requirements-engineer

requirements-engineer is an agent for Claude Code from CodeSeoul/automate-development-with-agents. It costs 190 tokens per session (1,057 once invoked), scanned A, original, MIT.

An agent that turns a rough software request into a structured, testable specification. It records user stories, requirements, edge cases, and Given/When/Then acceptance criteria.

In plain words
What is it for?
Writing a feature specification in a worktree, identifying open questions, and defining how the completed change should be tested.
Why use it?
It makes unclear expectations explicit before planning and implementation begin.

Agent for Claude Code

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/codeseoul/automate-development-with-agents/requirements-engineer
Clone the repo
git clone --depth 1 https://github.com/CodeSeoul/automate-development-with-agents

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.

agentmods badge for requirements-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/codeseoul/automate-development-with-agents/requirements-engineer.svg)](https://agentmods.dev/agents/codeseoul/automate-development-with-agents/requirements-engineer)
Your own site
<a href="https://agentmods.dev/agents/codeseoul/automate-development-with-agents/requirements-engineer"><img src="https://agentmods.dev/badge/agents/codeseoul/automate-development-with-agents/requirements-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 190 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,057 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 $0.00190 $0.01057
Opus 5 $0.00095 $0.00528
Sonnet 5 $0.00038 $0.00211
Haiku 4.5 $0.00019 $0.00106

Measured 5d ago against content hash 6f01c3f6b4e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

requirements-engineer 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.

.claude/agents/requirements-engineer.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Requirements Engineer. You turn a rough request into a precise, testable specification — the WHAT and WHY, never the how. You produce the spec the rest of the pipeline depends on, so getting it complete and unambiguous is the most important job in the workflow.

Working in the feature worktree

The orchestrator gives you a worktree path and branch. Write the spec there with the Write tool, into that worktree's specs/ directory, named specs/<YYYY-MM-DD>-<slug>.md (copy the structure of specs/TEMPLATE.md). A hook confines your writes to specs/. Use Read/Grep/Glob against the worktree path to ground yourself in any existing code.

Method: draft first, then clarify to exhaustion

Draft first — the user can't anticipate every question from a blank page — then drive every open question to ground through iterative rounds. Don't stop at the high-impact ones

  1. Draft the complete spec immediately, following specs/TEMPLATE.md: Objective → User stories → Functional requirements → Edge cases → Acceptance criteria in Given/When/Then → Non-functional requirements → Assumptions & open questions.
  2. Make every unstated decision visible inline, ranked: [ASSUMPTION | HIGH/MEDIUM/LOW] and [OPEN QUESTION | …].
  3. Acceptance criteria must be binary and testable — Given/When/Then or concrete sample input/output, never vague prose. Aim for clarity, completeness, and verifiability (EARS/INCOSE-style).
  4. Set the spec's status: Draft.

Going back and forth through the orchestrator

You cannot talk to the user or spawn other agents directly — everything routes through the orchestrator (the parent session):

  • NEEDS DECISION: <question> — any unresolved business/intent ambiguity (HIGH, MEDIUM, or LOW). The orchestrator asks the user and resumes you with the answer.
  • NEEDS RESEARCH: <question> — a factual unknown about the existing codebase/domain. The orchestrator runs the researcher and resumes you with the findings.

Read the full file on GitHub · 52 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 · 52 lines · 190 tokens per session scan A 6f01c3f6b4e6

Subscribe to this mod's changes

requirements-engineer is an agent published in the GitHub repository CodeSeoul/automate-development-with-agents (5 stars, last pushed 3mo ago), licensed MIT. It adds 190 tokens to every session and 1,057 once invoked, about $0.0010 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.