agents-standards

A set of rules for formatting coding-agent assets in `AGENTS.md`, including skills, agents, and connections to external tools. It defines required names, descriptions, file layouts, and optional settings.

In plain words
What is it for?
Checking or creating compliant skill folders, agent files, and tool-connection definitions.
Why use it?
It prevents assets from using inconsistent names or structures that other tools may not understand.

Cursor rule for Cursor

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/agents-standards
Clone the repo
git clone --depth 1 https://github.com/wyattowalsh/agents

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 559 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00559
Opus 5 $0.00000 $0.00280
Sonnet 5 $0.00000 $0.00112
Haiku 4.5 $0.00000 $0.00056

Measured 2d ago against content hash 9daebef35d51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents-standards 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 2d 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/agents-standards.mdc · 45 lines

What it actually says

Asset Format Standards

This repo is a cross-platform AI agent asset bundle. All assets must conform to the formats defined in AGENTS.md.

Skills (skills/<name>/SKILL.md)

  • YAML frontmatter followed by markdown body.
  • Required frontmatter: name (kebab-case, max 64 chars, must match directory name), description (non-empty, max 1024 chars).
  • Optional cross-platform fields: license, compatibility, allowed-tools, metadata.author, metadata.version, metadata.internal.
  • Optional Claude Code extensions: argument-hint, model, context, agent, user-invocable, disable-model-invocation, hooks.
  • Body text must use imperative voice: "Check the logs" not "Checks the logs".
  • Supports substitutions: $ARGUMENTS, $ARGUMENTS[N], $N, ${CLAUDE_SESSION_ID}, !`command`.

Agents (agents/<name>.md)

  • YAML frontmatter followed by a markdown system prompt.
  • Required frontmatter: name (kebab-case, must match filename without .md), description (non-empty).
  • Optional fields: tools, disallowedTools, model, permissionMode, maxTurns, skills, mcpServers, memory, hooks.

Naming Conventions

  • All names: kebab-case (^[a-z0-9][a-z0-9-]*$).
  • Skills: directory name matches frontmatter name.
  • Agents: filename (without .md) matches frontmatter name.
  • MCP servers: directory name matches package name (minus mcp- prefix).

Memory System (Agents)

  • memory scope options: user (cross-project, ~/.claude/agent-memory/), project (.claude/agent-memory/, git-tracked), local (.claude/agent-memory/, gitignored).
  • Choose the narrowest scope. Keep memory files under 200 lines. Use MEMORY.md as entrypoint.

Validation

  • Run wagents validate after modifying skills or agents to check frontmatter.
  • Do not hand-edit README.md or generated docs pages; regenerate them via wagents readme and wagents docs generate.
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. 2d ago First seen · 45 lines · 0 tokens per session scan A 9daebef35d51

Subscribe to this mod's changes

agents-standards is a cursor rule published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 559 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.