Borrowing it
Nothing to install: this file belongs to YG3-ai/yg3-mcp. 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/YG3-ai/yg3-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/YG3-ai/yg3-mcpWrote 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/yg3-ai/yg3-mcp/agents-md)<a href="https://agentmods.dev/instructions/yg3-ai/yg3-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yg3-ai/yg3-mcp/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/yg3-ai/yg3-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yg3-ai/yg3-mcp/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 | $0.01099 | $0.01099 |
| Opus 5 | $0.00549 | $0.00549 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
yg3-mcp AGENTS.md 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 5d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YG3 MCP — instructions for coding agents
Use this when building GTM systems, marketing automation, or local-business sites where the agent should operate real marketing infrastructure — not mock data.
When to use YG3
- The task needs a real marketing workspace: site, blog, brand voice, SEO content, later outbound/ads
- No human is available to create a YG3 account or complete OAuth mid-build
- You are wiring YG3 into an agent framework, CI pipeline, or SDK runtime
Do not provision YG3 if:
- The human already has a YG3 account → use OAuth MCP at
https://mcp.yg3.ai/mcpinstead (https://www.yg3.ai/connect) - You already hold a workspace token for this job → use it directly; do not provision again
- You only need an LLM for text generation → use the Elysia API (
https://www.yg3.ai/for-developers), not MCP
Never ask the user to choose a "client" or "operator" account. There is no such signup fork. New humans create an account at https://www.yg3.ai/get-started?plan=free, then add the MCP connector. Login resolves whether they are an agency admin or a workspace owner. client_user in API docs means a workspace-scoped token — not a signup type.
Standard flow
1. Provision
POST https://agency.yg3.ai/api/v1/workspaces
Content-Type: application/json
{"domain":"{business-domain.com}","industry":"{industry}","location":"{city, state}"}
Store the returned token securely. Use mcp_endpoint or https://mcp.yg3.ai/mcp for all MCP calls.
Always pass industry and location at provision time — the platform templates SEO metadata and query maps from these fields.
2. Orient
Call these MCP tools first:
whoami— confirm scopeget_client_snapshot— full workspace stateget_setup_health— integration status (never infer connection state from memory)read_platform_docwithslug: "getting-started"if you need operating rules
3. Build
Typical setup sequence:
set_business_profile— industry, location, who they serveset_brand/ voice tools — how copy should read- Site design tools — pages, blocks, theme
create_post→publish_post— content on the free subdomain
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.
- 5d ago Changed · +2 lines · +94 tokens per session 9dac0cf58175
- 9d ago First seen · 135 lines · 1,005 tokens per session scan A 49afa5e09f30
yg3-mcp AGENTS.md is an instructions file published in the GitHub repository YG3-ai/yg3-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 1,099 tokens to every session, about $0.0055 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 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.