fix: correct token calculation in context-usage hook example

The hook was converting total_chars to string before calculating tokens,
resulting in ~0 tokens reported. Fixed to calculate directly from char count.

- Remove unused estimate_tokens() function
- Calculate tokens as total_chars // 4 directly
- Archive fix-context-usage-hook change

openspec/changes/archive/2025-12-24-fix-context-usage-hook/tasks.md

@@ -0,0 +1,20 @@
+# Tasks: Fix Context Usage Hook Token Calculation
+
+## Implementation Tasks
+
+### 1. Fix the bug in 06-hooks/README.md example
+- [x] Update line 564 in the context-usage.py example: change `estimate_tokens(str(total_chars))` to `total_chars // 4`
+- [x] Remove the now-unused `estimate_tokens()` function from the example
+
+### 2. Update user's local hook file
+- [x] Fix `~/.claude/hooks/context-usage.py` with the same correction
+
+### 3. Verification
+- [x] Test the hook by running Claude Code and confirming non-zero token count is displayed
+- [x] Verify the percentage calculation is reasonable (should show usage increasing during conversation)
+
+## Acceptance Criteria
+
+- [x] After Claude responds, the Stop hook displays a non-zero token estimate
+- [x] The displayed percentage decreases as conversation grows
+- [x] Example in README.md matches the corrected implementation

openspec/changes/fix-context-usage-hook/tasks.md

@@ -1,20 +0,0 @@
-# Tasks: Fix Context Usage Hook Token Calculation
-
-## Implementation Tasks
-
-### 1. Fix the bug in 06-hooks/README.md example
-- [ ] Update line 564 in the context-usage.py example: change `estimate_tokens(str(total_chars))` to `total_chars // 4`
-- [ ] Remove the now-unused `estimate_tokens()` function from the example
-
-### 2. Update user's local hook file
-- [ ] Fix `~/.claude/hooks/context-usage.py` with the same correction
-
-### 3. Verification
-- [ ] Test the hook by running Claude Code and confirming non-zero token count is displayed
-- [ ] Verify the percentage calculation is reasonable (should show usage increasing during conversation)
-
-## Acceptance Criteria
-
-- [ ] After Claude responds, the Stop hook displays a non-zero token estimate
-- [ ] The displayed percentage decreases as conversation grows
-- [ ] Example in README.md matches the corrected implementation