Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add alesdrobysh/readability-claude/plugin install readabilityWrote 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.
[](https://agentmods.dev/skills/alesdrobysh/readability-claude/readability)<a href="https://agentmods.dev/skills/alesdrobysh/readability-claude/readability"><img src="https://agentmods.dev/badge/skills/alesdrobysh/readability-claude/readability/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.
<a href="https://agentmods.dev/skills/alesdrobysh/readability-claude/readability"><img src="https://agentmods.dev/badge/skills/alesdrobysh/readability-claude/readability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.00714 |
| Opus 5.5 | $0.00030 | $0.00286 |
| Sonnet 5.5 | $0.00015 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
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 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.
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;nullfor 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
- Get the draft from the user or the file they named.
- Score it with the requested threshold, or 60 by default.
- 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.
- Rewrite without dropping facts, examples, caveats, or the author's voice.
- Re-score. Stop when it clears the threshold or further simplification would damage the content.
- 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.
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.
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.
- 1mo ago First seen · 83 lines · 74 tokens per session scan A 262d9e4bbbfe
readability is a skill published in the GitHub repository alesdrobysh/readability-claude (1 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 714 once invoked, about $0.0003 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.
Other skills, from other repositories
software-code-review
Evaluate source code for correctness, quality, security, style conformance, and maintainability, producing a structured review report with findings and recommendations. Use when the user wants to review, critique, audit, evaluate, or inspect source code — checking for bugs, logic errors, unhandled error paths…
code-simplifier
Simplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.
template-prose-project
Prose-review pipeline exemplar — readability gates, structural checking, BibTeX validation, and quality review workflows.
clarity-and-concision
Teaches techniques for achieving relentless clarity and ruthless concision in business writing, including the 20-word sentence rule, concrete detail over abstraction, word economy tactics, and the reader's perspective test. Features extensive before/after examples demonstrating how bloated corporate prose can be cut…
plain-language-and-flow
Teaches how to eliminate corporate jargon (bizspeak), use chronological ordering for factual accounts, and create smooth document flow through transitional words, signposting, and paragraph continuity. Features a bizspeak blacklist, before/after translations of corporate prose, and a taxonomy of transitional phrases.…
web-section-splitter
Breaks a long-form article into web-optimized sections with subheadings, pull-quote suggestions, image placement markers, and reading-time estimates — ready for a web editor to drop into a CMS.