metaschema-module-authoring

metaschema-module-authoring is a skill for Claude Code from metaschema-framework/claude-plugins. It costs 36 tokens per session (4,537 once invoked), scanned A, original, CC0-1.0.

Guidance for creating and changing Metaschema modules, which are definitions of data structures that can be read and written as XML, JSON, or YAML.

In plain words
What is it for?
Use it to author modules in YAML or XML, define fields and structures, set namespaces and versions, and follow repository-specific conventions.
Why use it?
It helps developers design consistent data models and understand how the same model works across different file formats.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - href: ../common/common-types.yaml # YAML module.

Part of the metaschema plugin — 4 skills shipped together

Good fit Use it to author modules in YAML or XML, define fields and structures, set namespaces and versions, and follow repository-specific conventions.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/metaschema-framework/claude-plugins
agentmods
npx agentmods add skills/metaschema-framework/claude-plugins/metaschema-module-authoring

Made for: Claude Code.

Or install metaschema, the plugin that ships this one along with the rest of its 4 skills.

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 metaschema-module-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/metaschema-module-authoring/github.svg)](https://agentmods.dev/skills/metaschema-framework/claude-plugins/metaschema-module-authoring)
Your own site
<a href="https://agentmods.dev/skills/metaschema-framework/claude-plugins/metaschema-module-authoring"><img src="https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/metaschema-module-authoring/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 metaschema-module-authoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/metaschema-framework/claude-plugins/metaschema-module-authoring"><img src="https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/metaschema-module-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,537 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 $0.00036 $0.04537
Opus 5.5 $0.00014 $0.01815
Sonnet 5.5 $0.00007 $0.00907
Haiku 4.5 $0.00004 $0.00454

Measured 2mo ago against content hash 0ab6a02e370f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

metaschema-module-authoring 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 2mo 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.

plugins/metaschema/skills/metaschema-module-authoring/SKILL.md · 673 lines

How it starts

The opening of the file, as written. The whole thing — 673 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metaschema Module Authoring

This skill guides the creation and modification of Metaschema modules, which define information models that can be serialized to XML, JSON, or YAML.

Repository-specific conventions (file locations, namespaces, testing) are in .claude/rules/metaschema-authoring.md.

Module Authoring Formats

Metaschema modules can be authored in either XML or YAML format. These formats are semantically equivalent:

  • Both produce identical module definitions
  • Both enable parsing and serialization of data in all three formats (XML, JSON, YAML)
  • The choice of authoring format does not limit the data formats the module can handle

For example, a module written in YAML can parse XML documents and serialize to JSON, and vice versa. The authoring format is purely a developer preference.

Module Structure

YAML Format

---
METASCHEMA:
  schema-name: Human-readable module name
  short-name: module-short-name
  namespace: http://example.com/ns/module
  json-base-uri: http://example.com/ns/module
  schema-version: 1.0.0
  definitions:
  - object-type: assembly
    name: root-assembly
    # ... definition content

XML Format

<?xml version="1.0" encoding="UTF-8"?>
<METASCHEMA xmlns="http://csrc.nist.gov/ns/oscal/metaschema/1.0">
  <schema-name>Human-readable module name</schema-name>
  <schema-version>1.0.0</schema-version>
  <short-name>module-short-name</short-name>
  <namespace>http://example.com/ns/module</namespace>
  <json-base-uri>http://example.com/ns/module</json-base-uri>

  <define-assembly name="root-assembly">
    <!-- definition content -->
  </define-assembly>
</METASCHEMA>

Required Header Elements

Element Description
schema-name Human-readable module name for documentation
schema-version Semantic version (e.g., 1.0.0)
short-name Unique identifier, used in artifact names
namespace XML namespace URI for elements
json-base-uri URI for JSON Schema $schema keyword

Read the full file on GitHub · 673 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. 2mo ago First seen · 673 lines · 36 tokens per session scan A 0ab6a02e370f

Subscribe to this mod's changes

metaschema-module-authoring is a skill published in the GitHub repository metaschema-framework/claude-plugins (10 stars, last pushed 8mo ago), licensed CC0-1.0. It adds 36 tokens to every session and 4,537 once invoked, about $0.0001 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 2026-08-31.

Related

metaschema-module-authoring compared with skills from other repositories

metaschema-module-authoring next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
metaschema-module-authoringmetaschema-framework/claude-pluginsSkill108mo agoCC0-1.0A36Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k3d agoMITA200Claude Code, Codex
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill315k6d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code