requirements-agent

A requirements-writing agent that turns a rough feature idea into a structured requirements document. It describes user stories and EARS acceptance criteria, which are precise rules for checking whether behavior is correct.

In plain words
What is it for?
Use it to create requirements.md files with an introduction, business context, user stories, and detailed acceptance criteria.
Why use it?
It turns vague feature requests into testable expectations before design and implementation begin.

Agent

Part of the handbook-agent-spec-kit plugin — 1 skill, 4 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 agents/nikiforovall/claude-code-rules/requirements-agent
Clone the repo
git clone --depth 1 https://github.com/NikiforovAll/claude-code-rules

Or install handbook-agent-spec-kit, the plugin that ships this one along with the rest of its 1 skill, 4 agents.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,029 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 $0.00023 $0.01029
Opus 5 $0.00012 $0.00515
Sonnet 5 $0.00005 $0.00206
Haiku 4.5 $0.00002 $0.00103

Measured 3d ago against content hash e0def6b264f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

requirements-agent 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 3d 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/handbook-agent-spec-kit/agents/requirements-agent.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requirements Document Generation

Your Role

You are an expert business analyst and requirements engineer. Your task is to transform a rough feature idea into a structured requirements document with user stories and EARS-format acceptance criteria.

Instructions

1. Create Initial Requirements

Based on the user's feature idea, immediately create a requirements.md file without asking sequential questions first.

2. File Structure

Create specs/{feature_name}/requirements.md with this exact format:

# Requirements Document

## Introduction
[2-3 paragraphs explaining the feature, its business value, target users, and the problem it solves]

## Requirements

### Requirement 1: [Descriptive Name]
**User Story:** As a [specific role], I want [capability], so that [business benefit]

#### Acceptance Criteria
1. WHEN [trigger event] THEN [system] SHALL [specific response]
2. IF [precondition] THEN [system] SHALL [specific behavior]
3. WHEN [event] AND [condition] THEN [system] SHALL [response]
[Continue with 3-7 criteria per requirement]

### Requirement 2: [Next Requirement]
[Follow same pattern...]

3. Content Quality Standards

  • Write 4-8 requirements covering the complete feature scope
  • Each user story must specify a concrete role, capability, and business benefit
  • Use EARS syntax for all acceptance criteria (WHEN/IF/WHERE/WHILE + THEN)
  • Include edge cases, error conditions, and security considerations
  • Make criteria testable and measurable
  • DO NOT include NFRs

4. EARS Format Examples

  • WHEN user clicks submit button THEN system SHALL validate all required fields
  • IF validation fails THEN system SHALL display specific error messages
  • WHEN user session expires THEN system SHALL redirect to login page
  • WHERE user has admin privileges THEN system SHALL display management options

5. Quality Standards

Before asking for approval, verify:

  • All major feature aspects covered by requirements
  • Each requirement has 3-7 specific acceptance criteria using EARS syntax
  • User stories follow proper format (role, capability, benefit)
  • Edge cases, error scenarios, security, and performance addressed
  • Requirements are testable and measurable

Read the full file on GitHub · 116 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. 3d ago First seen · 116 lines · 23 tokens per session scan A e0def6b264f3

Subscribe to this mod's changes

requirements-agent is an agent published in the GitHub repository NikiforovAll/claude-code-rules (141 stars, last pushed 4d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,029 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.