specification-writing

specification-writing is a skill for Claude Code, Codex from dhofheinz/open-plugins. It costs 64 tokens per session (1,904 once invoked), scanned A, original, MIT.

A reference for writing precise software specifications, including requirement formats and acceptance criteria.

In plain words
What is it for?
Use it to write EARS requirements, Given/When/Then acceptance criteria, RFC 2119 terms such as MUST and SHOULD, requirement IDs, and specification quality checks.
Why use it?
It helps turn vague requests into requirements that developers can implement and test without guessing what each statement means.

Skill for Claude CodeCodex

Part of the refinery plugin — 2 skills, 6 agents shipped together

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 skills/dhofheinz/open-plugins/specification-writing
Any agent
npx skills add dhofheinz/open-plugins --skill specification-writing
Clone the repo
git clone --depth 1 https://github.com/dhofheinz/open-plugins

Made for: Claude Code, Codex.

Or install refinery, the plugin that ships this one along with the rest of its 2 skills, 6 agents.

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 specification-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/dhofheinz/open-plugins/specification-writing.svg)](https://agentmods.dev/skills/dhofheinz/open-plugins/specification-writing)
Your own site
<a href="https://agentmods.dev/skills/dhofheinz/open-plugins/specification-writing"><img src="https://agentmods.dev/badge/skills/dhofheinz/open-plugins/specification-writing.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,904 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 $0.00064 $0.01904
Opus 5 $0.00032 $0.00952
Sonnet 5 $0.00013 $0.00381
Haiku 4.5 $0.00006 $0.00190

Measured 5d ago against content hash 76b33c086949, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specification-writing 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.

plugins/refinery/skills/specification-writing/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specification Writing — Core Reference

This skill is preloaded by the refinery:spec-writer agent via its skills: frontmatter field. Its content becomes part of spec-writer's system context at agent startup. This skill is not user-invocable — it has no behavior on its own; it is reference material consulted by the agent during synthesis.

The same content (in a slightly different rendering for mode/stage files) lives in ${CLAUDE_SKILL_DIR}/../refine/references/requirement-syntax.md. The two files MUST stay in sync (per NFR-M-001 single-source-of-truth discipline). When updating one, update the other.

1. EARS — Easy Approach to Requirements Syntax

EARS provides six patterns for unambiguous functional requirements. Every functional requirement (FR-NNN) MUST use one of the six patterns.

1.1 Ubiquitous (always active)

The <system> shall <required behavior>.

When to use: a behavior that holds at all times.

Example: "The system shall maintain audit logs for all administrative actions."

1.2 Event-Driven (responds to a trigger)

When <trigger>, the <system> shall <required behavior>.

When to use: a behavior that responds to a discrete event.

Example: "When a user submits a login form, the system shall validate the credentials within 200ms."

1.3 State-Driven (active during a state)

While <state>, the <system> shall <required behavior>.

When to use: a behavior that holds during a specific operational state.

Example: "While the database is in maintenance mode, the system shall reject all write requests with HTTP 503."

1.4 Unwanted Behavior (defensive)

If <unwanted condition>, then the <system> shall <required behavior>.

When to use: a behavior that handles error or exceptional conditions.

Example: "If the upstream API returns a 5xx response, then the system shall retry up to three times with exponential backoff."

1.5 Optional Feature (conditional capability)

Where <feature is included>, the <system> shall <required behavior>.

Read the full file on GitHub · 200 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 · 200 lines · 64 tokens per session scan A 76b33c086949

Subscribe to this mod's changes

specification-writing is a skill published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,904 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.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens