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 agentmods add skills/taichuy/1flowbase/backend-developmentnpx skills add taichuy/1flowbase --skill backend-developmentgit clone --depth 1 https://github.com/taichuy/1flowbaseWhat 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 | $0.00117 | $0.01834 |
| Opus 5 | $0.00059 | $0.00917 |
| Sonnet 5 | $0.00023 | $0.00367 |
| Haiku 4.5 | $0.00012 | $0.00183 |
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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Development
Overview
本 Skill 是 1flowbase 后端实现期的边界守门员,不负责替代需求对齐或 QA 验收。进入这里时,默认已经有清晰目标、范围、成功标准和用户拍板点;本 Skill 只负责把已确认的 backend / API / Rust 任务按项目规则落到 api/。
Entry Contract
- 需求仍有数据、contract、migration、权限、状态归属、架构方向或跨模块职责选择时,先回
problem-framing。 - 涉及可测试行为变化时,先联动
test-driven-development;不能走 TDD 时,交付说明必须写明替代验证。 - 用户要求自检、验收、回归、质量报告或证据结论时,切到
qa-evaluation。 - 后端 API / 状态入口缺少已确认的接口预期、验收证据或测试设计时,不在实现期补需求;回到
problem-framing/test-driven-development。 - 进入
api/前先读api/AGENTS.md;存在更近的AGENTS.md时按最近规则执行。
When to Use
- 设计已确认后的接口、动作入口、模块边界、route / service / repository / adapter 实现。
- 调整状态流转、关键领域对象、写路径、事务边界或一致性规则。
- 实现 Rust / Axum API、storage adapter、migration、mapper、worker、runtime 后端逻辑。
- 收口多个模块直接改同一关键状态的问题。
- 处理 HostExtension / RuntimeExtension / CapabilityPlugin / Resource Action Kernel 的后端实现边界。
不要用于
- 纯视觉、交互、信息架构设计。
- 纯需求澄清、方案选择、issue shaping 或 ADR。
- 纯 QA 报告、回归结论或质量门禁路由。
Core Invariants
- 稳定核心决定“该不该做”;边界适配层负责“怎么做到”;关键状态只能从清晰唯一入口改变。
- 核心业务规则不得直接依赖外部协议格式、存储细节、provider stdout / stderr 或临时 UI 形态。
- 能力边界优先使用能力名,具体实现留在 adapter / repository / driver。
- API 输入保持短、平、单动作;新接口、service、repository 方法必须命名具体。
- 状态集合、流转规则、动作约束、幂等语义和错误边界必须显式。
- Rust 实现要用类型表达核心不变量、显式传播错误、封装状态转换,并把阻塞 IO、锁、事务和外部副作用放在清晰边界内。
- 系统内置数据模型、运行时读模型或
model_definitions / model_fields / scope_data_model_grants改动必须区分 system-owned contract 与 user-owned metadata;不可用 migration / reconcile 覆盖用户或管理员 metadata。 - 后台注册设置项是后端拥有的安全对象,不是前端页面权限;稳定
feature_id同时拥有 console surface 与 Settings API scope,角色只授权feature_id,不再展开一组可编辑 action grant。 - Settings API 在 Core 启动或 HostExtension 加载时绑定到唯一注册项;请求只校验绑定后的
feature_id与领域数据约束,不按页面 URL 推断权限,也不在请求期扫描或动态拼装 action 集合。 - 未注册、重复归属或引用 inactive feature 的 Settings API 必须 fail closed;不得保留 allow-by-default、前端兜底或管理员可编辑的 route-to-permission 表。
- 新抽象、公共接口、bool/flag 参数、helper/manager/utils、pass-through service 或重复 defensive check,先读
../_shared/design-rules.md;命中则回到problem-framing做更小 redesign。
Implementation Routing
- AI-friendly API rules:
references/api-design.md。 - State and consistency review:
references/state-and-consistency.md。 - Stable core vs adapter rules:
references/boundary-design.md。 - Local implementation rules:
references/implementation-rules.md。 - Rust backend practice rules:
references/rust-backend-practices.md。 - Builtin data model contract / metadata overlay rules:
references/builtin-data-model-contract.md,命中系统内置表、runtime read models、数据建模定义 metadata、字段描述、scope grant 或 API exposure 时读取。 - Console settings registration:
references/console-settings-registration.md,命中后台设置注册、Settings API、角色设置授权、HostExtension console surface 或对应 CLI / inventory 时读取。 - Anti-decay patterns:
references/anti-patterns.md。 - Pressure scenarios:
references/examples.md。 - Agent Flow runtime node payload contract:
references/agentflow-runtime-node-payload.md,仅在调整运行日志、debug artifact、节点输入/数据处理/输出接口时读取。
What ships with it
10 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 2.1 KB
- references/builtin-data-model-contract.md 2.8 KB
- references/console-settings-registration.md 3.0 KB
- references/examples.md 695 B
- references/implementation-rules.md 3.1 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.
- 2d ago First seen · 93 lines · 117 tokens per session scan A 08c0f353288a
backend-development is a skill published in the GitHub repository taichuy/1flowbase (259 stars, last pushed 3d ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,834 once invoked, about $0.0006 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
sync-cliproxy-core
Use when asked to 同步、更新、升级或审计 CLIProxyAPI、cliproxy、translator core、provider adapters、Antigravity 请求/响应转换、internal/protocol/cliproxy 转换快照,刷新上游 commit,或审查一次核心与渠道适配器的原子同步结果。.
ccload-release
用于发布 ccLoad 新版本,自动提交未提交改动并推送本地领先的 master,按固定版本通道计算并发布 Tag,等待 GitHub Actions,以及验证 GitHub Release 和对应通道的容器镜像。Beta 固定沿用最近稳定版的主版本和次版本;只有显式 stable 发布才允许修改次版本。.
provider-architecture
LiteLLM-RS provider system in two tiers - data-driven OpenAI-compatible catalog entries auto-routed through OpenAILikeProvider, plus code-based provider modules implementing the LLMProvider trait behind the closed Provider enum. Covers unified ProviderError handling, connection pooling, capabilities, and model…
hecate-tauri
Use when working on the Hecate native desktop app in tauri/. Covers the Tauri 2.x Rust layer, sidecar lifecycle, platform bundling, and the gateway↔webview integration.
10router-chat
Chat / code generation via 10Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through 10Router.
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…