https://agentmods.dev/skills/lishuangqiang/backend-agent-resume-scout/backend-agent-project-selector"><img src="https://agentmods.dev/badge/skills/lishuangqiang/backend-agent-resume-scout/backend-agent-project-selector/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/lishuangqiang/backend-agent-resume-scout/backend-agent-project-selector"><img src="https://agentmods.dev/badge/skills/lishuangqiang/backend-agent-resume-scout/backend-agent-project-selector.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 | $0.00168 | $0.02644 |
| Opus 5 | $0.00084 | $0.01322 |
| Sonnet 5 | $0.00034 | $0.00529 |
| Haiku 4.5 | $0.00017 | $0.00264 |
Grade A, and why
backend-agent-project-selector 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
后端 / Agent 项目选择器
能力范围
从 GitHub / Web 搜索适合写进简历的后端项目或完整业务型 Agent 项目，筛选后生成 backend-agent-project-resume-pack.md。
推荐模式是必填项。用户必须指定 agent-only、backend-only、mixed、safe-mode、challenge-mode 中的一种；如果用户初始化找项目、选择项目、推荐项目或生成简历项目但没有指定模式，先完整列出所有可选模式并让用户选择，不要开始搜索或生成推荐。
必须遵守
- 用户每次初始化找项目、选择项目、推荐项目或生成简历项目时，如果推荐模式缺失，必须先完整列出所有可选模式并反问，不能自行默认、推断或继续执行。
- 除非用户明确要求不要联网，否则要搜索当前 GitHub / Web 项目后再推荐。
- 优先完整业务系统，避免 demo、插件、薄封装、纯框架和只会调用一次大模型的项目。
backend-only不要默认只推荐 API 网关、IAM、调度、监控等底层技术项目；除非用户明确要求基础设施 / 中间件，否则应优先覆盖电商交易、内容社区、协作办公、工单客服、CRM/ERP、知识库、网盘、在线教育等完整业务项目。- 不要避开有业务闭环的业务项目；只避开浅层 CRUD、教程复刻、没有状态流转 / 异步链路 / 失败恢复 / 权限边界的业务项目。
- 默认不要把 IoT、嵌入式、硬件接入、设备管理、工业控制类平台作为后端项目推荐；除非用户明确要求硬件 / IoT / 物联网方向，否则这些项目应降权或淘汰。
- 先构建多样化候选池，再做最终选择；不要直接推荐全局高星项目，也不要把 star 数作为主要排序依据。
- star 数只作为“项目已有一定社区验证”的弱信号：达到 1k star 即可纳入正式候选池并认真评估；超过 1k 后不应因为 star 更高而显著加分。
- 搜索候选时必须主动覆盖中等 star 区间和细分领域项目，避免只用
sort=stars或只看几万 star 项目；后端和 Agent 项目都适用该规则。 - 候选池阶段要读取 README 前若干行做项目类型 probe，用于判断是否为业务系统、框架 / SDK / 桌面壳 / 工具链；README probe 只能用于筛选和项目定位，不能支撑最终“负责功能 / 技术难点”。
- 构建候选池时优先使用
references/search_github_candidates.py自动搜索、README probe、去重、分桶和初筛；如果手动搜索，最终也要输出同等字段的候选池和短名单确认内容。 - 拉取最终候选源码前，必须先向用户展示 3-4 个短名单项目、每个项目的选择理由和主要淘汰理由，并等待用户确认方向；用户确认后才能执行
pull_github_repos.py。 - 最终入选项目前必须运行
references/pull_github_repos.py真实拉取对应 GitHub 仓库到本地；未经过该脚本成功拉取并写入 manifest 的项目不得进入最终推荐。 - 源码验证只能基于
pull_github_repos.py拉取到本地的仓库目录进行；不能用 GitHub raw/API、README、网页搜索、模型记忆或经验判断替代本地源码验证。 - 如果脚本执行失败、仓库无法拉取、manifest 中该仓库状态不是
cloned、本地源码不可读，或无法从源码提取至少 5 个证据点，该项目必须淘汰。 - 必须区分
已有能力、建议改造、可写入简历。 - 简历功能点默认输出为“建议简历功能点（完成对应改造后可写）”；除非用户明确已经实现或本轮完成代码改造，否则不能把建议改造写成已完成成果。
- 项目亮点必须挖掘技术难度，不能只写“实现功能 / 接入组件 / 提供接口”；优先挖数据同步与一致性、MQ 异步链路、缓存与高并发、并发控制与幂等、任务调度、线程池与异步编排、流量治理、数据库优化、检索索引、权限安全、可观测性、接口治理、规则引擎、状态机、文件处理、实时通信、交易链路、Agent 工程等机制。
- 默认使用中文输出，除非用户要求其他语言。
参考资料加载
按任务需要加载，不要一次性加载所有资料：
references/执行流程.md：项目选择任务必载。references/用户输入模板.md：用户需要模板、示例，或推荐模式缺失需要反问时加载。references/筛选评分.md：筛选、分桶、推荐模式打分时加载。references/简历写法.md：写简历条目和面试问题前加载。references/输出模板.md：生成最终 Markdown 文件前加载。references/search_github_candidates.py：候选池搜索和短名单确认前优先执行；用于自动搜索 GitHub、读取 README probe、去重、分桶、排除前端 / 库 / IoT / 框架 / SDK / 桌面壳 / coding-agent 工具链等不合适项目，并生成候选池 JSON 与短名单预览 Markdown。references/pull_github_repos.py：最终候选源码验证前必须执行；用于真实拉取 GitHub 仓库并生成本地源码 manifest。references/markdown_to_pdf.py：最终交付必执行；将最终 Markdown 转成浅色、中文友好的 PDF。references/规则索引.md：只在需要查看文档映射关系时加载。
What ships with it
11 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.
- agents/openai.yaml 402 B
- references/markdown_to_apple_pdf.py 20 KB runs code
- references/markdown_to_pdf.py 20 KB runs code
- references/pull_github_repos.py 7.7 KB runs code
- references/search_github_candidates.py 22 KB runs code
- references/执行流程.md 8.6 KB
- references/用户输入模板.md 4.9 KB
- references/筛选评分.md 11 KB
- references/简历写法.md 16 KB
- references/规则索引.md 3.1 KB
- references/输出模板.md 6.8 KB
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 · 109 lines · 168 tokens per session scan A 523a89c71708
backend-agent-project-selector is a skill published in the GitHub repository lishuangqiang/backend-agent-resume-scout (319 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 168 tokens to every session and 2,644 once invoked, about $0.0008 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
aws-sdk-java-v2-core
Provides AWS SDK for Java 2.x client configuration, credential resolution, HTTP client tuning, timeout, retry, and testing patterns. Use when creating or hardening AWS service clients, wiring Spring Boot beans, debugging auth or region issues, or choosing sync vs async SDK usage.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…