Rules and command guidance for creating new coding-agent skills, agents, and tool servers. It covers the required file structure, naming style, validation, and generated documentation.

Use it when adding or modifying a skill, agent, or MCP server, then validate the result and regenerate the repository README and documentation.

It helps keep new repository assets consistent and prevents invalid names, missing metadata, or outdated generated files.

new-assets — Cursor rule for Cursor by wyattowalsh: Rules and command guidance for creating new coding-agent skills…

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.

agentmods

npx agentmods add rules/wyattowalsh/agents/new-assets

Clone the repo

git clone --depth 1 https://github.com/wyattowalsh/agents

Made for: Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/wyattowalsh/agents/new-assets.svg)](https://agentmods.dev/rules/wyattowalsh/agents/new-assets)

Your own site

<a href="https://agentmods.dev/rules/wyattowalsh/agents/new-assets"><img src="https://agentmods.dev/badge/rules/wyattowalsh/agents/new-assets.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 495 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00495
Opus 5	$0.00000	$0.00247
Sonnet 5	$0.00000	$0.00099
Haiku 4.5	$0.00000	$0.00049

Measured 4d ago against content hash af3f66740c02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-assets 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 4d 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.

.cursor/rules/new-assets.mdc · 53 lines

What it actually says

Creating New Assets

Always use the CLI scaffolding commands and follow naming conventions. Do not create asset files manually from scratch.

CLI Commands

# Skills
wagents new skill <name>            # → skills/<name>/SKILL.md
wagents new skill <name> --no-docs  # Skip docs page scaffold

# Agents
wagents new agent <name>            # → agents/<name>.md

# MCP Servers
wagents new mcp <name>              # → mcp/<name>/ (server.py + pyproject.toml + fastmcp.json)

Naming

All names must be kebab-case: ^[a-z0-9][a-z0-9-]*$.
Skill directory name must match the frontmatter name field.
Agent filename (without .md) must match the frontmatter name field.
MCP server directory name should match the package name (minus mcp- prefix).

Validation

After creating or modifying skills/agents, run wagents validate to check frontmatter compliance.
After asset changes, regenerate derived artifacts:
- wagents readme — Regenerates README.md from repo contents.
- wagents docs generate — Regenerates MDX content pages for the docs site.

MCP Server Structure

First-party MCP servers in mcp/<name>/ must follow FastMCP v3 conventions:

Entry point: server.py with mcp = FastMCP("Name").
Config: fastmcp.json pointing to server.py with uv environment.
Package: pyproject.toml with fastmcp>=2 dependency.
Workspace: Root pyproject.toml must include the exact member path under [tool.uv.workspace], e.g. members = ["mcp/<name>"].

Bundle Root Policy

Do not duplicate skills/, agents/, mcp/, or instructions/ into platform-specific plugin folders.
The repository root is the canonical bundle root.

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.

4d ago First seen · 53 lines · 0 tokens per session scan A af3f66740c02

Subscribe to this mod's changes

new-assets is a cursor rule published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 495 tokens. 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.

Building agents

new-assets

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Creating New Assets

CLI Commands

Naming

Validation

MCP Server Structure

Bundle Root Policy

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

cli-error-handling

prefer-direct-imports-over-module-mocks

control-plane-descriptors

family-instance-domain-actions