Move the to-do list from NOTES.md to a kandown board

Each note is a task in tasks/ with the owner's words under ## Context; the
board rules are in .kandown/kandown_work.md and docs/kandown.md explains how
kandown works here.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

AGENTS.md

@@ -11,7 +11,8 @@ The owner (the user) directs the work and is the real playtester. You build, tes
 
 ## Start of every session
 
-1. Read `NOTES.md`. It is the user's to-do inbox (see "Working from NOTES.md" below).
+1. Run `kandown work`. It prints the user's task board and the rules for working it (see
+   "Working from the task board" below).
 2. Read `docs/PROJECT_MAP.md` before searching the code. It says where everything lives. Its
    index lists every top-level function and variable by file.
 3. Before changing how the game plays, read the relevant part of `docs/DESIGN.md`. Many choices
@@ -39,24 +40,21 @@ These rules matter more than speed.
   ask first. If the choice is small or easy to undo, take the sensible reading, say which one you
   took, and carry on.
 
-## Working from NOTES.md
+## Working from the task board
 
-`NOTES.md` belongs to the user. They add notes at any time and ask you to work on them ("do the
-notes", "do the belt note"). Work on notes only when asked.
+The user's to-do list is a kandown board: one Markdown file per task in `tasks/`. **Read
+`docs/kandown.md` before using it**: it says how the board works here, which commands are safe
+(never run `kandown <command> --help`: it runs the command), and what a task file looks like.
+The rules for working the board are in `.kandown/kandown_work.md`, and `kandown work` prints
+them. In short:
 
-- **Kinds of note.**
-  - Tasks ("add...", "make...", "fix...") are built.
-  - Discussion notes ("let's think about...", "brainstorm...", "what can we do about...",
-    "let's talk about...") get options with trade-offs and a recommendation. Do not build them
-    until the user decides.
-  - Questions get answers.
-- **Keep the user's wording.** Never rewrite or tidy a note. If you need to add context, add a
-  sub-bullet that starts with `(agent)`.
-- **When a task is finished**, move the note, word for word, into the "Done, please check"
-  section at the bottom. Under it, add an `(agent)` sub-bullet saying what changed and how to
-  check it in the game. Do not delete it: the user deletes it after checking. If the user says
-  it is not fixed, move it back up and add their feedback as a sub-bullet.
-- **Log your work.** Add an entry at the top of `docs/agent-log.md` with the date, the note,
+- Work on tasks only when asked. Todo tasks are built; Backlog tasks tagged `discussion` get
+  options with trade-offs and a recommendation, and nothing is built until the user decides.
+- Never reword the user's words in a task's `## Context`. Add your notes as subtasks with
+  `report:` lines, or in the `report` field.
+- When a task is finished, move it to **Review** with a `report` saying what changed and how to
+  check it in the game. Only the user moves tasks to Done.
+- **Log your work.** Add an entry at the top of `docs/agent-log.md` with the date, the task,
   what changed, the files touched, the tests run, and anything left open.
 - **Record decisions.** When the user decides something about the design, add it to the
   decisions list in `docs/DESIGN.md` with the date and the reason they gave.
@@ -178,3 +176,5 @@ screenshots and the pitfalls. The essentials:
 - Never commit secrets: tokens, passwords, or keys.
 - Work happens one agent at a time. If running several agents side by side is set up later,
   this section will say how they coordinate.
+
+This project uses Kandown. Before task work, run `kandown work` and follow its output. <!-- kandown:agent-ref -->