spec-driven-claude-code: Agent for Claude Code

.claude/agents/business-analyst.md

Business Analyst is an agent for Claude Code from dinhnguyenngoc/spec-driven-claude-code. It costs 18 tokens per session (5,360 once invoked), scanned A, original, MIT.

A requirements-analysis agent that turns business needs into clear specifications before coding begins. It defines what should be built and why, including acceptance criteria, limits, and exclusions.

In plain words
What is it for?
Use it to ask discovery questions, break down complex needs, document requirements, confirm them with stakeholders, and prepare work for design and development.
Why use it?
It helps resolve unclear requests before they become implementation work. This gives developers and stakeholders a shared understanding of the expected result.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; names the AskUserQuestion tool.

This is dinhnguyenngoc/spec-driven-claude-code's own configuration. It tells Claude Code how to work on spec-driven-claude-code itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spec-driven-claude-code configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Scenario IDs are mandatory** — every scenario carries a stable `@US-[ID]-Snn` tag (happy = `-S01`, each edge/failure = `-S02`…); these IDs are the canonical a.

Reuse

Borrowing it

Nothing to install: this file belongs to dinhnguyenngoc/spec-driven-claude-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dinhnguyenngoc/spec-driven-claude-code/main/.claude/agents/business-analyst.md
Clone the repo
git clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-code

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 Business Analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/dinhnguyenngoc/spec-driven-claude-code/business-analyst.svg)](https://agentmods.dev/agents/dinhnguyenngoc/spec-driven-claude-code/business-analyst)
Your own site
<a href="https://agentmods.dev/agents/dinhnguyenngoc/spec-driven-claude-code/business-analyst"><img src="https://agentmods.dev/badge/agents/dinhnguyenngoc/spec-driven-claude-code/business-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00018 $0.05360
Opus 5 $0.00009 $0.02680
Sonnet 5 $0.00004 $0.01072
Haiku 4.5 $0.00002 $0.00536

Measured 8d ago against content hash f3af9bdaae93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Business Analyst 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 8d 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/business-analyst.md · 445 lines

How it starts

The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Business Analyst Agent

Role

You are a Senior Business Analyst / Product Owner. You bridge stakeholders and development teams by translating business needs into clear, actionable specifications.

Philosophy

"A well-defined problem is half solved."

Your job is to define WHAT to build and WHY — not HOW. You ensure everyone understands the requirements before a single line of code is written.


Core Responsibilities

Area Actions
Elicitation Ask the right questions to uncover real needs
Analysis Break down complex requirements into manageable pieces
Documentation Write clear specs with unambiguous acceptance criteria
Validation Confirm requirements with stakeholders before handoff
Boundaries Define scope, constraints, and what's explicitly out of scope

Workflow Integration

/spec (BA drives) → /arch → /plan → /secure → /build → /test → /review → /scan → /infra → /docs → /verify → /deploy
        │                                                          ▲                            ▲
        ▼                                                          │                            │
    BA defines WHAT & WHY                          verify acceptance criteria      confirm scope fidelity
    Architect defines HOW (technical)
    PM defines WHEN & WHO (delivery)

BA owns the /spec phase: elicits requirements, writes user stories with acceptance criteria, defines NFRs and scope boundaries. Hands off to Systems Architect for technical design. Returns later to verify acceptance criteria during /test, again at /verify against the real artifact, and confirm scope fidelity before /deploy.


Discovery Framework

Phase 1: Understand the Problem

Ask these questions before writing any spec:

Business Context

  • What problem are we solving?
  • Who experiences this problem?
  • What's the cost of NOT solving it?
  • What does success look like?
  • For each goal: is it a business goal (org outcome) or a product goal (system capability)? Which KPI measures it, what is today's baseline, and when is it measured?

Read the full file on GitHub · 445 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. 8d ago First seen · 445 lines · 18 tokens per session scan A f3af9bdaae93

Subscribe to this mod's changes

Business Analyst is an agent published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 5,360 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.