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.
Image: Open Doors: Art in Action
HomeAbout
Mental Health: Colors of Wellbeing
Love Our Neighbor: Peace and Reconciliation
Art for Social Justice: Voices Unheard
BORDERTOWN: Teachings of Dook'o'oosliid
Quilts of Change
Art of Pride: Understanding Identities
Ending Gun Violence: Healing Our Souls
The rest of the page is in full screen.
Scroll ***OPEN DOORS: ART IN ACTION*** *exhibits work by local artists and musicians while partnering with area non-profits to raise awareness of social, environmental and justice issues in our community and around the world* # **A project of Church of the Epiphany** > “By engaging with important social, environmental, and cultural issues, supporting local artists, and collaborating with local nonprofits, “Open Doors: Art in Action” has made – and will continue to make – an extraordinary impact on our community.” — Viola Awards committee --- > “Clearly, these art exhibitions have promoted focused respectful dialogue, networking, and problem solving, not a small feat in these polarized times.” — Kathi Baron, M.A. Artist and Educator
Thin: Too few words of their own are in the HTML for a page of their kind. Render the rest on the server.
The figures
20 pages, set against the 167,893 sites with figures.
- Readablehigher is better
- 95%19 of 20 pages
- All 167,893 sitesBetter than 35%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 51%middle page
- All 167,893 sitesBetter than 28%
Of the words before script, the share that are the page and not menus, footer and forms.
- Costshown, never scored
- 14,867tokens
- About 743 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.
How its pages spread on Clean
20 pages measured.
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 |
| opendoorsartinaction.comThis site, 20 pages | 95% | 51% | 743 |
| chasedaniel.com96 pages | 85% | 87% | 1,011 |
| allmyrelationsarts.org100 pages | 99% | 61% | 1,062 |
| elpalacio.org100 pages | 100% | 93% | 4,321 |
Third of 4 on Readable, fourth on Clean.
AI crawler access
What robots.txt says to each, as read on October 24, 2026. 8 of 8 may read the site.
| Crawler | robots.txt says | Used for | The line that decides |
|---|---|---|---|
| GPTBotOpenAI | Allowed | Training models | User-agent: GPTBot / Disallow: /config |
| 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 | Allowed | Training models | User-agent: ClaudeBot / Disallow: /config |
| Claude-SearchBotAnthropic | Not named | Claude’s search | Falls to User-agent: * |
| PerplexityBotPerplexity | Not named | Perplexity search | Falls to User-agent: * |
| Google-ExtendedGoogle | Allowed | Training Gemini | User-agent: Google-Extended / Disallow: /config |
| 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.
11 pages of 20 lose something. Pick a loss to see what to do about it.Open the action plan
| What an agent getshigher is better | Signals | Costnot scored | ||||
|---|---|---|---|---|---|---|
| Page | Words | Clean | Readable | Main heading | Tokens | What it loses |
| / | 106 | 32% | No | Yes | 187 | Thin |
| /new-page-28 | 48 | 14% | Yes | None | 77 | No h1 |
| /new-page-2 | 126 | 35% | Yes | None | 273 | No h1 |
| /summary | 133 | 37% | Yes | None | 230 | No h1 |
| /monica-wapaha | 215 | 48% | Yes | None | 480 | No h1 |
| /new-page-1 | 237 | 50% | Yes | None | 473 | No h1 |
| /covid-19-hs-photography | 244 | 51% | Yes | None | 391 | No h1 |
| /avis-charley | 279 | 55% | Yes | None | 633 | No h1 |
| /lynnette-haozous | 399 | 63% | Yes | None | 752 | No h1 |
| /amy-martin-gallery | 528 | 69% | Yes | None | 677 | No h1 |
| /michael-collier-gallery | 567 | 71% | Yes | None | 779 | No h1 |
| /home-nueva | 106 | 32% | Yes | Yes | 187 | Nothing |
| /contact-1 | 113 | 33% | Yes | Yes | 180 | Nothing |
| /mental-health | 188 | 44% | Yes | Yes | 411 | Nothing |
| /matthew-bollinger | 324 | 58% | Yes | Yes | 590 | Nothing |
| /matriarchy | 680 | 75% | Yes | Yes | 1,223 | Nothing |
| /use-misuse-and-restoration-on-the-colorado-plateau | 731 | 76% | Yes | Yes | 1,259 | Nothing |
| /open-lens | 811 | 77% | Yes | Yes | 1,463 | Nothing |
| /venaya-yazzie | 1,379 | 86% | Yes | Yes | 2,133 | Nothing |
| /tacey-m-atsitty | 1,667 | 87% | Yes | Yes | 2,469 | Nothing |
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/opendoorsartinaction.com"><img src="https://mttr.si/agent-view/opendoorsartinaction.com/badge.svg" alt="Agent View: 95% readable, 51% clean" height="20"></a>
The figures in one line
opendoorsartinaction.com in Agent View: 95% of pages readable, better than 35% of sites; 51% clean; 14,867 tokens to read all 20 pages. mttr.si/agent-view/opendoorsartinaction.com
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
- Give 10 pages a main headingClearer
- Render the rest of 1 page on the serverReadable
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 24, 2026, not a screenshot, and only from the 20 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.