diff --git a/AGENTS.md b/AGENTS.md
index edb8e9e..7556fda 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -5,10 +5,10 @@
 ### Running Tests
 ```bash
 basex -t /path/to/test/file.xqm    # Run all tests in a file
-basex -t /path/to/test/dir         # Run all tests in directory
-basex -t test/simple.xqm           # Run doci unit tests (6 tests)
+basex -t test/simple.xqm           # Run unit tests (7 tests)
 basex -t test/smoke.xq             # Run smoke tests (no assertions)
 ```
+**Running Single Tests**: BaseX runs all tests in a file. To run a single test, comment out others or use `%unit:test` selectively. Test names: `test:from-file`, `test:from-string1`, `test:from-string2`, `test:update-start`, `test:update-end`, `test:update-lines`, `test:lines`.
 
 ### Query Execution
 ```bash
@@ -38,12 +38,9 @@ basex  # Start interactive BaseX shell
 - Use hyphens for multi-word names (e.g., `pdfbox.xqm`)
 - Resource files: lowercase with hyphens (e.g., `test-data.txt`)
 
-### Namespace Declarations
 ```xquery
-module namespace module-name = 'urn:project:namespace';
+module namespace doci = 'urn:quodatum:text:doci';
 ```
-- Use reverse domain name notation for consistency
-- Match namespace URI to file path structure
 
 ### Records & Types
 - Use `declare record` for structured data
@@ -87,9 +84,10 @@ import module namespace mod = 'namespace' at "path/to/file.xqm";
 - Prefer `let` over `for` for single items
 - Use `if-then-else` expressions
 - Leverage XQuery 3.1+ functions: `tokenize()`, `string-join()`
-- Use `!` for mapping single items
+- Use `!` for mapping single items (e.g., `$lines!doci:build(.)`)
 - Use `*` for mapping sequences: `expr!func()`
 - Prefer `switch() case when` over nested `if-then-else`
+- Use `trace()` for debugging: `=>trace("$var")` or `=>trace("label")`
 
 ### Error Handling
 ```xquery
@@ -125,7 +123,7 @@ declare function foo($param as xs:string) as xs:integer { ... }
 
 ### Record Field Access
 - Use `?field` syntax for record field access (e.g., `$doci?lines`)
-- Optional fields marked with `?` after field name in record declaration
+- Optional fields marked with `?` after field name in record declaration in declaration, but `?field` syntax for access
 
 ### Documentation
 ```xquery
@@ -211,6 +209,8 @@ docs: update module documentation
 ## Notes
 
 - BaseX 12.2 supports XQuery 3.1 syntax
-- The `fn:do-until` function may not be available; use `hof:until` as alternative
+- Use `hof:until` instead of `fn:do-until` if available
 - Java interoperability available through `Q{namespace}` syntax (e.g., `Q{java:java.io.File}new()`)
 - For PDF processing (`pdfbox` module), external JAR dependencies required
+- The `doci:separator()` function auto-detects line separators (`\n`, `\r\n`, `\r`)
+- Use `=>trace()` liberally during debugging to inspect intermediate values