anchi-toolkit 1.0.0

package/.cursor/skills/debugging/SKILL.md

@@ -0,0 +1,84 @@
+---
+name: Debugging
+description: Systematic debugging framework ensuring root cause investigation before fixes. Includes four-phase debugging process, backward call stack tracing, multi-layer validation, and verification protocols. Use when encountering bugs, test failures, unexpected behavior, performance issues, or before claiming work complete. Prevents random fixes, masks over symptoms, and false completion claims.
+version: 3.0.0
+languages: all
+---
+
+# Debugging
+
+Comprehensive debugging framework combining systematic investigation, root cause tracing, defense-in-depth validation, and verification protocols.
+
+## Core Principle
+
+**NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST**
+
+Random fixes waste time and create new bugs. Find the root cause, fix at source, validate at every layer, verify before claiming success.
+
+## When to Use
+
+**Always use for:** Test failures, bugs, unexpected behavior, performance issues, build failures, integration problems, before claiming work complete
+
+**Especially when:** Under time pressure, "quick fix" seems obvious, tried multiple fixes, don't fully understand issue, about to claim success
+
+## The Four Techniques
+
+### 1. Systematic Debugging (`references/systematic-debugging.md`)
+
+Four-phase framework ensuring proper investigation:
+- Phase 1: Root Cause Investigation (read errors, reproduce, check changes, gather evidence)
+- Phase 2: Pattern Analysis (find working examples, compare, identify differences)
+- Phase 3: Hypothesis and Testing (form theory, test minimally, verify)
+- Phase 4: Implementation (create test, fix once, verify)
+
+**Key rule:** Complete each phase before proceeding. No fixes without Phase 1.
+
+**Load when:** Any bug/issue requiring investigation and fix
+
+### 2. Root Cause Tracing (`references/root-cause-tracing.md`)
+
+Trace bugs backward through call stack to find original trigger.
+
+**Technique:** When error appears deep in execution, trace backward level-by-level until finding source where invalid data originated. Fix at source, not at symptom.
+
+**Includes:** `scripts/find-polluter.sh` for bisecting test pollution
+
+**Load when:** Error deep in call stack, unclear where invalid data originated
+
+### 3. Defense-in-Depth (`references/defense-in-depth.md`)
+
+Validate at every layer data passes through. Make bugs impossible.
+
+**Four layers:** Entry validation → Business logic → Environment guards → Debug instrumentation
+
+**Load when:** After finding root cause, need to add comprehensive validation
+
+### 4. Verification (`references/verification.md`)
+
+Run verification commands and confirm output before claiming success.
+
+**Iron law:** NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
+
+Run the command. Read the output. Then claim the result.
+
+**Load when:** About to claim work complete, fixed, or passing
+
+## Quick Reference
+
+```
+Bug → systematic-debugging.md (Phase 1-4)
+  Error deep in stack? → root-cause-tracing.md (trace backward)
+  Found root cause? → defense-in-depth.md (add layers)
+  About to claim success? → verification.md (verify first)
+```
+
+## Red Flags
+
+Stop and follow process if thinking:
+- "Quick fix for now, investigate later"
+- "Just try changing X and see if it works"
+- "It's probably X, let me fix that"
+- "Should work now" / "Seems fixed"
+- "Tests pass, we're done"
+
+**All mean:** Return to systematic process.

