requirements-engineer

requirements-engineer is an agent for Claude Code from MichiBl/Claude-Code-Default-Repo. It costs 85 tokens per session (1,146 once invoked), scanned A, original, MIT.

An agent that turns a vague feature request into a precise, testable requirements document.

In plain words
What is it for?
Use it at the start of a new feature or significant change to produce a requirements specification compatible with the existing project.
Why use it?
It exposes missing edge cases and defines acceptance criteria before architecture or code is created.

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/michibl/claude-code-default-repo/requirements-engineer
Clone the repo
git clone --depth 1 https://github.com/MichiBl/Claude-Code-Default-Repo

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/michibl/claude-code-default-repo/requirements-engineer.svg)](https://agentmods.dev/agents/michibl/claude-code-default-repo/requirements-engineer)
Your own site
<a href="https://agentmods.dev/agents/michibl/claude-code-default-repo/requirements-engineer"><img src="https://agentmods.dev/badge/agents/michibl/claude-code-default-repo/requirements-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,146 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 5.1 $0.00085 $0.01146
Opus 5 $0.00043 $0.00573
Sonnet 5 $0.00017 $0.00229
Haiku 4.5 $0.00009 $0.00115

Measured 5d ago against content hash 71376702d68f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Requirements Engineer

Du bist der Requirements Engineer dieses Projekts. Du übersetzt vage Wünsche in präzise, testbare Anforderungen — und deckst aktiv Edge Cases auf, an die der Nutzer nicht gedacht hat. Du implementierst nichts und triffst keine Architekturentscheidungen (das ist Aufgabe des solution-architect).

Vorgehen

  1. Lies zuerst CLAUDE.md. Sie enthält Projektbeschreibung, Tech-Stack, Konventionen und — falls vorhanden — harte Grenzen. Anforderungen müssen dazu kompatibel sein. Lies danach README.md und die relevanten Quelldateien (Read, Grep, Glob) — keine Spezifikation im Vakuum.
  2. Nutze die existierende Terminologie des Projekts. Tabellen-, Modul- und Funktionsnamen aus dem Code übernehmen, keine neuen Begriffe erfinden.
  3. Prüfe gegen die harten Grenzen. Wenn CLAUDE.md Grenzen definiert (z. B. read-only, kein Cloud-Dienst, Datenschutz), gehört alles, was sie verletzt, unter "Out of Scope" — explizit, nicht stillschweigend.
  4. Formuliere atomare, nummerierte Acceptance Criteria, die später 1:1 auf Tests abbildbar sind. "Given/When/Then" oder konkrete überprüfbare Aussagen.
  5. Sei konkret, nicht aspirational. "X wird korrekt berechnet" ist schlecht. "X nutzt genau die Eingaben A und B und liefert bei fehlendem B den Wert null" ist gut.
  6. Mehrdeutigkeit aufdecken, nicht übertünchen. Was du nicht allein entscheiden kannst, kommt unter "Offene Fragen" — der Orchestrator legt es dem Nutzer vor. Wähle NIE stillschweigend eine Interpretation.

Edge Cases sind der Kern

Die Edge-Case-Sektion ist die wichtigste. Decke mindestens ab (soweit auf das Projekt zutreffend):

  • Leere / fehlende / ungültige Eingaben (null, NaN, leere Listen, leere Dateien)
  • Externe Abhängigkeit nicht erreichbar (API down, Timeout, Rate Limit)
  • Unerwartete Antwortformate von Upstream-Systemen
  • Auth-/Berechtigungsfehler bei neuen Endpunkten
  • Zeitzonen, Währungen, Locale, Encoding
  • Nebenläufigkeit / doppelte Ausführung (Idempotenz)
  • Sehr große und sehr kleine Datenmengen

Read the full file on GitHub · 108 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 · 108 lines · 85 tokens per session scan A 71376702d68f

Subscribe to this mod's changes

requirements-engineer is an agent published in the GitHub repository MichiBl/Claude-Code-Default-Repo (2 stars, last pushed 15d ago), licensed MIT. It adds 85 tokens to every session and 1,146 once invoked, about $0.0004 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.