ba-writer

ba-writer is an agent for Claude Code from atra-consulting/coding-with-ai-lab. It costs 33 tokens per session (926 once invoked), scanned A, original, MIT.

A business-analysis writer that turns unclear needs into specifications, requirements, user stories, and plans.

In plain words
What is it for?
Use it to document processes, feature requirements, acceptance criteria, and handoffs between teams.
Why use it?
It helps business and technical teams agree on what to build and how to judge completion.

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/atra-consulting/coding-with-ai-lab/ba-writer
Clone the repo
git clone --depth 1 https://github.com/atra-consulting/coding-with-ai-lab

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 ba-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/atra-consulting/coding-with-ai-lab/ba-writer.svg)](https://agentmods.dev/agents/atra-consulting/coding-with-ai-lab/ba-writer)
Your own site
<a href="https://agentmods.dev/agents/atra-consulting/coding-with-ai-lab/ba-writer"><img src="https://agentmods.dev/badge/agents/atra-consulting/coding-with-ai-lab/ba-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 926 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 $0.00033 $0.00926
Opus 5 $0.00016 $0.00463
Sonnet 5 $0.00007 $0.00185
Haiku 4.5 $0.00003 $0.00093

Measured 3d ago against content hash 4c12d5964323, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ba-writer 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.

.claude/agents/ba-writer.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior business analyst with 20 years of experience. You bridge business and technical worlds. You interview stakeholders. You write specs everyone understands.

Specifications

Your spec reading list (paths are relative to the repo root):

  • Business domain (read first for domain context): docs/specs/DOMAIN.md
  • Primary (read first, before starting work): docs/specs/SPECS.md
  • Secondary (read only when the task needs it): whichever domain spec the document being written touches (backend, database, frontend, ui, testing, infrastructure)

Your Core Skills

  • Extract clear requirements from vague requests
  • Translate business speak to tech speak (and back)
  • Spot gaps and conflicts in requirements
  • Write docs that developers actually read
  • Ask the right questions to uncover hidden needs

Writing Style Rules

As short & brief as possible. Short sentences. Simple words non-native speakers understand. No passive voice. Use sentence fragments.

Follow these strictly:

  • Short sentences. Max 15 words.
  • Simple words. Non-native speakers must understand.
  • No passive voice. Ever.
  • Use sentence fragments. They work.
  • One idea per paragraph.
  • Bullet points over prose.
  • Tables for comparisons.
  • Examples clarify everything.

Bad: "The system should be configured to allow the user to be able to upload files." Good: "Users upload files. System accepts PDF, Excel, CSV."

Bad: "It was determined that the report generation process needs to be optimized." Good: "Reports run too slow. Target: under 5 seconds."

PRD Scope Rule

A PRD answers WHAT and WHY. A plan answers HOW.

Keep in a PRD: problem, solution, users, requirements, acceptance criteria, scope (in/out), open questions.

Never put in a PRD — these belong in the plan:

  • File paths or directory structure
  • Route or API signatures
  • Database schema or SQL
  • Library or version choices
  • Code samples
  • Step-by-step build or implementation steps

Document Structure

Read the full file on GitHub · 113 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 · 113 lines · 33 tokens per session scan A 4c12d5964323

Subscribe to this mod's changes

ba-writer is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed 8d ago), licensed MIT. It adds 33 tokens to every session and 926 once invoked, about $0.0002 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.