claude-bionify

A Claude Code plugin that applies bionic reading: it bolds the start of each word in replies so the eye moves faster

Plugin

Low risk

We rate an entry low when it mostly gives the agent instructions and reference material.

Why this level

  • Only changes text display, with no network and no data writes
All reasons and checks

abullard1/claude-bionify

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add plugins/claude-bionify

Detects the agents on your machine, checks the risk and pins the version.

Other ways to install

Run one by one in the Claude Code chat

/plugin marketplace add abullard1/claude-bionify
/plugin install claude-bionify@claude-bionify

Checked against the repository on Sep 25, 2026, commit 2e504db.

Text for your agent

In Claude Code run /plugin marketplace add abullard1/claude-bionify and /plugin install claude-bionify@claude-bionify. Control it with /claude-bionify:on and /claude-bionify:off.

Other ways from the author
/plugin marketplace add abullard1/claude-bionify
/plugin install claude-bionify@claude-bionify

Active right after install. Settings are offered when enabled.

This is third-party code. Review the repository files before installing.

What it does

The plugin bolds the leading part of each word in Claude Code's streamed replies, giving the eye a fixation point per word. This is the bionic reading technique, grounded in eye-movement research. Only the on-screen look changes: the transcript and what Claude itself reads keep the original unbolded text, which you can reopen any time. It has three boundary modes, plus settings for fixation strength, minimum word length and skipping acronyms, links, paths and headings. It runs with no dependencies and no network, and falls back to the original text on any error.

Who it is for. For anyone who reads long answers more easily this way: people with ADHD and dyslexia, and anyone who wants a calmer read.

Good fit when

  • Long Claude Code answers are hard to read and you want a fixation point per word
  • You want a more accessible text presentation without changing the content itself
  • You want to tune the strength and boundary of the bolding for yourself

Not a fit when

  • Bolding word starts hinders rather than helps your reading
  • Your terminal or theme does not render bold

Example request

Turn on bionic reading and make the bolding lighter

Limitations

It changes only the display in Claude Code, and the transcript stays original. It needs bold rendering support in the terminal. It works as a Claude Code plugin, with no other hosts claimed in the README.

How to disable. Turn it off temporarily with /claude-bionify:off or uninstall the plugin via /plugin.

Security check

  • Only changes text display, with no network and no data writes

README in short

The README describes claude-bionify as a Claude Code plugin that bolds the start of each word in streamed replies, giving the eye a fixation point. Only the on-screen look changes, and the original text stays in the transcript and is available through the history view. It has three boundary modes, settings for fixation strength and minimum word length, and it leaves code, links, paths and acronyms intact. Install is two lines through the plugin marketplace, with on and off commands. The plugin has no dependencies, no network and no telemetry, and falls back to the original text on error.

FAQ

Does it change what is saved in history?

No. The bolding is on screen only; the transcript and what Claude reads keep the original unbolded text.

Does it need network access?

No. The plugin has no dependencies and no network, and runs entirely on your machine.

Official

A self-hosted knowledge base with block-level references and a built-in MCP server for connecting AI agents to your notes

MCP serverMedium risk46.5KRepository stars
Editors’ pick

A CLI for every Google Workspace API with JSON output and agent skills: Drive, Gmail, Calendar, Sheets and more

CLIHigh risk31.2KRepository stars
Editors’ pick

Local search over Markdown notes, docs and meeting transcripts: keywords, semantic search and reranking, with an MCP server

CLIMedium riskNo VPN needed30.1KRepository stars
Editors’ pick

A task manager for AI-driven development: breaks a PRD into dependent tasks and guides the agent through them via MCP or CLI

MCP serverMedium risk28.1KRepository stars
Foxx AIclaude-bionify

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.