🔧 chore: improve skills cross-references and CLAUDE.md guidance

- Add --amend option with safety rules to commit command
- Add logging skill cross-references to angular-template and html-template
- Fix logging skill name from logging-helper to logging
- Add extended thinking triggers, context monitoring, and code investigation
  rules to CLAUDE.md

.claude/commands/commit.md

@@ -174,6 +174,42 @@ Example of splitting commits:
 ## Command Options
 
 - `--no-verify`: Skip running the pre-commit checks (lint, build, generate:docs)
+- `--amend`: Amend the previous commit (RESTRICTED - see rules below)
+
+## Amend Rules (CRITICAL)
+
+**ONLY use `--amend` in these specific cases:**
+
+1. **Adding pre-commit hook fixes**: If a pre-commit hook modified files (formatting, linting auto-fixes), you may amend to include those changes.
+
+2. **Before amending, ALWAYS verify:**
+   ```bash
+   # Check authorship - NEVER amend another developer's commit
+   git log -1 --format='%an %ae'
+
+   # Check not pushed - NEVER amend pushed commits
+   git status  # Should show "Your branch is ahead of..."
+   ```
+
+3. **If either check fails:**
+   - Create a NEW commit instead
+   - Never amend commits authored by others
+   - Never amend commits already pushed to remote
+
+**Example workflow for pre-commit hook changes:**
+```bash
+# 1. Initial commit triggers pre-commit hook
+git commit -m "feat(scope): add feature"
+# Hook modifies files...
+
+# 2. Verify safe to amend
+git log -1 --format='%an %ae'  # Your name/email
+git status                      # "Your branch is ahead..."
+
+# 3. Stage hook changes and amend
+git add .
+git commit --amend --no-edit
+```
 
 ## Important Notes
 

.claude/skills/angular-template/SKILL.md

@@ -18,6 +18,7 @@ Guide for modern Angular 20+ template patterns: control flow, lazy loading, proj
 **Related Skills:** These skills work together when writing Angular templates:
 - **[html-template](../html-template/SKILL.md)** - E2E testing attributes (`data-what`, `data-which`) and ARIA accessibility
 - **[tailwind](../tailwind/SKILL.md)** - ISA design system styling (colors, typography, spacing, layout)
+- **[logging](../logging/SKILL.md)** - MANDATORY logging in all Angular files using `@isa/core/logging`
 
 ## Control Flow (Angular 17+)
 

.claude/skills/html-template/SKILL.md

@@ -19,6 +19,7 @@ Use this skill when:
 **Works seamlessly with:**
 - **[angular-template](../angular-template/SKILL.md)** - Angular template syntax, control flow, and modern patterns
 - **[tailwind](../tailwind/SKILL.md)** - ISA design system styling for visual design
+- **[logging](../logging/SKILL.md)** - MANDATORY logging in all Angular components using `@isa/core/logging`
 
 ## Overview
 

.claude/skills/logging/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: logging-helper
+name: logging
 description: This skill should be used when working with Angular components, directives, services, pipes, guards, or TypeScript classes. Logging is MANDATORY in all Angular files. Implements @isa/core/logging with logger() factory pattern, appropriate log levels, lazy evaluation for performance, error handling, and avoids console.log and common mistakes.
 ---
 

CLAUDE.md

@@ -112,6 +112,52 @@ angular-template → html-template → logging → tailwind
 
 Use `/clear` between unrelated tasks to prevent context degradation.
 
+### Long-Running Task Pattern
+
+For complex tasks approaching context limits:
+1. Dump progress to a `.md` file (e.g., `progress.md`)
+2. Use `/clear` to reset context
+3. Resume by reading the progress file
+4. Continue from where you left off
+
+### Context Monitoring
+
+- Use `/context` to check current token usage
+- Fresh session baseline: ~20k tokens
+- Consider `/compact` when approaching 150k tokens
+- Prefer `/clear` over `/compact` when starting new topics
+
+## Extended Thinking
+
+Use progressive thinking depth for complex analysis:
+
+| Trigger | Thinking Budget | Use Case |
+|---------|----------------|----------|
+| `"think"` | ~4k tokens | Basic analysis, simple decisions |
+| `"think hard"` | ~10k tokens | Moderate complexity, multi-factor decisions |
+| `"think harder"` | ~16k tokens | Deep analysis, architectural decisions |
+| `"ultrathink"` | ~32k tokens | Maximum depth, critical planning |
+
+**Examples:**
+- "Think about how to structure this component"
+- "Think hard about the best approach for state management"
+- "Ultrathink about the architecture for this feature"
+
+## Code Investigation (MANDATORY)
+
+**Never speculate about code you haven't read.**
+
+If user references a specific file:
+1. **READ the file first** using the Read tool
+2. **THEN provide analysis** based on actual contents
+3. If file doesn't exist, **say so explicitly**
+
+**Anti-Hallucination Rules:**
+- Never describe code you haven't opened
+- Never assume file contents based on names
+- Never guess API signatures without documentation
+- Always verify imports and dependencies exist
+
 ## Implementation Decisions
 
 | Task Type                         | Required Agent     | Escalation Path                           |