write-series

write-series is a command for Claude Code from indianic/byline. It costs 24 tokens per session (1,024 once invoked), scanned A, original, MIT.

A command that writes and publishes one article through Byline, an article-writing service, using a fixed sequence of steps. It creates a brief, writes the HTML, and verifies the result.

In plain words
What is it for?
Use it to create and publish one article for a specified persona, topic, website, and word count.
Why use it?
It reduces the number of tool calls needed for a single article while retaining the required checks. It also makes the choice between evergreen and recent-news writing explicit.

Command 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 commands/indianic/byline/write-series
Clone the repo
git clone --depth 1 https://github.com/indianic/byline

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 write-series

README.md
[![agentmods](https://agentmods.dev/badge/commands/indianic/byline/write-series.svg)](https://agentmods.dev/commands/indianic/byline/write-series)
Your own site
<a href="https://agentmods.dev/commands/indianic/byline/write-series"><img src="https://agentmods.dev/badge/commands/indianic/byline/write-series.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,024 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 $0.00024 $0.01024
Opus 5 $0.00012 $0.00512
Sonnet 5 $0.00005 $0.00205
Haiku 4.5 $0.00002 $0.00102

Measured 4d ago against content hash fc0d2b2a88bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-series 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 4d 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/commands/write-series.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write and publish ONE article using the Byline MCP tools. Arguments: $ARGUMENTS

Run these steps in order. The point of this command is that a correct article costs six tool calls, not the eighteen a series run used to take. Do not add calls the steps below do not ask for.

1. Brief — one call

build_writing_brief with the persona, topic, target site, and word_count.

Choose mode deliberately. blog for anything evergreen; news only when the piece genuinely turns on events of the last 30 days, and then research is mandatory and must come from exactly one origin. If it is unclear which, ask the user rather than guessing.

Read the SCORECARD TARGETS block in the returned brief. It prints the exact integers score_draft will measure this article against — evidence items, attribution markers, question headings, first-hand moments, sentence-length spread, paragraph-run cap — already computed for your word count. Hitting them while writing is the whole reason a revision round is avoidable. Note the look value from the IMAGES block; every image in this article must use it.

2. Write the draft

Write the full HTML now, to the brief and to those targets. Two things people get wrong:

  • The NEVER USE THESE list in the brief is the exact lexicon that is graded. It is printed from the scorer's own array, so there is no second list to guess at.
  • Leave exactly one [[content_image]] placeholder for the in-body image.

3. Images — one call

generate_images with every image the article needs in a single call: a hero, the in-body image, and any gallery frames. Pass the same look to each, and give each a distinct slot.

Do not read the generated files back. The result already carries width, height, format and mime, read from the image bytes. Reading a PNG through a vision model to confirm its dimensions is the single most wasteful thing this pipeline used to do.

Check every entry: a batch reports ok: false per image rather than failing as a unit. If one was refused on safety grounds, reword that prompt and re-run only that slot with generate_image.

Read the full file on GitHub · 89 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. 4d ago First seen · 89 lines · 24 tokens per session scan A fc0d2b2a88bc

Subscribe to this mod's changes

write-series is a command published in the GitHub repository indianic/byline (2 stars, last pushed 23d ago), licensed MIT. It adds 24 tokens to every session and 1,024 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 2026-08-31.