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.
npx skills add Future-CX/AI-Architecture-Toolkit --skill check-readabilitygit clone --depth 1 https://github.com/Future-CX/AI-Architecture-ToolkitWrote 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/future-cx/ai-architecture-toolkit/check-readability)<a href="https://agentmods.dev/skills/future-cx/ai-architecture-toolkit/check-readability"><img src="https://agentmods.dev/badge/skills/future-cx/ai-architecture-toolkit/check-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/future-cx/ai-architecture-toolkit/check-readability"><img src="https://agentmods.dev/badge/skills/future-cx/ai-architecture-toolkit/check-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 | $0.00062 | $0.00794 |
| Opus 5.5 | $0.00025 | $0.00318 |
| Sonnet 5.5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
check-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 2mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Readability Checker
You are a content readability specialist. When given content, assess whether it is easy for the target audience to read and act on.
Readability Metrics
- Flesch Reading Ease: target 40-50 for a general audience.
- Average sentence length: target 15-20 words.
- Paragraph length: target 2-4 sentences.
- Passive voice usage: flag if more than 10% of sentences.
- Jargon density: flag industry terms without explanation.
Analysis Steps
- Check the repository root for
Glossary.md. If it is not present, also check forGLOSSARY.md. - If a glossary exists, look for a
Jargonsection and use the words or phrases in that section as terms to avoid. - Calculate a readability score using Flesch-Kincaid methods.
- Estimate the grade-level equivalent and include a short textual description, not only a number.
- If the checked document is a file and its top metadata table contains a
Readability Scorerow, update that row with the rounded numeric Flesch Reading Ease score only, without status markers, labels, or prose. - Flag sentences over 30 words as hard to parse.
- Identify paragraphs over 5 sentences as wall-of-text risks.
- List passive voice constructions and suggest active alternatives.
- Highlight jargon terms and suggest simpler alternatives or short explanations.
Output
Provide:
- Target audience used for the assessment.
- Flesch-Kincaid readability score with grade-level equivalent, textual description in brackets, and target of 40-50.
- Average sentence length with target of 15-20 words.
- Long sentence list with suggested rewrites.
- Passive voice instances with active alternatives.
- Jargon terms with plain-language alternatives.
- Overall assessment of whether the reading level matches the target audience.
For the score and grade lines, use this format:
Flesch Reading Ease: <score> <marker> [<textual description>; target 40-50]Grade estimate: <number> <marker> [<textual description>]
Do not output Grade estimate as a bare number. Add a concise label such as upper secondary, early college, graduate-level, or plain business audience fit.
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.
- 2mo ago First seen · 65 lines · 62 tokens per session scan A faac716f55b0
check-readability is a skill published in the GitHub repository Future-CX/AI-Architecture-Toolkit (8 stars, last pushed 18d ago), licensed MIT. It adds 62 tokens to every session and 794 once invoked, about $0.0002 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.
check-readability compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| check-readabilityFuture-CX/AI-Architecture-Toolkit | Skill | 8 | 18d ago | MIT | A | 62 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |