Plugin Authoring

What it does

When your agent uses it

• Tasks that involve MCP servers

Example prompts

• “/plugin-authoring”

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

1. 1Use toolbox_list to inspect existing plugins and avoid duplicates.
2. 2If needed, create the plugin with toolbox_manage using kind="toolbox", action="create". New custom toolboxes start disabled so incomplete…
3. 3Create each TypeScript tool with toolbox_manage using kind="tool", action="create". The generated file is a valid SDK template and the…
4. 4Edit the generated .ts file with file_edit for precise changes or apply_patch for structural changes. Do not write source through bash.
5. 5Implement tools with the public SDK
6. 6Keep tool inputs small, explicit, and typed. Return normal MCP content; use structuredContent when structured output materially helps…
7. 7Never embed secrets in committed tool source or toolbox.json. Read credentials from an appropriate local secret/config source.
8. 8Use toolbox_manage with action="reload", then toolbox_list and verify there is no load error.
9. 9Enable the tool and then the toolbox only after the implementation loads successfully.
10. 10Use tool_search to confirm discovery and tool_call to run a realistic test.

What it can do on your machine

Read from SKILL.md and the folder at commit c6ae729. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Plugin Authoring loads about 709 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 322 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~31

When it runs · the whole SKILL.md, loaded when a task matches

~709

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from XiaoPuOuO/openchatx-mcp at commit c6ae729, republished under its MIT licence (© XiaoPuOuO). 322 words, ~709 tokens.

name

plugin-authoring

description

Create or revise openchatx-mcp Toolbox plugins and TypeScript tools from a user's natural-language request.

import { defineTool, z } from "openchatx-mcp/toolbox"

export default defineTool({
  name: "example",
  description: "Describe exactly when the agent should use this tool.",
  inputSchema: z.object({
    value: z.string(),
  }),
  async execute({ value }, context) {
    return {
      content: [{ type: "text", text: value }],
    }
  },
})

© XiaoPuOuO, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in toolboxes/toolbox-manager/skills/plugin-authoring of XiaoPuOuO/openchatx-mcp.

Open the folder on GitHubat commit c6ae729