sdd-workflow

sdd-workflow is a cursor rule for coding agents from Desko77/cursor-1c-skills. It costs 12 tokens per session (2,503 once invoked), scanned A, original, MIT.

A nine-phase Specification-Driven Development workflow for planning complex 1C software changes before writing code. 1C is a business software platform commonly used for accounting and enterprise operations.

In plain words
What is it for?
Use it for 1C changes involving several modules, external integrations, architectural work, or complex business rules; it is not intended for trivial edits.
Why use it?
It reduces the risk of implementing the wrong design by requiring the specification to be prepared and reviewed first.

Cursor rule

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.

agentmods
npx agentmods add rules/desko77/cursor-1c-skills/sdd-workflow
Clone the repo
git clone --depth 1 https://github.com/Desko77/cursor-1c-skills

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 sdd-workflow

README.md
[![agentmods](https://agentmods.dev/badge/rules/desko77/cursor-1c-skills/sdd-workflow.svg)](https://agentmods.dev/rules/desko77/cursor-1c-skills/sdd-workflow)
Your own site
<a href="https://agentmods.dev/rules/desko77/cursor-1c-skills/sdd-workflow"><img src="https://agentmods.dev/badge/rules/desko77/cursor-1c-skills/sdd-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,503 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.02503
Opus 5 $0.00006 $0.01252
Sonnet 5 $0.00002 $0.00501
Haiku 4.5 $0.00001 $0.00250

Measured 5d ago against content hash 7f88dc2b9907, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-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 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.

rules/sdd-workflow.mdc · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specification-Driven Development (SDD)

Workflow разработки доработок 1С через спецификацию.

Применяется: при разработке доработок 1С, где требуется планирование.


Принцип

Спецификация создается и ревьюится ДО написания кода. Ошибки в плане дешевле ошибок в коде.


Когда применять

  • Доработки, затрагивающие несколько модулей/объектов
  • Интеграции с внешними системами
  • Архитектурные изменения
  • Задачи со сложной бизнес-логикой

Не применять для: тривиальных правок (одна строка, опечатка), простых баг-фиксов с очевидной причиной.


9 фаз

Фаза 0: Оценка сложности

Определить масштаб задачи и стратегию исследования.

Сложность Признаки Стратегия
Простая Одно изменение, очевидная реализация 1 исследование, 1 план
Средняя Несколько модулей, требует понимания архитектуры 1-2 исследования, 1 план
Сложная Много подсистем, неочевидные зависимости 2-4 параллельных исследования, варианты архитектуры
Критичная Архитектурные изменения, высокие риски 4+ исследований, мультисэмплинг архитектуры

Артефакт: оценка сложности с обоснованием и выбранной стратегией.


Фаза 1: Уточнение требований

Понять, что нужно построить.

  1. Если задача неясна - задать уточняющие вопросы:
    • Какую проблему решаем?
    • Что должна делать доработка?
    • Ограничения? Требования к производительности?
  2. Резюмировать понимание
  3. Получить подтверждение от пользователя

Артефакт: требования (исходный запрос, уточнения, ключевые требования, ограничения).


Фаза 2: Исследование кодовой базы

Понять существующий код и паттерны. Методология исследования - см. code-exploration-guide.md.

Количество параллельных исследований зависит от сложности (фаза 0). Каждое исследование фокусируется на своем аспекте: архитектура, данные, интеграции, производительность.

Что искать:

  • Похожие доработки и паттерны в проекте
  • Архитектура затрагиваемых подсистем
  • Точки интеграции
  • Потенциальные конфликты
  • Стандарты и методология ИТС, справка платформы (its_help, search_1c_documentation)

Read the full file on GitHub · 250 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.

  1. 5d ago First seen · 250 lines · 12 tokens per session scan A 7f88dc2b9907

Subscribe to this mod's changes

sdd-workflow is a cursor rule published in the GitHub repository Desko77/cursor-1c-skills (55 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 2,503 once invoked, about $0.0001 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 2026-08-30.