Borrowing it
Nothing to install: this file belongs to wyattowalsh/agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wyattowalsh/agents/main/AGENTS.mdgit clone --depth 1 https://github.com/wyattowalsh/agentsWrote 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.
[](https://agentmods.dev/instructions/wyattowalsh/agents/agents-md)<a href="https://agentmods.dev/instructions/wyattowalsh/agents/agents-md"><img src="https://agentmods.dev/badge/instructions/wyattowalsh/agents/agents-md/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.
<a href="https://agentmods.dev/instructions/wyattowalsh/agents/agents-md"><img src="https://agentmods.dev/badge/instructions/wyattowalsh/agents/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.10668 | $0.10668 |
| Opus 5.5 | $0.04267 | $0.04267 |
| Sonnet 5.5 | $0.02134 | $0.02134 |
| Haiku 4.5 | $0.01067 | $0.01067 |
Grade B, and why
agents AGENTS.md scanned grade B with 1 finding 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 1mo 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
| Portable Agent Plugin | `plugin.json`, `mcp.json`, `skills/` | Agent Plugins 1.0 source package with strict Agent Skills and only the secret-free MCPHub `harness` default | How it starts
The opening of the file, as written. The whole thing — 536 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@./instructions/global.md
AGENTS.md — AI Agent Asset Standards
This file is the source of truth for asset formats, naming conventions, and workflows in this repository.
1. Asset Formats
Skill Format (skills/<name>/SKILL.md)
Skills use YAML frontmatter followed by a markdown body.
Required fields:
| Field | Type | Constraints |
|---|---|---|
name |
string | kebab-case, max 64 chars, must match directory name |
description |
string | non-empty, max 1024 chars |
Optional fields (portable Agent Skills contract):
| Field | Type | Description |
|---|---|---|
license |
string | SPDX identifier (for example, MIT) |
compatibility |
string | Environment requirements, max 500 characters |
allowed-tools |
string | Space-delimited tool allowlist (experimental) |
metadata |
map of string->string | Namespaced or project metadata |
Root skill frontmatter is a strict portable source surface. Do not add
Claude-, Cursor-, Codex-, Grok-, OpenCode-, or VS Code-specific keys to
skills/*/SKILL.md. Typed native values such as argument-hint, model,
context, agent, user-invocable, disable-model-invocation, hooks,
paths, and the repository's boolean internal behavior live only in
config/skill-adapters.json. Every target/field pair must explicitly preserve
or degrade there; generated native packages merge the overlay without mutating
the portable source.
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.
- 1mo ago Changed · +71 lines · +1,315 tokens per session scan A → B 70340217cf57
- 1mo ago First seen · 465 lines · 9,353 tokens per session scan A 493741a06fda
agents AGENTS.md is an instructions file published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 10,668 tokens to every session, about $0.0427 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.