byline: Instructions file for Claude Code

CLAUDE.md

byline CLAUDE.md is an instructions file for Claude Code from indianic/byline. It costs 2,024 tokens per session, scanned A, original, MIT.

A repository instruction file for Claude Code, an AI coding assistant, working on the Byline project. It defines how to verify changes, inspect real tool output, and handle claims about external systems.

In plain words
What is it for?
Use it when changing or testing Byline, especially for work involving external APIs, MCP tools, the filesystem, generated images, or live websites.
Why use it?
It reduces defects caused by trusting mocked tests, guessed API details, or output that was never checked. It tells the coding assistant when to test real boundaries such as HTTP services, files, and terminals.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is indianic/byline's own configuration. It tells Claude Code how to work on byline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything byline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to indianic/byline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/indianic/byline/main/CLAUDE.md
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 byline CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/indianic/byline/claude-md/github.svg)](https://agentmods.dev/instructions/indianic/byline/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/indianic/byline/claude-md"><img src="https://agentmods.dev/badge/instructions/indianic/byline/claude-md/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 byline CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/indianic/byline/claude-md"><img src="https://agentmods.dev/badge/instructions/indianic/byline/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,024 This file is loaded in full into every session.
When invoked 2,024 The same file — it is already loaded in full.
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 $0.02024 $0.02024
Opus 5.5 $0.00810 $0.00810
Sonnet 5.5 $0.00405 $0.00405
Haiku 4.5 $0.00202 $0.00202

Measured 1mo ago against content hash 077c13fb1eaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

byline CLAUDE.md 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 1mo 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.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

npm test                                              # unit suite, no network (vitest)
npx vitest run tests/tools.test.ts                    # one file
npx vitest run tests/tools.test.ts -t "schedule"      # one test by name
RUN_INTEGRATION=1 npx vitest run tests/integration/   # live Ghost/WordPress/research APIs; self-skips without a configured site
npm run typecheck                                     # tsc --noEmit, src/ only
npm run build                                         # tsc -> dist/
npm run dev                                           # tsx src/index.ts (MCP server over stdio)
BYLINE_DEBUG=1 byline <cmd>                           # CLI with stack traces

Two entry points, one binary: bin/byline.js dispatches to the CLI when stdin and stdout are a TTY, otherwise to the MCP server. Its Node-version guard must stay free of import, node: and top-level await.

Architecture in one screen

The host model does the thinking; Byline does everything that touches the outside world. A post moves through the MCP tools in src/tools/ in this order: research_topic (optional, src/plugins/research/) → build_writing_brief (src/craft/brief.ts + dimensions.ts, seeded random per-article hook/arc/voice/texture/author-presence) → the host writes HTML → score_draft (src/craft/score.ts, mechanical regex checks; only platform_html, structure and ai_summary_block block) → generate_image(s)/upload_image(s)/find_media/use_media → create_post with write-back diffing. Personas are YAML in ~/.byline/personas/ (src/config/personas.ts; unknown fields are kept as extras and rendered into the brief, never dropped).

Three invariants shape the code more than anything else:

  • Brief and scorer share one definition. BANNED, BANNED_CONSTRUCTIONS and THRESHOLDS live in score.ts; brief.ts imports them so what the writer is warned about and what it is marked down for cannot drift.
  • HtmlProfile drives platform-specific prose. Ghost's is a constant; WordPress's is resolved per user from unfiltered_html and fails toward restrictive. src/cli/ names no platform or provider; src/craft/ and src/tools/ take platform-specific prose from HtmlProfile rather than branching on the platform, with one documented exception in media-tools.ts.
  • Plugins register in one place each: platforms in src/plugins/registry.ts, provider families (images, research) in src/plugins/providers.ts. src/cli/ walks their CredentialField descriptors and names no platform or provider.

Read the full file on GitHub · 142 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. 1mo ago Changed · +56 lines · +754 tokens per session 077c13fb1eaa
  2. 2mo ago First seen · 86 lines · 1,270 tokens per session scan A a4851874d97e

Subscribe to this mod's changes

byline CLAUDE.md is an instructions file published in the GitHub repository indianic/byline (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,024 tokens to every session, about $0.0081 per session on Opus 5.5. 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.

Related

byline CLAUDE.md compared with instructions from other repositories

byline CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
byline CLAUDE.mdindianic/bylineInstructions file21mo agoMITA2,024Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode