connector-assistant

connector-assistant is a skill for Claude Code, Codex from DemonDamon/AgenticX. It costs 110 tokens per session (3,789 once invoked), scanned A, original, Apache-2.0.

A conversation skill for creating and managing connectors, which link external systems such as APIs, remote tool servers, or databases to an agent. It distinguishes these connections from separate agent identities and ordinary tool installations.

In plain words
What is it for?
It is for listing available connection templates, reusing existing connections, asking for system and authentication details, creating connections, and testing connectivity.
Why use it?
It prevents duplicate connections and avoids collecting the wrong information or credentials. It also checks that a connection works after setup.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for listing available connection templates, reusing existing connections, asking for system and authentication details, creating connections, and testing connectivity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/demondamon/agenticx/connector-assistant
Install

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.

Any agent
npx skills add DemonDamon/AgenticX --skill connector-assistant
Clone the repo
git clone --depth 1 https://github.com/DemonDamon/AgenticX

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for connector-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/demondamon/agenticx/connector-assistant/github.svg)](https://agentmods.dev/skills/demondamon/agenticx/connector-assistant)
Your own site
<a href="https://agentmods.dev/skills/demondamon/agenticx/connector-assistant"><img src="https://agentmods.dev/badge/skills/demondamon/agenticx/connector-assistant/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.

agentmods 80×15 button for connector-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/demondamon/agenticx/connector-assistant"><img src="https://agentmods.dev/badge/skills/demondamon/agenticx/connector-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,789 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.03789
Opus 5.5 $0.00044 $0.01516
Sonnet 5.5 $0.00022 $0.00758
Haiku 4.5 $0.00011 $0.00379

Measured 7d ago against content hash 5a0b1ee10749, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

connector-assistant 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 7d 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.

agenticx/skills/connector-assistant/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

连接器助手

0. 概念:连接器 ≠ 分身

  • 连接器(Connector)=一个「模板实例」:把外部系统接进 Near,在「设置 → 连接器 → 我的连接」、市场卡片、对话框连接器选择器里只出现一次。三种形态:
    • mcp:远程 MCP Server(存于 ~/.agenticx/mcp.json);
    • rest:HTTP API,登记到本机连接器网关(connector-runtime,~/.agenticx/connector-runtime/connectors/<id>.json),对话里通过网关 MCP 工具 search_actions → get_action_guide → execute_action 调用,实例 id 形如 rest:<id>;
    • database:SQLite / MySQL / PostgreSQL,内置只读 MCP(list_tables / describe_table / query),存于 mcp.json。
  • 分身(Avatar)=另一个智能体人格,与连接器无关。
  • 通用 MCP Server ≠ 连接器:手动添加 / 导入 / 市场安装的 MCP 只在「插件市场 → MCP」里展示与管理,不进「我的连接」。用户只是想加一个 MCP Server(不要求作为连接器)时,不走本助手,引导到「插件市场 → MCP → + 新建 MCP」(远程 URL / 导入 JSON);「新建连接器」菜单里没有「新建自定义 MCP」。只有用户明确要把它作为连接器接入时,才用 connector_manage create 建(会打连接器标,出现在「我的连接」)。
  • 用户说「创建一个连接器 叫 abc」→ abc 是连接器名。禁止 create_avatar、禁止追问「abc 是不是分身」、禁止说「无法创建原生连接器」然后结束。

1. 工具

只用 connector_manage(不要手写 / file_edit mcp.json,不要 mcp_import):

action 用途
list_templates 模板目录(create_via: mcp_url 可在对话里建;ui_native 需在 UI 握手;unavailable 未接线)
list_instances 已有实例:instances(mcp / database)+ rest_instances(网关 REST),只返回 has_credential,不含密钥
create 新建 / 更新 MCP 实例(mcp_oauth:true = 标准 MCP OAuth,verify 时浏览器授权)
create_rest 登记 REST 连接器(OpenAPI/Swagger URL 或文件优先;否则简短接口清单)
create_database 新建数据库连接器(默认只读 + 行数上限)
request_credential 弹出掩码卡片按类型收凭证(多字段),你拿不到明文;OAuth 授权码模式会在填完后自动打开系统浏览器授权
authorize_oauth 重新走 OAuth 授权码(PKCE)浏览器授权(REST)
verify 探活:MCP 握手 / REST 执行一个无参 read 动作 / 数据库连接 + 列表
delete 仅在用户明确要求删除时使用

2. 流程(严格按序)

第 1 步:先盘点,避免重复建设

  1. 并行调用 connector_manage {action:"list_templates"} 与 {action:"list_instances"}。
  2. 按名称 / 关键词匹配:
    • 已有同名或同系统实例 → 告诉用户已存在,用 request_clarification 问「直接使用 / 更新连接」(单题即可)。选「更新」时 create 带 overwrite:true。
    • 命中模板且 create_via=mcp_url → 走模板实例:template_id 用该模板 id。模板带 mcp_url(官方端点,已核实)时不要再问地址,url 可省略(自动用 mcp_url);否则只问上游地址(第 2 步只保留 Q3)。认证方式按模板 auth:
      • mcp_oauth(官方远程 MCP,OAuth 2.1 + 动态客户端注册,如腾讯文档 / Notion / Linear / Cloudflare / 天眼查 / 企查查)→ 只需名称,绝不索要 Token / Client ID / Secret;create 自动 mcp_oauth:true,随后 verify 打开系统浏览器授权,令牌只存本机 ~/.agenticx/connectors/oauth/(0600)。
      • 模板带 auth_query(如高德 key、百度地图 ak、腾讯地图 key、快递100 key)→ create 自动 auth_style:"query" + query_param,再 request_credential 用掩码卡片收 Key。
      • 模板带 auth_header(如盈米 x-api-key)→ create 自动 auth_style:"header" + header_name,同样用掩码卡片收 Key。
      • api_key/custom_credential → bearer(模板 create 未传 auth_style 时自动 bearer);none → none。
      • 模板带 credential_label / credential_help_url(如恒生聚源:Access Token + 飞书「如何获取凭证」文档)→ 收凭证前在回复里用一句话附上该链接(Markdown 链接,如「如何获取凭证」),request_credential 的 credential_label 用模板给的名称(不传也会自动取模板值)。
    • 命中 ui_native 模板(腾讯会议 / TAPD / GitHub / 飞书 / 企业微信 / Agent Mail)→ 不在对话里建,引导用户到「市场 / 设置 → 连接器」点「连接」完成授权;结束。
    • 命中 unavailable 模板(OAuth 类)→ 说明暂未接线,可改用该服务的 MCP Server URL 走自定义。
    • 都不匹配 → 第 2 步。

Read the full file on GitHub · 159 lines

Changes

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.

  1. 7d ago First seen · 159 lines · 110 tokens per session scan A 5a0b1ee10749

Subscribe to this mod's changes

connector-assistant is a skill published in the GitHub repository DemonDamon/AgenticX (443 stars, last pushed today), licensed Apache-2.0. It adds 110 tokens to every session and 3,789 once invoked, about $0.0004 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 2026-10-09.