package/.cursor/skills/debugging/references/defense-in-depth.md

@@ -0,0 +1,124 @@
+# Defense-in-Depth Validation
+
+Validate at every layer data passes through to make bugs impossible.
+
+## Core Principle
+
+**Validate at EVERY layer data passes through. Make bug structurally impossible.**
+
+When fix bug caused by invalid data, adding validation at one place feels sufficient. But single check can be bypassed by different code paths, refactoring, or mocks.
+
+## Why Multiple Layers
+
+Single validation: "We fixed bug"
+Multiple layers: "We made bug impossible"
+
+Different layers catch different cases:
+- Entry validation catches most bugs
+- Business logic catches edge cases
+- Environment guards prevent context-specific dangers
+- Debug logging helps when other layers fail
+
+## The Four Layers
+
+### Layer 1: Entry Point Validation
+**Purpose:** Reject obviously invalid input at API boundary
+
+```typescript
+function createProject(name: string, workingDirectory: string) {
+  if (!workingDirectory || workingDirectory.trim() === '') {
+    throw new Error('workingDirectory cannot be empty');
+  }
+  if (!existsSync(workingDirectory)) {
+    throw new Error(`workingDirectory does not exist: ${workingDirectory}`);
+  }
+  if (!statSync(workingDirectory).isDirectory()) {
+    throw new Error(`workingDirectory is not a directory: ${workingDirectory}`);
+  }
+  // proceed
+}
+```
+
+### Layer 2: Business Logic Validation
+**Purpose:** Ensure data makes sense for this operation
+
+```typescript
+function initializeWorkspace(projectDir: string, sessionId: string) {
+  if (!projectDir) {
+    throw new Error('projectDir required for workspace initialization');
+  }
+  // proceed
+}
+```
+
+### Layer 3: Environment Guards
+**Purpose:** Prevent dangerous operations in specific contexts
+
+```typescript
+async function gitInit(directory: string) {
+  // In tests, refuse git init outside temp directories
+  if (process.env.NODE_ENV === 'test') {
+    const normalized = normalize(resolve(directory));
+    const tmpDir = normalize(resolve(tmpdir()));
+
+    if (!normalized.startsWith(tmpDir)) {
+      throw new Error(
+        `Refusing git init outside temp dir during tests: ${directory}`
+      );
+    }
+  }
+  // proceed
+}
+```
+
+### Layer 4: Debug Instrumentation
+**Purpose:** Capture context for forensics
+
+```typescript
+async function gitInit(directory: string) {
+  const stack = new Error().stack;
+  logger.debug('About to git init', {
+    directory,
+    cwd: process.cwd(),
+    stack,
+  });
+  // proceed
+}
+```
+
+## Applying the Pattern
+
+When find bug:
+
+1. **Trace data flow** - Where does bad value originate? Where used?
+2. **Map all checkpoints** - List every point data passes through
+3. **Add validation at each layer** - Entry, business, environment, debug
+4. **Test each layer** - Try to bypass layer 1, verify layer 2 catches it
+
+## Example from Real Session
+
+Bug: Empty `projectDir` caused `git init` in source code
+
+**Data flow:**
+1. Test setup → empty string
+2. `Project.create(name, '')`
+3. `WorkspaceManager.createWorkspace('')`
+4. `git init` runs in `process.cwd()`
+
+**Four layers added:**
+- Layer 1: `Project.create()` validates not empty/exists/writable
+- Layer 2: `WorkspaceManager` validates projectDir not empty
+- Layer 3: `WorktreeManager` refuses git init outside tmpdir in tests
+- Layer 4: Stack trace logging before git init
+
+**Result:** All 1847 tests passed, bug impossible to reproduce
+
+## Key Insight
+
+All four layers were necessary. During testing, each layer caught bugs others missed:
+- Different code paths bypassed entry validation
+- Mocks bypassed business logic checks
+- Edge cases on different platforms needed environment guards
+- Debug logging identified structural misuse
+
+**Don't stop at one validation point.** Add checks at every layer.

package/.cursor/skills/debugging/references/root-cause-tracing.md

@@ -0,0 +1,122 @@
+# Root Cause Tracing
+
+Systematically trace bugs backward through call stack to find original trigger.
+
+## Core Principle
+
+**Trace backward through call chain until finding original trigger, then fix at source.**
+
+Bugs often manifest deep in call stack (git init in wrong directory, file created in wrong location). Instinct is to fix where error appears, but that's treating symptom.
+
+## When to Use
+
+**Use when:**
+- Error happens deep in execution (not at entry point)
+- Stack trace shows long call chain
+- Unclear where invalid data originated
+- Need to find which test/code triggers problem
+
+## The Tracing Process
+
+### 1. Observe the Symptom
+```
+Error: git init failed in /Users/jesse/project/packages/core
+```
+
+### 2. Find Immediate Cause
+What code directly causes this?
+```typescript
+await execFileAsync('git', ['init'], { cwd: projectDir });
+```
+
+### 3. Ask: What Called This?
+```typescript
+WorktreeManager.createSessionWorktree(projectDir, sessionId)
+  → called by Session.initializeWorkspace()
+  → called by Session.create()
+  → called by test at Project.create()
+```
+
+### 4. Keep Tracing Up
+What value was passed?
+- `projectDir = ''` (empty string!)
+- Empty string as `cwd` resolves to `process.cwd()`
+- That's the source code directory!
+
+### 5. Find Original Trigger
+Where did empty string come from?
+```typescript
+const context = setupCoreTest(); // Returns { tempDir: '' }
+Project.create('name', context.tempDir); // Accessed before beforeEach!
+```
+
+## Adding Stack Traces
+
+When can't trace manually, add instrumentation:
+
+```typescript
+async function gitInit(directory: string) {
+  const stack = new Error().stack;
+  console.error('DEBUG git init:', {
+    directory,
+    cwd: process.cwd(),
+    stack,
+  });
+
+  await execFileAsync('git', ['init'], { cwd: directory });
+}
+```
+
+**Critical:** Use `console.error()` in tests (not logger - may not show)
+
+**Run and capture:**
+```bash
+npm test 2>&1 | grep 'DEBUG git init'
+```
+
+**Analyze stack traces:**
+- Look for test file names
+- Find line number triggering call
+- Identify pattern (same test? same parameter?)
+
+## Finding Which Test Causes Pollution
+
+If something appears during tests but don't know which test:
+
+Use bisection script: `scripts/find-polluter.sh`
+
+```bash
+./scripts/find-polluter.sh '.git' 'src/**/*.test.ts'
+```
+
+Runs tests one-by-one, stops at first polluter.
+
+## Key Principle
+
+**NEVER fix just where error appears.** Trace back to find original trigger.
+
+When found immediate cause:
+- Can trace one level up? → Trace backwards
+- Is this the source? → Fix at source
+- Then add validation at each layer (see defense-in-depth.md)
+
+## Real Example
+
+**Symptom:** `.git` created in `packages/core/` (source code)
+
+**Trace chain:**
+1. `git init` runs in `process.cwd()` ← empty cwd parameter
+2. WorktreeManager called with empty projectDir
+3. Session.create() passed empty string
+4. Test accessed `context.tempDir` before beforeEach
+5. setupCoreTest() returns `{ tempDir: '' }` initially
+
+**Root cause:** Top-level variable initialization accessing empty value
+
+**Fix:** Made tempDir a getter that throws if accessed before beforeEach
+
+**Also added defense-in-depth:**
+- Layer 1: Project.create() validates directory
+- Layer 2: WorkspaceManager validates not empty
+- Layer 3: NODE_ENV guard refuses git init outside tmpdir
+- Layer 4: Stack trace logging before git init

