Agent View
The site as an AI agent gets it, beside the site as a person sees it. What it can read, what it has to cut away, and what it never sees.
Popular Searches
Image: NAV Logo
Districtwide SolutionElementaryMiddle SchoolHigh SchoolDigital Well-Being UnitEarly Learning (PreK)Elementary Classroom Kits (K–5)Out-of-School Time (K–5)
Image: icon facebook
Image: icon instagram
Image: icon youtube
Image: CFC Lockup
Privacy Policy
The rest of the page is in full screen.
Popular Searches [](https://www.secondstep.org/) [](https://www.secondstep.org/resource/5-common-myths-about-empathy#)[](https://www.secondstep.org/resource/5-common-myths-about-empathy#)[](https://www.secondstep.org/resource/5-common-myths-about-empathy#) [](https://www.secondstep.org/resource/5-common-myths-about-empathy#) [Privacy Policy](https://www.secondstep.org/resource/5-common-myths-about-empathy#) [Cookie Preferences](https://www.secondstep.org/resource/5-common-myths-about-empathy#) [Terms of Use](https://www.secondstep.org/resource/5-common-myths-about-empathy#) [License Agreements](https://www.secondstep.org/resource/5-common-myths-about-empathy#) [Copyright Permissions](https://www.secondstep.org/resource/5-common-myths-about-empathy#) [Site Map](https://www.secondstep.org/resource/5-common-myths-about-empathy#) © 2012–2026 Committee for Children Second Step is a registered trademark of Committee for Children
Thin: Too few words of their own are in the HTML for a page of their kind. Render the rest on the server. No <main>: Wrap the page’s own content in <main>, so a reader knows where it starts and stops, and Clean can be measured. No h1: Give each one h1 that says what the page is.
The figures
99 pages, set against the 167,893 sites with figures and 127 in education. Change is since the read on October 23, 2026.
- Readablehigher is better
- 74%73 of 99 pages
- Down 7 points from 81%
- All 167,893 sitesBetter than 22%127 education sitesBetter than 10%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 84%middle page
- Up 2 points from 82%
- All 167,893 sitesBetter than 72%127 education sitesBetter than 80%
Of the words before script, the share that are the page and not menus, footer and forms. 58 pages are not measured, with no <main> or no words.
- Costshown, never scored
- 174,806tokens
- About 1,766 a page
To read every page once. A long page that answers well is not worse for it. Tokens are estimated at about 4 characters each.
Readable and Clean over 2 reads
Readable from 81% to 74% and Clean from 82% to 84%, between October 23, 2026 and October 25, 2026.
How its pages spread on Clean
41 pages measured. Not measured: 58 with no <main> or no words.
Against its rivals
The sites nearest it by what they do, with figures. Close means similar work, not better.
| Readinghigher is better | Costnot scored | ||
|---|---|---|---|
| Site | Readable | Clean | Tokens a page |
| secondstep.orgThis site, 99 pages | 74% | 84% | 1,766 |
| alongside.care100 pages | 98% | None | 1,251 |
| classroommagazines.scholastic.com99 pages | 100% | 58% | 870 |
| us.corwin.com100 pages | 99% | 80% | 1,829 |
Fourth of 4 on Readable, first on Clean.
AI crawler access
What robots.txt says to each, as read on October 25, 2026. 8 of 8 may read the site.
| Crawler | robots.txt says | Used for | The line that decides |
|---|---|---|---|
| GPTBotOpenAI | Not named | Training models | Falls to User-agent: * |
| OAI-SearchBotOpenAI | Not named | ChatGPT search | Falls to User-agent: * |
| ChatGPT-UserOpenAI | Not named | A page a person asks about | Falls to User-agent: * |
| ClaudeBotAnthropic | Not named | Training models | Falls to User-agent: * |
| Claude-SearchBotAnthropic | Not named | Claude’s search | Falls to User-agent: * |
| PerplexityBotPerplexity | Not named | Perplexity search | Falls to User-agent: * |
| Google-ExtendedGoogle | Not named | Training Gemini | Falls to User-agent: * |
| bingbotMicrosoft | Not named | Bing and Copilot | Falls to User-agent: * |
Every AI crawler mttr checks may read it. Not named means the rules for every crawler apply.
Every page
Worst first. Each opens in Agent View at the top.
58 pages of 99 lose something. Pick a loss to see what to do about it.Open the action plan
Show where it stands
A card, a badge and a line, each with the figures.
A badge for the site
<a href="https://mttr.si/agent-view/secondstep.org"><img src="https://mttr.si/agent-view/secondstep.org/badge.svg" alt="Agent View: 74% readable, 84% clean" height="20"></a>
The figures in one line
secondstep.org in Agent View: 74% of pages readable, better than 10% of education sites; 84% clean; 174,806 tokens to read all 99 pages. mttr.si/agent-view/secondstep.org
What to do next
Fix the pages, let an agent do it, and read the site again to see the figures move.
Fix what agents miss
- Wrap 58 pages in <main>Clean measured
- Render the rest of 26 pages on the serverReadable
- Give 24 pages a main headingClearer
Connect your agent
Claude Code, Codex or Cursor reads the site’s fixes over MCP, fixes a page in your code, has mttr read it again, and checks the fix landed.
https://mttr.si/mcpSet up an agent
Claim the site
Prove it is yours with a DNS record or a file. Your agent can then reach its reads and jobs, and set each change to wait for your approval.
Claim the siteDrawn from the HTML mttr fetched on its read of October 25, 2026, not a screenshot, and only from the 99 pages read, where the read stopped at its page limit. An assistant’s own reader may differ. Tokens are estimated at about 4 characters each. A site an agent reads well is not a site an assistant cites.