diff --git a/AGENTS.md b/AGENTS.md
index d41d3cb..cfcd638 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -130,10 +130,10 @@ One-line commit messages and PR titles; short PR summaries. No AI-attribution ma
 
 ## 7. The working loop
 
-A session works one chunk, starting from the first item in `todo.md` whose "Lands after item N"
-items have all landed, and stops when that chunk merges, whatever it was asked to finish: a release
-is a chain of sessions, so an instruction to work until a release is done names the chain, not the
-session. An open PR is a chunk already in flight, and finishing it is the session.
+A session works one chunk, starting from the first item in `todo.md` whose "Lands after" item has
+landed, and stops when that chunk merges, whatever it was asked to finish: a release is a chain of
+sessions, so an instruction to work until a release is done names the chain, not the session. An
+open PR is a chunk already in flight, and finishing it is the session.
 Per chunk:
 
 1. Fresh worktree off updated `origin/main`; implement tests-first (§3).
diff --git a/todo.md b/todo.md
index 6a15522..ebc59d2 100644
--- a/todo.md
+++ b/todo.md
@@ -44,8 +44,6 @@
 
 ### 40. Make `markdownToAdf(adfToMarkdown(doc))` deep-equal `doc` for every document `adfToMarkdown` takes.
 
-takes.
-
 Today it holds for editor-normal documents only: two adjacent text nodes with the same marks merge,
 an empty `attrs`, `marks` or `content` drops, and `-0` reads back `0` — shapes pipelines and bots
 build. Spell each so it reads back as written; CommonMark's spelling stays wherever the document