agentmods.dev

product-workflow

product-workflow is a skill for Codex from ehlyzov/skills. It costs 66 tokens per session (9,244 once invoked), scanned A, original, MIT.

A set of instructions for creating product documents such as product requirements, user scenarios, roadmaps, and implementation plans.

In plain words
What is it for?
It is for documenting product goals, current user journeys, feature effects, decisions, roadmaps, and plans for implementation or hardening.
Why use it?
It helps turn a product request into structured documents and plans while keeping product planning separate from ordinary coding work.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Codex.

not rated 2repo 11d ago A scan 66 tokens original MIT

Good fit It is for documenting product goals, current user journeys, feature effects, decisions, roadmaps, and plans for implementation or hardening.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ehlyzov/skills/product-workflow
View source ↗ ehlyzov/skills
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 ehlyzov/skills --skill product-workflow
Clone the repo
git clone --depth 1 https://github.com/ehlyzov/skills

Made for: Codex.

Its marketplace also offers this one on its own, as the plugin product-workflow — /plugin install product-workflow after adding the marketplace above.

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.

agentmods badge for product-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/ehlyzov/skills/product-workflow/github.svg)](https://agentmods.dev/skills/ehlyzov/skills/product-workflow)
Your own site
<a href="https://agentmods.dev/skills/ehlyzov/skills/product-workflow"><img src="https://agentmods.dev/badge/skills/ehlyzov/skills/product-workflow/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.

agentmods 80×15 button for product-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/ehlyzov/skills/product-workflow"><img src="https://agentmods.dev/badge/skills/ehlyzov/skills/product-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,244 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.09244
Opus 5 $0.00033 $0.04622
Sonnet 5 $0.00013 $0.01849
Haiku 4.5 $0.00007 $0.00924

Measured 9d ago against content hash 5411343f3168, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

product-workflow 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build_pdf.sh, scripts/verify_artifacts.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

product-workflow/SKILL.md · 438 lines

How it starts

The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Workflow

Скилл создаёт продуктовые документы и планы. Он не исполняет утверждённый технический план и не управляет обычной разработкой. Выбирай только те артефакты и фазы, которые пользователь запросил явно; полный пакет не является режимом по умолчанию.

Возможные выходы:

  1. Продуктовое описание (docs/product/overview.md + docs/product/scenarios/01..N.md) — задача, персоны, проблемы, цели, N сценариев по строгому шаблону.
  2. Журнал решений (docs/product/decisions.md) — варианты, факты, trade-offs, рекомендация агента и явный статус решения.
  3. Baseline текущих сценариев (docs/product/current-scenario-baseline.md + docs/product/scenario-cards.md + docs/product/scenario-graph.dot) — карта существующих сценариев, компактные пользовательские истории, страницы и переходы, если продукт уже существует или задача является доработкой.
  4. Impact-документ инкремента (docs/product/increments/<feature>-impact.md) — как новая фича расширяет, меняет или добавляет сценарии относительно baseline.
  5. План реализации (docs/plans/<product>-implementation-plan.md) — command-level задачи T0..TN для оркестратора + worker-а.
  6. План усиления (docs/plans/<product>-hardening-plan.md) — архитектура / безопасность / поддерживаемость, не добавляющая функционала; задачи H1..HN с зависимостями от T-задач.
  7. Независимый вердикт и PDF (docs/product/validation/verdict.md + PDF в ~/Downloads/) — stakeholder-facing продуктовый документ без T/H-планов по умолчанию.

Независимый верификатор обязателен только для полного PRD/delivery package, stakeholder PDF и явно запрошенного финального product gate. Для узкого режима он проверяет только созданный артефакт и его прямые источники. Не заставляй малую задачу оплачивать аудит полного продуктового архива.

Когда использовать

  • Пользователь явно сказал: «нужно продуктовое описание», «PRD по фиче X», «спроектируй сценарии», «составь продуктовый план реализации», «hardening plan», «оформи продукт».
  • Есть кодовая база и нужно зафиксировать её продуктовое лицо + roadmap.
  • Нужно встроить новую фичу или доработку в уже существующий продукт, не создавая сценарный «остров».
  • Есть идея/новый продукт без кода — нужно собрать целостную картину сценариев + план.
  • Пользователь хочет один артефакт-PDF для шеринга со стейкхолдерами.

Read the full file on GitHub · 438 lines

Files

What ships with it

26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 438 lines · 66 tokens per session scan A 5411343f3168

Subscribe to this mod's changes

product-workflow is a skill published in the GitHub repository ehlyzov/skills (2 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 9,244 once invoked, about $0.0003 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.

PlanningWriting and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens