Agent Reading Test
1. Truncation
150K-char page with canary tokens at 10K, 40K, 75K, 100K, and 130K. Maps exactly where your agent's truncation limit kicks in.
page-size-html, page-size-markdown2. Boilerplate Burial
80K of inline CSS before the real content. Tests whether agents distinguish CSS noise from documentation.
content-start-position3. SPA Shell
Client-side rendered page. Content only appears after JavaScript executes. Most agents see an empty shell.
rendering-strategy4. Tabbed Content
8 language variants in tabs. Canary tokens in tabs 1, 4, and 8. Tests how far into serialized tab content the agent reads.
tabbed-content-serialization5. Soft 404
Returns HTTP 200 with a "page not found" message. Tests whether the agent recognizes it as an error page.
http-status-codes6. Broken Code Fence
Markdown with an unclosed code fence. Everything after it becomes "code." Tests markdown parsing awareness.
markdown-code-fence-validity7. Content Negotiation
Different canary tokens in HTML vs. markdown versions. Tests whether your agent requests the better format.
content-negotiation8. Cross-Host Redirect
301 redirect to a different hostname. Most agents won't follow it (security measure). The canary is on the other side.
redirect-behavior9. Header Quality
Three cloud platforms, identical "Step 1/2/3" headers. Tests whether agents can determine which section is which.
section-header-quality10. Content Start
Real content buried after 50% navigation chrome. Tests whether agents read past the sidebar serialization.
content-start-position