package/.cursor/skills/debugging/references/systematic-debugging.md

@@ -0,0 +1,102 @@
+# Systematic Debugging
+
+Four-phase debugging framework that ensures root cause investigation before attempting fixes.
+
+## The Iron Law
+
+```
+NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
+```
+
+If haven't completed Phase 1, cannot propose fixes.
+
+## The Four Phases
+
+Must complete each phase before proceeding to next.
+
+### Phase 1: Root Cause Investigation
+
+**BEFORE attempting ANY fix:**
+
+1. **Read Error Messages Carefully** - Don't skip past errors/warnings, read stack traces completely
+2. **Reproduce Consistently** - Can trigger reliably? Exact steps? If not reproducible → gather more data
+3. **Check Recent Changes** - What changed? Git diff, recent commits, new dependencies, config changes
+4. **Gather Evidence in Multi-Component Systems**
+   - For EACH component boundary: log data entering/exiting, verify environment propagation
+   - Run once to gather evidence showing WHERE it breaks
+   - THEN analyze to identify failing component
+5. **Trace Data Flow** - Where does bad value originate? Trace up call stack until finding source (see root-cause-tracing.md)
+
+### Phase 2: Pattern Analysis
+
+**Find pattern before fixing:**
+
+1. **Find Working Examples** - Locate similar working code in same codebase
+2. **Compare Against References** - Read reference implementation COMPLETELY, understand fully before applying
+3. **Identify Differences** - List every difference however small, don't assume "that can't matter"
+4. **Understand Dependencies** - What other components, settings, config, environment needed?
+
+### Phase 3: Hypothesis and Testing
+
+**Scientific method:**
+
+1. **Form Single Hypothesis** - "I think X is root cause because Y", be specific not vague
+2. **Test Minimally** - SMALLEST possible change to test hypothesis, one variable at a time
+3. **Verify Before Continuing** - Worked? → Phase 4. Didn't work? → NEW hypothesis. DON'T add more fixes
+4. **When Don't Know** - Say "I don't understand X", don't pretend, ask for help
+
+### Phase 4: Implementation
+
+**Fix root cause, not symptom:**
+
+1. **Create Failing Test Case** - Simplest reproduction, automated if possible, MUST have before fixing
+2. **Implement Single Fix** - Address root cause identified, ONE change, no "while I'm here" improvements
+3. **Verify Fix** - Test passes? No other tests broken? Issue actually resolved?
+4. **If Fix Doesn't Work**
+   - STOP. Count: How many fixes tried?
+   - If < 3: Return to Phase 1, re-analyze with new information
+   - **If ≥ 3: STOP and question architecture**
+5. **If 3+ Fixes Failed: Question Architecture**
+   - Pattern: Each fix reveals new shared state/coupling problem elsewhere
+   - STOP and question fundamentals: Is pattern sound? Wrong architecture?
+   - Discuss with human partner before more fixes
+
+## Red Flags - STOP and Follow Process
+
+If catch yourself thinking:
+- "Quick fix for now, investigate later"
+- "Just try changing X and see if it works"
+- "Add multiple changes, run tests"
+- "Skip the test, I'll manually verify"
+- "It's probably X, let me fix that"
+- "I don't fully understand but this might work"
+- "One more fix attempt" (when already tried 2+)
+
+**ALL mean:** STOP. Return to Phase 1.
+
+## Human Partner Signals You're Doing It Wrong
+
+- "Is that not happening?" - Assumed without verifying
+- "Will it show us...?" - Should have added evidence gathering
+- "Stop guessing" - Proposing fixes without understanding
+- "Ultrathink this" - Question fundamentals, not just symptoms
+- "We're stuck?" (frustrated) - Approach isn't working
+
+**When see these:** STOP. Return to Phase 1.
+
+## Common Rationalizations
+
+| Excuse | Reality |
+|--------|---------|
+| "Issue is simple, don't need process" | Simple issues have root causes too |
+| "Emergency, no time for process" | Systematic is FASTER than guess-and-check |
+| "Just try this first, then investigate" | First fix sets pattern. Do right from start |
+| "One more fix attempt" (after 2+ failures) | 3+ failures = architectural problem |
+
+## Real-World Impact
+
+From debugging sessions:
+- Systematic approach: 15-30 minutes to fix
+- Random fixes approach: 2-3 hours of thrashing
+- First-time fix rate: 95% vs 40%
+- New bugs introduced: Near zero vs common

