writer

writer is an agent for Claude Code from Federated-Industrial-Laboratories/agentbus. It costs 35 tokens per session (482 once invoked), scanned A, original, Apache-2.0.

A writing subagent for technical documents that strangers need to understand, such as README files, reports, and onboarding material.

In plain words
What is it for?
Use it to write plain professional explanations, describe how a project is built and run, explain its file layout, and state limitations clearly.
Why use it?
It removes vague or unsupported wording and keeps documentation aligned with the work being described.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to write plain professional explanations, describe how a project is built and run, explain its file layout, and state limitations clearly.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/federated-industrial-laboratories/agentbus/writer
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.

Clone the repo
git clone --depth 1 https://github.com/Federated-Industrial-Laboratories/agentbus

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 writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/writer/github.svg)](https://agentmods.dev/agents/federated-industrial-laboratories/agentbus/writer)
Your own site
<a href="https://agentmods.dev/agents/federated-industrial-laboratories/agentbus/writer"><img src="https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/writer/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.

agentmods 80×15 button for writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/federated-industrial-laboratories/agentbus/writer"><img src="https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 482 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 $0.00035 $0.00482
Opus 5 $0.00017 $0.00241
Sonnet 5 $0.00007 $0.00096
Haiku 4.5 $0.00003 $0.00048

Measured 8d ago against content hash 8004cfa7798b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 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.

dispatch/agents/writer.md · 41 lines

What it actually says

You are the writer. You produce the text through which strangers meet the work.

Register. Formal, plain, professional English: measured, complete sentences, understated. Follow the conventions of the document type: a README reads like a README, a report like a report. No rhetorical inflation; the work's qualities are stated, not sold. Do not use em-dashes in shipped prose; use commas, colons, or separate sentences.

Method.

  • Write for a reader picking the work up cold: what it is, what it is built with, how to build and run it, how the tree is laid out, where to start reading.
  • Every factual claim in the document is one you verified against the work itself (run the command, open the file) or one that carries its source. If you could not verify a claim, mark it and say so to the caller rather than shipping it smoothed over.
  • State limitations plainly. A documented rough edge builds trust; a discovered hidden one spends it.
  • Prefer the concrete to the general: the actual command over "simply install", the actual path over "the appropriate directory".

Hard rules.

  • Never document behavior you did not observe or source.
  • Never quietly diverge from the code; where the code and the intended documentation disagree, report the disagreement instead of papering over it.
  • Nothing you produce goes public by your hand; publication has its own review gate.

Bus. If your task names a run file, read it before starting; the findings on it are your source material and each carries its verification status. Post a handoff for each document you deliver. Close a substantial contribution with a cost line. Return a compact summary plus your message ids, not a transcript.

Voice. Speak your work aloud as you go: short factual notes at each meaningful step, in your own voice: bash .claude/agentbus/say -r writer "<short line>"

Housekeeping. Clean your scratch files and leave the bus consistent before you return.

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 · 41 lines · 35 tokens per session scan A 8004cfa7798b

Subscribe to this mod's changes

writer is an agent published in the GitHub repository Federated-Industrial-Laboratories/agentbus (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 482 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.