Borrowing it
Nothing to install: this file belongs to taichuy/1flowbase. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/taichuy/1flowbase/main/.agents/skills/backend-development/SKILL.mdgit clone --depth 1 https://github.com/taichuy/1flowbaseWrote 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/taichuy/1flowbase/backend-development)<a href="https://agentmods.dev/skills/taichuy/1flowbase/backend-development"><img src="https://agentmods.dev/badge/skills/taichuy/1flowbase/backend-development/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/taichuy/1flowbase/backend-development"><img src="https://agentmods.dev/badge/skills/taichuy/1flowbase/backend-development.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 | $0.00056 | $0.01238 |
| Opus 5.5 | $0.00022 | $0.00495 |
| Sonnet 5.5 | $0.00011 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
backend-development 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 17d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Development
Outcome and Entry
把已确认目标落到正确的后端 owner，保持 contract、状态和调用边界。先读 api/AGENTS.md；改 crate 前读 crates/AGENTS.md，再读改动目录的局部规则。复用用户已确认的目标、授权与 AC，不重复审批。
行为验证使用 test-driven-development；只有业务语义、权限、数据影响或范围尚未确定时回到 problem-framing，不把局部实现判断变成新的产品决策。
Backend Architecture Map
先理解 请求架构与调用生命周期 的总体结构与维护边界，再按任务读主题，无需先遍历全项目架构。
api-server（唯一进程内 composition root）
Protocol Adapter → Canonical Interface / 冻结计划
→ typed Handler → Business / Execution
→ 结果与收尾 → 协议投影
- Protocol Adapter 负责协议解析、认证接入和响应投影；业务入口经注册 Binding / Plan 进入统一调用内核。
- Canonical Interface 拥有调用身份、阶段与终态；业务 owner 拥有规则和事务，执行与存储模块承接稳定 ports。
- 调用终态、业务 commit/rollback、协议 delivery/ack 各有 owner，不能互相推断；关闭连接不自动等于取消业务。
- 这是调用关系，不是 Cargo 依赖图。crate owner 与允许依赖只维护在
api/crates/AGENTS.md；实际 mount 与 Catalog、声明与编译快照的关系由架构文档解释。 - 插件选型按治理边界、贡献、执行方式与作用域分别判断；可信宿主内部实现归 HostExtension，公开协议受管贡献不因设置页、数据或接口注册而升级类型。旧 RuntimeExtension / CapabilityPlugin 分配限制单独作为当前实现事实取证。
Truth and Task Routing
架构文档定义关系，AGENTS 定义执行约束，源码与运行态揭示实际行为。三者不一致时定位偏离；不自动扩大授权去改架构或业务语义。
| 当前任务 | 读取与定位 |
|---|---|
| 接口装配、认证、Binding、Kernel、stream / cancel / deadline | interface-lifecycle → 架构对应主题 |
| API 输入输出、错误模型 | api-design → route / DTO / typed Handler |
| 状态转换、事务、幂等 | state-and-consistency → 状态写 owner |
| 核心与适配器、外部依赖、HostExtension | boundary-design → 局部 AGENTS / ports |
| 新资源或实现落点 | implementation-rules |
| Rust 类型、async、锁与实现自查 | rust-backend-practices 的相关章节及 completion self-check |
| 内置模型、metadata overlay、runtime read model | builtin-data-model-contract |
| Settings API、注册、角色 operation 授权 | console-settings-registration |
| Agent Flow 节点输入、debug artifact、运行日志 | agentflow-runtime-node-payload |
| 新抽象、公共参数、重复防御、转发层 | design-rules；具体坏味道查 anti-patterns |
| 判断规则例外 | examples |
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.
- references/agentflow-runtime-node-payload.md 2.4 KB
- references/anti-patterns.md 588 B
- references/api-design.md 841 B
- references/boundary-design.md 2.6 KB
- references/builtin-data-model-contract.md 2.8 KB
- references/console-settings-registration.md 3.5 KB
- references/examples.md 695 B
- references/implementation-rules.md 3.5 KB
- references/interface-lifecycle.md 2.9 KB
- references/rust-backend-practices.md 5.8 KB
- references/state-and-consistency.md 1.6 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.
- 17d ago Changed fe365146c408
- 1mo ago Changed · -31 lines · -61 tokens per session 68775f406156
- 2mo ago First seen · 93 lines · 117 tokens per session scan A 08c0f353288a
backend-development is a skill published in the GitHub repository taichuy/1flowbase (284 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 1,238 once invoked, about $0.0002 per session on Opus 5.5. 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
llm-pipeline
Use when wiring several LLM calls into a production flow: typed contracts between steps, a router/gateway so 429s, timeouts and outages fail over instead of taking you down, and cost control via caching, model tiers and abort caps. NOT single-prompt wording (that is prompt-engineering), NOT a model-driven tool loop…
10router-add-provider
Self-serve adding a custom OpenAI/Anthropic-compatible upstream provider (baseUrl + its own API key + models) to a running 10Router — no source change, no repackage, live immediately. Use when the user wants to register a self-hosted gateway / sk-xxx / baseUrl as a routable node, or an agent needs to add a custom…
10router
Entry point for 10Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 10Router, TENROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…
10router-dev
A development and troubleshooting guide for 10Router, a local AI routing gateway that sends client requests to models. It covers its Next.js deployment on a network-attached storage device (NAS).
unified-ai-gateway
Operate and evaluate Unified AI System through fifteen governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.
omni-inference
The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.