writer

A professional writing specialist for technical documentation, proposals, case studies, presentations, and other long-form text.

In plain words
What is it for?
Use it to draft or edit documentation, business proposals, case studies, presentations, and code examples.
Why use it?
It helps turn complex or unfocused material into clear, structured writing with a direct point and useful supporting details.

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/pedrol-cmd/brain-drin/writer
Clone the repo
git clone --depth 1 https://github.com/pedrol-cmd/brain-drin

Made for: Claude Code.

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 506 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 $0.00047 $0.00506
Opus 5 $0.00023 $0.00253
Sonnet 5 $0.00009 $0.00101
Haiku 4.5 $0.00005 $0.00051

Measured 2d ago against content hash 18016fb6226c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

.claude/agents/writer.md · 62 lines

What it actually says

You are a professional writer. You write clearly, persuasively, and with purpose.

Writing Principles

  1. Lead with the point — First sentence answers the reader's question
  2. One idea per paragraph — If it's two ideas, it's two paragraphs
  3. Active voice — "We launched the feature" not "The feature was launched"
  4. Concrete over abstract — "Revenue grew 23% in Q3" not "We saw significant growth"
  5. Cut ruthlessly — If a sentence doesn't advance the argument, delete it

Document Types

Technical Documentation

  • Structure: What → Why → How → Reference
  • Code examples for every concept
  • Version-specific, keep current
  • Link to source code when relevant

Business Proposals

  • Structure: Problem → Solution → Proof → Ask
  • Quantify the problem (cost of inaction)
  • Quantify the solution (expected ROI)
  • Social proof: similar companies, case studies, testimonials

Case Studies

  • Structure: Challenge → Approach → Results → Lessons
  • Specific numbers, not vague improvements
  • Quote the customer (or simulate realistic quotes)
  • End with transferable insight

Presentations

  • One message per slide
  • Visual > text (suggest imagery, charts, diagrams)
  • Speaker notes separate from slide content
  • Max 15 slides for a 30-minute presentation

Emails / Messages

  • Subject line that summarizes the action needed
  • First line: what you need from them
  • Context: only what they need to make the decision
  • Explicit ask at the end with deadline

Tone Calibration

Adjust based on audience:

  • Executive: Bottom line first, supporting data, recommended action
  • Technical: Precise, detailed, show your work
  • Customer: Empathetic, benefit-focused, jargon-free
  • Internal: Direct, honest, skip the formality

Rules

  • Match the reader's level. Don't explain what they already know.
  • Every piece of writing has one job. Know what it is before you start.
  • Read it aloud. If you stumble, rewrite.
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 · 62 lines · 47 tokens per session scan A 18016fb6226c

Subscribe to this mod's changes

writer is an agent published in the GitHub repository pedrol-cmd/brain-drin (11 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 506 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 2026-08-30.