A process for writing a technical design specification before starting a non-trivial coding task. Spec-driven development means agreeing on the design and requirements before implementation.

Planning new entities, subscription logic, payment integrations, and other tasks that need several implementation steps or architectural decisions.

It exposes important unknowns early and reduces the chance of building the wrong architecture or data model. Work pauses for answers when open questions could force a major rewrite.

How reorder-js/reorder configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to reorder-js/reorder. 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/reorder-js/reorder/main/.agents/skills/create-spec/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/reorder-js/reorder

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/reorder-js/reorder/create-spec/github.svg)](https://agentmods.dev/skills/reorder-js/reorder/create-spec)

Your own site

<a href="https://agentmods.dev/skills/reorder-js/reorder/create-spec"><img src="https://agentmods.dev/badge/skills/reorder-js/reorder/create-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/reorder-js/reorder/create-spec"><img src="https://agentmods.dev/badge/skills/reorder-js/reorder/create-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 668 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00050	$0.00668
Opus 5.5	$0.00020	$0.00267
Sonnet 5.5	$0.00010	$0.00134
Haiku 4.5	$0.00005	$0.00067

Measured 11d ago against content hash 07922fdac42e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-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 11d 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/skills/create-spec/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-driven development (Design Before Coding)

This skill enforces the "specification before code" approach inspired by OpenMercato's best practices. It prevents design mistakes and provides structure to the implementation process.

When to Create a Specification?

For any non-trivial task (e.g., adding a new entity, modifying subscription renewal logic, integrating a payment gateway) that requires at least 3 implementation steps or architectural decisions, you must first write a technical specification. Before drafting, consult docs/roadmap/README.md to verify the planned phase (Now, Next, or Later) and ensure the proposed scope aligns with consciously deferred boundaries.

Workflow

Language Requirement: The specification file MUST ALWAYS be written 100% in English, regardless of the conversation language.

Check Roadmap & Create a Skeleton Spec:
- Check docs/roadmap/README.md for existing architectural direction and boundaries.
- Create a file at .agents/specs/{date}-{title}.md.
- Use the YYYY-MM-DD format for date and kebab-case for the title.
- The skeleton should include a brief description (TLDR/Overview) and key objectives.
Open Questions Section:
- Before expanding the full specification, list key unknowns as a numbered list (Q1, Q2...).
- Focus on questions about architecture, data models, or scope, where an incorrect assumption would force you to rewrite large parts of the code.
- STOP and ask the user for answers to these questions. Do not write code or the full specification until the user responds.
Complete the Specification:
- After receiving answers from the user, complete the specification file with technical details (database schema, API contracts, implementation steps).
- Remove the Open Questions section.
Implementation Phases:
- Split the work into phases (e.g., Phase 1: Database & Module setup, Phase 2: Workflows & APIs, Phase 3: UI integration).
- Each step should represent a testable unit of work.

Read the full file on GitHub · 65 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.

11d ago Changed · +2 lines 07922fdac42e
2mo ago Changed · +2 lines 1929ddee699c
2mo ago First seen · 61 lines · 50 tokens per session scan A c1c718b262ad

Subscribe to this mod's changes

create-spec is a skill published in the GitHub repository reorder-js/reorder (59 stars, last pushed 12d ago), licensed MIT. It adds 50 tokens to every session and 668 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 2026-08-30.

Planning commerce e-commerce javascript medusa medusajs open-source

create-spec next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
create-specreorder-js/reorder	Skill	59	12d ago	MIT	A	50	Claude Code, Codex
task-manageriamlukethedev/Claw3D	Skill	2.4k	2d ago	MIT	A	56	Claude Code, Codex
soundclawiamlukethedev/Claw3D	Skill	2.4k	2d ago	MIT	A	18	Claude Code, Codex
todoiamlukethedev/Claw3D	Skill	2.4k	2d ago	MIT	A	12	Claude Code, Codex
saleor-paper-storefrontsaleor/storefront	Skill	1.6k	yesterday	none	A	68	Claude Code, Codex
paper-migrationssaleor/storefront	Skill	1.6k	yesterday	none	A	55	Claude Code, Codex
storefront-best-practicesmedusajs/medusa-agent-skills	Skill	235	2d ago	none	A	117	Claude Code

reorder: Skill for Claude Code