A specification-driven workflow for Oh My Engine that follows the OpenSpec format. It provides commands for importing requirements, proposing and planning changes, applying them, verifying the result and archiving completed work.

Use it to initialize the workflow, import a product brief or prompt, create a change proposal, plan and apply tasks, verify the result, and archive the change.

It gives development work a defined path from requirements to implementation and verification, so changes are easier to track and review.

How oh-my-engine/oh-my-engine configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to oh-my-engine/oh-my-engine. 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/oh-my-engine/oh-my-engine/main/.claude/skills/ome-spec/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/oh-my-engine/oh-my-engine

Made for: Claude Code.

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/oh-my-engine/oh-my-engine/ome-spec/github.svg)](https://agentmods.dev/skills/oh-my-engine/oh-my-engine/ome-spec)

Your own site

<a href="https://agentmods.dev/skills/oh-my-engine/oh-my-engine/ome-spec"><img src="https://agentmods.dev/badge/skills/oh-my-engine/oh-my-engine/ome-spec/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/oh-my-engine/oh-my-engine/ome-spec"><img src="https://agentmods.dev/badge/skills/oh-my-engine/oh-my-engine/ome-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,658 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	$0.00013	$0.02658
Opus 5	$0.00006	$0.01329
Sonnet 5	$0.00003	$0.00532
Haiku 4.5	$0.00001	$0.00266

Measured 9d ago against content hash ee5ea86b6ccf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ome-spec 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.

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.

.claude/skills/ome-spec/SKILL.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ome-spec

基于规范驱动的开发工作流，兼�?OpenSpec 的目录和生命周期，同时保�?Oh My Engine �?skill 分发和记忆系统�?

使用方法

# 初始�?spec 工作�?
/ome-spec init

# 导入 PRD / 提示�?/ 附件
/ome-spec import <change-id>

# 基于导入上下文拆�?spec 草案
/ome-spec decompose <change-id>

# 手工创建变更提案（保留）
/ome-spec propose <change-id>

# 约束较强的变�?
/ome-spec propose <change-id> --design-first

# Bug 修复
/ome-spec propose <change-id> --bugfix

# 细化设计与任�?
/ome-spec plan <change-id>

# 执行开�?
/ome-spec apply <change-id>

# 验证完成�?
/ome-spec verify <change-id>

# 归档并更新长期规�?
/ome-spec archive <change-id>

Claude Code 可直接使用上面的 slash command�? Codex 请按技能名 ome-spec 触发，并沿用相同子命令和参数�?

可执行入�?

主入口是 TypeScript 驱动�?ome spec�?

ome spec init
ome spec import <change-id> --source-file docs/prd.md --prompt-file docs/prompt.md
ome spec import <change-id> --source-text "Copied PRD text" --asset mockup.png
ome spec decompose <change-id>
ome spec propose <change-id>
ome spec plan <change-id>
ome spec apply <change-id>
ome spec apply <change-id> --task "Implement the change"
ome spec status <change-id>
ome spec verify <change-id>
ome spec archive <change-id>
ome spec propose <change-id> --design-first
ome spec propose <change-id> --bugfix

旧的 shell 兼容转发器已移除；统一使用 ome spec�?

脚本能力边界�?

init：创建工作区和默认配�?
import：将 PRD、提示词、附件归档到 context/
decompose：基�?context/ 准备 analysis.md 和标�?OpenSpec scaffold
propose：生�?change scaffold
plan：标记计划阶段并�?Planning Notes
apply：输出实现上下文、已采纳 skill �?execution directives，并支持勾选任�?验收项回写进�?
status：汇总当�?phase、任务计数、engine-memory context �?execution directive 数量
verify：基�?tasks.md、proposal.md 的勾选项、TBD: 模板标记检查、spec delta 完整性，以及 config.json 里的 verifyCommands 做通过/失败判断
archive：在 verify 通过后归�?change，并在首次接受时创建长期 capability spec，之后基于已接受 delta 重建 canonical summary/requirements/compatibility，同时持续同步当前快照与历史

apply 不会自动改业务代码；它会把已采纳 skill 转成必须遵循�?execution directives，直接作用于实现提示�?

目录约定

Spec 工作�?

.ome/omespec/
├── project.md
├── changes/
�?  └── <change-id>/
�?      ├── context/
�?      �?  ├── source.md
�?      �?  ├── prompt.md
�?      �?  ├── analysis.md
�?      �?  ├── references.json
�?      �?  └── assets/
�?      ├── proposal.md
�?      ├── design.md
�?      ├── tasks.md
�?      └── specs/
�?          └── <capability>/
�?              └── spec.md
├── specs/
�?  └── <capability>/
�?      └── spec.md
└── archive/

Read the full file on GitHub · 309 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.

9d ago First seen · 309 lines · 13 tokens per session scan A ee5ea86b6ccf

Subscribe to this mod's changes

ome-spec is a skill published in the GitHub repository oh-my-engine/oh-my-engine (5 stars, last pushed 7d ago), licensed MIT. It adds 13 tokens to every session and 2,658 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 2026-08-31.

OpenSpec Planning spec verification workflow

spec-writing

Write a spec that a different engineer could implement without asking questions. Invoke when starting a new feature, especially one that will be handed off or implemented later.

orlando-japan/claude-code-setting · 34 tokens

ai-loop

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

sickn33/agentic-awesome-skills · 28 tokens

workflow

Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…

jeremylongshore/tons-of-skills-marketplace · 101 tokens

Workspine

Disciplined repo-native workflow for AI-assisted development. Spec first, then build, then verify.

PatrickSys/workspine · 24 tokens

absolute-work

End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this…

maddhruv/absolute · 104 tokens

absolute-spec

Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review → stop. No task board, no build. Use when you want a spec to discuss, hand off, or review before committing to…

maddhruv/absolute · 122 tokens

oh-my-engine: Skill for Claude Code