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/basementstudio/xmcp/create-toolnpx skills add basementstudio/xmcp --skill create-toolgit clone --depth 1 https://github.com/basementstudio/xmcpWhat 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 | $0.00033 | $0.00902 |
| Opus 5 | $0.00016 | $0.00451 |
| Sonnet 5 | $0.00007 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
create-tool 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 3d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create xmcp Tool
You are helping the user create a new xmcp tool. Follow this interactive workflow.
Step 1: Gather Information
Before generating any code, ask the user these questions using AskUserQuestion:
-
Tool name (if not provided as argument): What should the tool be named? (Use kebab-case)
-
Handler type: Ask which handler type they need:
- Standard - For data queries, calculations, API calls (returns string/JSON)
- Template Literal (HTML) - For HTML widgets with external scripts
- React Component - For interactive stateful widgets (.tsx file)
-
Schema fields: What parameters should the tool accept? Ask for:
- Parameter name
- Type (string, number, boolean, enum, array, object)
- Description
- Whether it's optional
- Any validation rules
-
Annotations: Ask about behavior hints:
- Is it read-only? (doesn't modify environment)
- Is it destructive? (may delete or modify data)
- Is it idempotent? (repeated calls have same effect)
- Does it interact with external world? (openWorldHint)
-
Widget support (if Template Literal or React): Ask if they need:
- OpenAI tool invocation messages (invoking/invoked status)
- Widget accessibility (widgetAccessible)
- Widget-to-tool communication
Step 2: Generate the Tool
Create the tool file in src/tools/ with the appropriate extension:
.tsfor Standard and Template Literal handlers.tsxfor React Component handlers
File Location
src/tools/{tool-name}.ts # or .tsx for React
Tool Structure Reference
Every xmcp tool has three main exports:
// 1. Schema (optional) - Define parameters with Zod
export const schema = { /* ... */ };
// 2. Metadata (optional) - Tool configuration
export const metadata: ToolMetadata = { /* ... */ };
// 3. Handler (required) - Default export function
export default function handler(params) { /* ... */ }
Quick Reference
Essential Imports
import { z } from "zod";
import { type InferSchema, type ToolMetadata } from "xmcp";
What ships with it
1 file 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.
- 3d ago First seen · 118 lines · 33 tokens per session scan A c0c267dac205
create-tool is a skill published in the GitHub repository basementstudio/xmcp (1,324 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 902 once invoked, about $0.0002 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
openai-knowledge
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available…
om-create-agents-md
Create or rewrite AGENTS.md files for Open Mercato packages and modules. Use this skill when adding a new package, creating a new module, or when an existing AGENTS.md needs to be created or refactored. Ensures prescriptive tone, the Always/Ask First/Never/Validation Commands boundary structure, MUST-style rules…
om-share-this-session
Prepare and publicly share a complete sanitized coding-agent session plus a ZIP of this session's generated files, then open an upstream harness-feedback issue. Use when the user says "share this session", "report this agent run", "udostępnij tę sesję", or "zgłoś przebieg agenta". Never use for automatic telemetry or…
om-module-scaffold
Build a complete standalone business app, module, or CRUD vertical slice using Open Mercato discovery, commands, APIs, ACL/setup, UI, events, search, migrations, and tests. Use for customer management, deal-pipeline changes, CRM lead capture, library/booking/rental systems, "create a module", "add CRUD entity"…
agentic-code-orchestrator
Unified codebase manipulation, AI deployment, data analysis, and academic delivery engine. Absorbs 6 coding protocols + data-analysis + academic-delivery + spec-driven-dev.
om-evolve-harness
Add a reproducible standalone agent-harness use case or correct failed routing/context with semantic assertions, one knowledge owner, and before/after evaluation. Use for "add harness case", "agent got this wrong", "extend the harness", "new use case", or "rozszerz harness".