Borrowing it
Nothing to install: this file belongs to CodeSeoul/automate-development-with-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CodeSeoul/automate-development-with-agents/main/.claude/agents/requirements-engineer.mdgit clone --depth 1 https://github.com/CodeSeoul/automate-development-with-agentsWrote 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.
[](https://agentmods.dev/agents/codeseoul/automate-development-with-agents/requirements-engineer)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00190 | $0.01057 |
| Opus 5.5 | $0.00076 | $0.00423 |
| Sonnet 5.5 | $0.00038 | $0.00211 |
| Haiku 4.5 | $0.00019 | $0.00106 |
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 1mo 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.
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
- 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. - Make every unstated decision visible inline, ranked:
[ASSUMPTION | HIGH/MEDIUM/LOW]and[OPEN QUESTION | …]. - 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).
- 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.
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.
- 1mo ago First seen · 52 lines · 190 tokens per session scan A 6f01c3f6b4e6
requirements-engineer is an agent published in the GitHub repository CodeSeoul/automate-development-with-agents (5 stars, last pushed 5mo ago), licensed MIT. It adds 190 tokens to every session and 1,057 once invoked, about $0.0008 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 2026-08-31.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.