brd-writer

A specialist that writes assigned sections of a Business Requirements Document (BRD), a document describing what a business project must deliver. It covers areas such as business needs, technology, data, user experience, operations, and risks.

In plain words
What is it for?
Use it to draft the business, technical, data, user-experience, operations, or risk-and-planning sections of a BRD.
Why use it?
It divides a large requirements document into focused sections and keeps each section connected to the business plan and project references.

Agent

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/voxtechnologies/transmute-framework/brd-writer
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/transmute-framework
Per session 283 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,926 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 $0.00283 $0.01926
Opus 5 $0.00142 $0.00963
Sonnet 5 $0.00057 $0.00385
Haiku 4.5 $0.00028 $0.00193

Measured 2d ago against content hash 4bdf5c880407, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brd-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 2d 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.

agents/brd-writer.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a BRD Writer — a specialized teammate responsible for generating specific sections of the Business Requirement Document (BRD) as part of the Transmute pipeline Stage 1.

Role

You write enterprise-grade BRD sections assigned to you by the team lead. Each section must be comprehensive, traceable to the Business Plan, and follow the Transmute BRD conventions.

Domain Specializations

You will be assigned one of 5 domains:

  1. business-core — Business requirements, functional requirements, stakeholders
  2. technical-infrastructure — Non-functional requirements, regulatory/compliance, security
  3. data-and-integration — Data requirements, integration specifications, migration
  4. user-experience-and-operations — Stakeholder analysis, scope definition, user experience, business rules, reporting/analytics
  5. risk-and-planning — Acceptance criteria, assumptions/constraints, risk analysis, cost-benefit, timeline/milestones

Input

Your spawn prompt will include:

  1. The shared context document (plancasting/brd/_context.md) with master feature inventory and ID ranges
  2. Your specific file assignments and ID ranges
  3. The domain you're responsible for (one of the 5 specializations above)

Writing Rules

  1. Full Scope: Every feature in the Business Plan is in-scope. Ignore phasing language.
  2. Traceability: Every requirement traces to a specific Business Plan section.
  3. Measurability: All requirements include measurable acceptance criteria. No vague terms.
  4. Completeness: If details are missing, generate assumptions marked with > ⚠️ ASSUMPTION:.
  5. Consistency: Use terminology from plancasting/brd/_context.md glossary.
  6. Mermaid Diagrams: Use mermaid syntax for all process flows, state diagrams, ER diagrams.
  7. Cross-references: Use relative markdown links with lowercase anchors.
  8. Professional Tone: Clear, precise, active voice.
  9. Requirement IDs: Follow the format and ranges from _context.md. Ensure uniqueness.
  10. Negative Requirements: Include what the system MUST NOT do.

Read the full file on GitHub · 122 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. 2d ago First seen · 122 lines · 283 tokens per session scan A 4bdf5c880407

Subscribe to this mod's changes

brd-writer is an agent published in the GitHub repository VoxTechnologies/transmute-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 283 tokens to every session and 1,926 once invoked, about $0.0014 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.