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/mcp-configuration-developmentnpx skills add taichuy/1flowbase --skill mcp-configuration-developmentgit 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/mcp-configuration-development)<a href="https://agentmods.dev/skills/taichuy/1flowbase/mcp-configuration-development"><img src="https://agentmods.dev/badge/skills/taichuy/1flowbase/mcp-configuration-development.svg" alt="Measured on agentmods" 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 | $0.00093 | $0.01580 |
| Opus 5 | $0.00046 | $0.00790 |
| Sonnet 5 | $0.00019 | $0.00316 |
| Haiku 4.5 | $0.00009 | $0.00158 |
Grade A, and why
mcp-configuration-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 5d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Configuration Development
Goal
把当前 1flowbase 源码表达的用户任务与可执行接口，转换为 Agent 可逐层发现、理解并调用的 MCP Virtual UI。GUI 与后端产品源码只作为只读取证；只修改完成任务所需的 MCP 配置数据，不把配置缺口伪装成产品代码任务。
Source of Truth
- 从 GUI 路由、页面、动作和状态文案提取用户目标、领域术语与操作顺序。
- 从 backend interface catalog、DTO、领域状态与执行入口确认可调用契约。
- 从现有 MCP catalog 确认实例、Group、Tool、Binding 和 discovery policy 的真实状态。
- 以当前源码为原始说明文档，不维护会随产品漂移的静态应用能力清单。
开始设计前，必须完整读取：
- Virtual UI：目录投影、去重和探索原则。
- Source Routing：按问题选择证据源。
- Configuration Contract：字段职责与配置边界。
应用变更前读取与任务最接近的示例。验收前完整读取 Acceptance。
Workflow
- 确定一个边界清晰的用户任务范围，列出起点、目标结果和必要前置状态。
- 沿 GUI 源码还原人类完成该任务的路径，只提取用户目标和领域词，不复制纯展示组件树。
- 沿 backend/interface catalog 找到每个动作的可绑定接口，核对参数、结果、风险、权限和状态约束。
- 通过渐进列表、关键词和单项读取盘点现有 MCP catalog；只有结果规模可控时才读取完整 catalog，先判断复用、修复或新增。
- 设计 canonical Virtual UI：按用户目标组织 Group 路径，让一个业务能力只有一个规范入口；必要时用搜索和简短描述提高可发现性。
- 形成有限变更账本，记录计划创建、复用、更新和删除的 Tool、Group、Binding、mapping 与 policy，以及每项回滚身份；这些对象是本 Skill 的完整允许写集。
- 先验证一个代表性 Tool 的创建或更新与
mcp_get；通过后按Tool → Group → Binding → policy应用，避免先留下空目录。 - 在每项写入前复核接口仍可绑定、目标记录仍存在且当前值未并发变化；写入后重新读取确认落库结果。
- 创建会动态注册后续接口的资源时，先完成创建与生命周期切换，再重新发现 interface catalog；只为已经出现的动态接口配置 canonical Tool。
- 用 Agent 视角依次验证
mcp_list → mcp_get → mcp_call，覆盖成功路径和至少一个关键失败边界。 - 输出覆盖表、未覆盖能力和原因；区分配置、业务接口与运行时缺口。中途停止时按账本回滚本轮无消费者的半成品，不越界修代码。
Change Rules
- 保持 GUI 的任务顺序和术语，但合并重复出现的相同能力。
- discovery 保持直观、开放、渐进；权限与状态合法性由后端调用边界统一执行。
- 先复用已有 Tool，再考虑新增；复用要求执行 contract 与 Agent-facing 名称、描述、mapping 都对新入口真实，不因 interface 相同就复用领域专用 Tool。
- 使用稳定、任务导向的
tool_id、Group path 和显示名称；不要复述 HTTP method/path 充当用户语义。 short_description写“调用后得到什么”；普通能力的full_description使用空字符串""。- 仅当跨字段、跨 Tool、跨状态或跨制品的组合契约无法由其他字段表达，且缺失会导致错误调用时填写
full_description。 - 把 Agent 参数名、含义和必填性写入
input_mapping的映射配置；不要要求业务 DTO 重复维护 MCP 专用文案。 - Agent-facing 描述只写入 Group、Tool、mapping 与 policy 配置记录；不得为补 MCP 描述修改
web/、i18n、业务 catalog、后端 DTO / OpenAPI、migration、MCP 协议或运行时代码。 - 检查必需容器对象是否能由当前接口 request Schema 自动物化；用真实
mcp_call证明空对象可达目标业务边界，不为通过 Schema 伪造 selector 或占位值。 output_mapping只表达必要的结果投影；无需投影时使用{}，不得复制result_schema充当 mapping。- 创建父资源后先读取返回值或详情，确认系统是否已原子创建默认子资源；不要假定还需再次创建 Page Tab、默认节点或同类子项。
- 不配置
children_count；它由启用的子 Group、可见 Binding 和启用 Tool 在运行时派生。 - 不借配置任务调整产品语义、业务权限或产品源码。发现这些缺口时停止对应写入并报告证据。
What ships with it
8 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.
- 5d ago First seen · 74 lines · 93 tokens per session scan A 0550ccf60599
mcp-configuration-development is a skill published in the GitHub repository taichuy/1flowbase (259 stars, last pushed yesterday), licensed Apache-2.0. It adds 93 tokens to every session and 1,580 once invoked, about $0.0005 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。.
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-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.