What is workflow-loop-me?

An interview guide for finding repeated work that could be delegated to an agent, such as handling tickets, reports, or support requests.

Use it after an initial requirements discussion to identify recurring work, review existing process documents, and write a detailed workflow specification.

It turns a vague idea for an agent into a specific workflow that can be implemented without leaving key questions unanswered.

workflow-loop-me — Skill for Claude Code and Codex by mekotenkov-ux

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.

Any agent

npx skills add mekotenkov-ux/seomeatagentscreator --skill workflow-loop-me

Clone the repo

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

Made for: Claude Code, Codex.

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/skills/mekotenkov-ux/seomeatagentscreator/workflow-loop-me/github.svg)](https://agentmods.dev/skills/mekotenkov-ux/seomeatagentscreator/workflow-loop-me)

Your own site

<a href="https://agentmods.dev/skills/mekotenkov-ux/seomeatagentscreator/workflow-loop-me"><img src="https://agentmods.dev/badge/skills/mekotenkov-ux/seomeatagentscreator/workflow-loop-me/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/skills/mekotenkov-ux/seomeatagentscreator/workflow-loop-me"><img src="https://agentmods.dev/badge/skills/mekotenkov-ux/seomeatagentscreator/workflow-loop-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,143 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00059	$0.01143
Opus 5.5	$0.00024	$0.00457
Sonnet 5.5	$0.00012	$0.00229
Haiku 4.5	$0.00006	$0.00114

Measured 2mo ago against content hash aebcf54a8609, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workflow-loop-me 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.

agent-system/skills/workflow-loop-me/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Loop Me

Задача - не просто понять, какого агента хочет пользователь, а выяснить, какие повторяемые рабочие процессы реально стоит делегировать агенту.

Используйте после grill-me и до архитектуры агента.

Prior art: loop/workflow lens вдохновлен открытым MIT skill loop-me by Matt Pocock: https://github.com/mattpocock/skills/blob/main/skills/in-progress/loop-me/SKILL.md

Главный принцип

Ищите loops: повторяемые паттерны в работе пользователя, команды, недели, дня, канала, inbox, issue flow, продажах, контенте, QA, исследованиях, отчетности или поддержке.

Workflow - это спецификация одного loop, которую можно реализовать как агентский процесс, обычный checklist, automation, tool run или гибрид. Не навязывайте AI, расписание, checkpoint или автономию, если интервью не доказало, что они нужны.

Правила интервью

Задавайте один материальный вопрос за раз.
Для каждого вопроса давайте recommended default, если он уместен.
Не превращайте разговор в длинную анкету.
Сначала ищите существующие артефакты: docs, tickets, reports, scripts, spreadsheets, inbox labels, calendars, SOPs, dashboards, logs.
Записывайте язык пользователя: как он сам называет каналы, события, роли, артефакты и проблемы.
Не проектируйте агента, пока ключевой workflow не описан как реализуемая спецификация.

Vocabulary

Используйте эти термины только когда они помогают уточнить процесс:

Loop - повторяемая активность или ситуация.
Workflow spec - документированная версия loop, пригодная для реализации.
Trigger - событие или расписание, которое запускает run.
Input - что приходит на вход: файл, issue, письмо, чат, URL, таблица, запрос, сигнал.
Actor - кто участвует: пользователь, клиент, reviewer, agent, tool, external system.
Tool/channel - где workflow живет: repo, CRM, docs, messenger, inbox, dashboard, IDE, CMS.
State - что нужно помнить между runs.
Artifact - что workflow создает или меняет.
Checkpoint - где человек должен принять решение или проверить результат.
Brief - короткая decision-ready выжимка для checkpoint, а не raw draft.
Push right - отложить checkpoint как можно дальше, чтобы человек видел уже подготовленное решение.
Done signal - внешний признак, что run завершен.
Failure mode - как workflow ломается и что делать.

Read the full file on GitHub · 88 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 · 88 lines · 59 tokens per session scan A aebcf54a8609

Subscribe to this mod's changes

workflow-loop-me is a skill published in the GitHub repository mekotenkov-ux/seomeatagentscreator (7 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,143 once invoked, about $0.0002 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 Planning

workflow-loop-me next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
workflow-loop-memekotenkov-ux/seomeatagentscreator	Skill	7	3mo ago	MIT	A	59	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code