What is seomeatagentscreator AGENTS.md?

Repository instructions for Seomeat Agents Creator, a project for designing, testing, packaging, and publishing agent systems and skills. They describe the required workflow, language, safety controls, and release evidence.

Guiding agent-system discovery, specifications, permissions, evaluations, packaging, installation checks, independent review, and release decisions.

They give contributors a shared process for making agent packages reproducible and usable by a fresh installation, rather than relying on hidden chat context.

How mekotenkov-ux/seomeatagentscreator configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to mekotenkov-ux/seomeatagentscreator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mekotenkov-ux/seomeatagentscreator/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/mekotenkov-ux/seomeatagentscreator

Made for: Codex, OpenCode.

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/instructions/mekotenkov-ux/seomeatagentscreator/agents-md/github.svg)](https://agentmods.dev/instructions/mekotenkov-ux/seomeatagentscreator/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/mekotenkov-ux/seomeatagentscreator/agents-md"><img src="https://agentmods.dev/badge/instructions/mekotenkov-ux/seomeatagentscreator/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mekotenkov-ux/seomeatagentscreator/agents-md"><img src="https://agentmods.dev/badge/instructions/mekotenkov-ux/seomeatagentscreator/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 516 This file is loaded in full into every session.

When invoked 516 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00516	$0.00516
Opus 5.5	$0.00206	$0.00206
Sonnet 5.5	$0.00103	$0.00103
Haiku 4.5	$0.00052	$0.00052

Measured 2mo ago against content hash fe080895e0a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

seomeatagentscreator 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 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.

AGENTS.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Seomeat Agents Creator

Этот репозиторий содержит универсальную систему создания агентских систем и скиллов.

Назначение

Помогать проектировать, отлаживать, проверять, упаковывать и публиковать агентские системы так, чтобы они работали для fresh-agent без скрытого контекста текущего чата.

Рабочий порядок

Прочитайте agent-system/AGENTS.md.
Для нового агента начните с agent-system/skills/grill-me/SKILL.md, затем проведите workflow discovery по agent-system/skills/workflow-loop-me/SKILL.md.
До написания адаптеров заполните workflow notes/spec/ledger и agent-system/templates/agent-ir.template.json.
До заявлений о готовности создайте versioned system identity, harness boundary, default-deny permission policy, approval ledger, append-only run events, Eval Validity, Trigger Lab, trajectory-aware Output Eval и Assumption Registry. Затем соберите package, проверьте fresh install и independent review; только после этого закройте SHA-256 evidence bundle и финальный machine release decision по всем 13 gates.
Если пользователь дает ссылки на репозитории или инструменты, индексируйте их через agent-system/skills/repo-tool-librarian/SKILL.md; не встраивайте их без отдельного явного запроса.
Держите репозиторий универсальным: публикуйте только повторяемую методику, шаблоны, инструкции и чеклисты.
Используйте agent-system/references/frontier-harness-engineering.md; research-only приемы остаются experiment/defer до локального matched-budget holdout.

Язык

Основной язык проекта: русский. Английские имена файлов и полей используются только для переносимости между инструментами.

Безопасность

Публиковать можно только универсальные материалы:

инструкции;
шаблоны;
checklists;
публичные docs;
нейтральные примеры без данных реальных проектов.

Нельзя публиковать:

.env, токены, cookies, реальные credentials;
временные рабочие папки, debug-runs, browser profiles;
конкретные доменные скиллы и агенты;
непубличные источники, логи, отчеты, raw exports;
локальные абсолютные пути;
файлы, которые предполагают историю текущего чата.

Read the full file on GitHub · 41 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.

2mo ago First seen · 41 lines · 516 tokens per session scan A fe080895e0a8

Subscribe to this mod's changes

seomeatagentscreator AGENTS.md is an instructions file published in the GitHub repository mekotenkov-ux/seomeatagentscreator (7 stars, last pushed 3mo ago), licensed MIT. It adds 516 tokens to every session, about $0.0021 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.

Building agents

seomeatagentscreator AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
seomeatagentscreator AGENTS.mdmekotenkov-ux/seomeatagentscreator	Instructions file	7	3mo ago	MIT	A	516	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

seomeatagentscreator: Instructions file for Codex