readability

readability is a skill for Claude Code, Codex from alesdrobysh/readability-claude. It costs 74 tokens per session (714 once invoked), scanned A, original, MIT.

A checker for how easy substantial English writing is to read. It reports reading ease, word variety, and related text measures.

In plain words
What is it for?
Use it to check and simplify documentation, pull-request descriptions, commit messages, blog posts, and explanations.
Why use it?
It helps reveal when documentation, explanations, or other long prose may be harder to read than intended.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the readability plugin — 1 skill shipped together

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 skills/alesdrobysh/readability-claude/readability
Any agent
npx skills add alesdrobysh/readability-claude --skill readability
Clone the repo
git clone --depth 1 https://github.com/alesdrobysh/readability-claude

Made for: Claude Code, Codex.

Or install readability, the plugin that ships this one along with the rest of its 1 skill.

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 readability

README.md
[![agentmods](https://agentmods.dev/badge/skills/alesdrobysh/readability-claude/readability.svg)](https://agentmods.dev/skills/alesdrobysh/readability-claude/readability)
Your own site
<a href="https://agentmods.dev/skills/alesdrobysh/readability-claude/readability"><img src="https://agentmods.dev/badge/skills/alesdrobysh/readability-claude/readability.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 714 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 $0.00074 $0.00714
Opus 5 $0.00037 $0.00357
Sonnet 5 $0.00015 $0.00143
Haiku 4.5 $0.00007 $0.00071

Measured 4d ago against content hash 262d9e4bbbfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

readability 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/analyzer.js, scripts/check.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugin/skills/readability/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Readability

Check substantial English prose with the pure-JavaScript analyzer bundled in this plugin. It makes no network requests and has no runtime dependencies.

Do not run it on code, command output, log dumps, non-English text, or short replies. The scores are not meaningful for those inputs.

Run the analyzer

The script is at ${CLAUDE_PLUGIN_ROOT}/skills/readability/scripts/check.js. It reads stdin, prints JSON, and exits 1 when the Reading Ease score misses --threshold:

echo "<DRAFT>" | node "${CLAUDE_PLUGIN_ROOT}/skills/readability/scripts/check.js" --threshold 60

For a file:

node "${CLAUDE_PLUGIN_ROOT}/skills/readability/scripts/check.js" --threshold 60 < draft.md

For long drafts, use a file or stdin. Do not put long prose in a shell-quoted --text argument.

Output

{
  "word_count": 174,
  "sentence_count": 12,
  "paragraph_count": 4,
  "avg_sentence_length": 14.5,
  "avg_word_length": 4.8,
  "ttr": 0.61,
  "mtld": 74.2,
  "flesch_reading_ease": 64.3,
  "complexity_label": "Moderate"
}
  • flesch_reading_ease: 0-100; higher is easier. 70+ is simple, 50-69 moderate, and below 50 complex.
  • mtld: lexical diversity; null for fewer than 50 words.
  • ttr: unique tokens divided by all tokens.
  • avg_sentence_length: the main signal to inspect when a draft scores low.

Workflow

  1. Get the draft from the user or the file they named.
  2. Score it with the requested threshold, or 60 by default.
  3. If it misses:
    • Above 25 words per sentence: split long sentences.
    • Above 6 characters per word: prefer plainer words where meaning permits.
    • Below 30 Reading Ease: also remove nested clauses and needless passive voice.
  4. Rewrite without dropping facts, examples, caveats, or the author's voice.
  5. Re-score. Stop when it clears the threshold or further simplification would damage the content.
  6. Show the rewritten draft and the before/after Reading Ease scores.

Guardrails

Flesch Reading Ease measures sentence and word shape, not truth, style, or quality. Never game the number at the cost of meaning. A score of 100 is not a claim that the prose is good.

Read the full file on GitHub · 83 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 83 lines · 74 tokens per session scan A 262d9e4bbbfe

Subscribe to this mod's changes

readability is a skill published in the GitHub repository alesdrobysh/readability-claude (1 stars, last pushed 29d ago), licensed MIT. It adds 74 tokens to every session and 714 once invoked, about $0.0004 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.