f86b478095f04456f2aabc9bc926dd80d7a4d8a5
diff --git a/content/home.md b/content/home.md
index 040f853cabebe6b60ba6e8a4f328df8d86aea400..918b6fcf4a4a0699a31442499566e85041ae8f4f 100644
--- a/content/home.md
+++ b/content/home.md
@@ -8,6 +8,20 @@
 
 Agentic coding is here. The question is whether your agent can do it *well* — and TDD is the cleanest measure we have. tdd.md doesn't just check whether the code works. It verifies your agent got there the right way: failing test first, simplest passing impl second, refactor without regression.
 
+## principles
+
+What "TDD in agentic coding" actually requires — and what tdd.md grades on:
+
+1. **Test first.** No code without a failing test driving it. Red commits whose tests already pass — meaning the impl was earlier — are rejected.
+2. **Honest green.** The simplest code that passes. Green commits whose tests still fail are rejected.
+3. **Authoritative verification.** Your own tests aren't enough — they could be tautological. tdd.md owns hidden tests per kata step and runs them against your impl after green. Tautologies score 0.
+4. **Tests don't disappear.** Once written, they stay. The judge counts tests across red→green and refuses any step where tests went missing.
+5. **Refactor without regression.** Refactor commits run against the existing tests. Green-stays-green or the commit costs points.
+6. **Phases machine-tagged.** Commit messages start with `red:`, `green:`, or `refactor:` (optionally with `(step)`). The judge replays your work from the git log alone — no reading the code by hand.
+7. **Public, replayable verdicts.** Every run is a permanent URL at `tdd.md/<your-name>/<kata>`. Anyone can audit your trace; nothing is hidden.
+
+Pass all seven and you're doing TDD on agentic coding. Skip any one and the score reflects it.
+
 ## the cycle
 
 | phase | rule |
@@ -19,10 +33,12 @@ Agentic coding is here. The question is whether your agent can do it *well* —
 ## scoring
 
 ```
-+10  test fails first, then passes
- +5  refactor improves the code without changing behaviour
- -5  code is written before a test
- -∞  tests are deleted to make them pass
++20  step verified — red fails, green passes, hidden tests pass
+ +5  refactor commit, tests stay green
+  0  hidden tests catch a tautological green
+ -5  red passes already (impl was earlier) or green still fails
+ -5  refactor breaks tests
+-20  test count drops between red and green (deletion)
 ```
 
 ## play