package/.cursor/skills/debugging/references/verification.md

@@ -0,0 +1,123 @@
+# Verification Before Completion
+
+Run verification commands and confirm output before claiming success.
+
+## Core Principle
+
+**Evidence before claims, always.**
+
+Claiming work complete without verification is dishonesty, not efficiency.
+
+## The Iron Law
+
+```
+NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
+```
+
+If haven't run verification command in this message, cannot claim it passes.
+
+## The Gate Function
+
+```
+BEFORE claiming any status or expressing satisfaction:
+
+1. IDENTIFY: What command proves this claim?
+2. RUN: Execute FULL command (fresh, complete)
+3. READ: Full output, check exit code, count failures
+4. VERIFY: Does output confirm claim?
+   - If NO: State actual status with evidence
+   - If YES: State claim WITH evidence
+5. ONLY THEN: Make claim
+
+Skip any step = lying, not verifying
+```
+
+## Common Failures
+
+| Claim | Requires | Not Sufficient |
+|-------|----------|----------------|
+| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
+| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
+| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
+| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
+| Regression test works | Red-green cycle verified | Test passes once |
+| Agent completed | VCS diff shows changes | Agent reports "success" |
+| Requirements met | Line-by-line checklist | Tests passing |
+
+## Red Flags - STOP
+
+- Using "should", "probably", "seems to"
+- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!")
+- About to commit/push/PR without verification
+- Trusting agent success reports
+- Relying on partial verification
+- Thinking "just this once"
+- Tired and wanting work over
+- **ANY wording implying success without having run verification**
+
+## Rationalization Prevention
+
+| Excuse | Reality |
+|--------|---------|
+| "Should work now" | RUN verification |
+| "I'm confident" | Confidence ≠ evidence |
+| "Just this once" | No exceptions |
+| "Linter passed" | Linter ≠ compiler |
+| "Agent said success" | Verify independently |
+| "Partial check is enough" | Partial proves nothing |
+
+## Key Patterns
+
+**Tests:**
+```
+✅ [Run test command] [See: 34/34 pass] "All tests pass"
+❌ "Should pass now" / "Looks correct"
+```
+
+**Regression tests (TDD Red-Green):**
+```
+✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
+❌ "I've written regression test" (without red-green verification)
+```
+
+**Build:**
+```
+✅ [Run build] [See: exit 0] "Build passes"
+❌ "Linter passed" (linter doesn't check compilation)
+```
+
+**Requirements:**
+```
+✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
+❌ "Tests pass, phase complete"
+```
+
+**Agent delegation:**
+```
+✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
+❌ Trust agent report
+```
+
+## When To Apply
+
+**ALWAYS before:**
+- ANY variation of success/completion claims
+- ANY expression of satisfaction
+- ANY positive statement about work state
+- Committing, PR creation, task completion
+- Moving to next task
+- Delegating to agents
+
+**Rule applies to:**
+- Exact phrases
+- Paraphrases and synonyms
+- Implications of success
+- ANY communication suggesting completion/correctness
+
+## The Bottom Line
+
+**No shortcuts for verification.**
+
+Run command. Read output. THEN claim result.
+
+Non-negotiable.

package/.cursor/skills/debugging/scripts/find-polluter.sh

@@ -0,0 +1,63 @@
+#!/bin/bash
+# Bisection script to find which test creates unwanted files/state
+# Usage: ./find-polluter.sh <file_or_dir_to_check> <test_pattern>
+# Example: ./find-polluter.sh '.git' 'src/**/*.test.ts'
+
+set -e
+
+if [ $# -ne 2 ]; then
+  echo "Usage: $0 <file_to_check> <test_pattern>"
+  echo "Example: $0 '.git' 'src/**/*.test.ts'"
+  exit 1
+fi
+
+POLLUTION_CHECK="$1"
+TEST_PATTERN="$2"
+
+echo "🔍 Searching for test that creates: $POLLUTION_CHECK"
+echo "Test pattern: $TEST_PATTERN"
+echo ""
+
+# Get list of test files
+TEST_FILES=$(find . -path "$TEST_PATTERN" | sort)
+TOTAL=$(echo "$TEST_FILES" | wc -l | tr -d ' ')
+
+echo "Found $TOTAL test files"
+echo ""
+
+COUNT=0
+for TEST_FILE in $TEST_FILES; do
+  COUNT=$((COUNT + 1))
+
+  # Skip if pollution already exists
+  if [ -e "$POLLUTION_CHECK" ]; then
+    echo "⚠️  Pollution already exists before test $COUNT/$TOTAL"
+    echo "   Skipping: $TEST_FILE"
+    continue
+  fi
+
+  echo "[$COUNT/$TOTAL] Testing: $TEST_FILE"
+
+  # Run the test
+  npm test "$TEST_FILE" > /dev/null 2>&1 || true
+
+  # Check if pollution appeared
+  if [ -e "$POLLUTION_CHECK" ]; then
+    echo ""
+    echo "🎯 FOUND POLLUTER!"
+    echo "   Test: $TEST_FILE"
+    echo "   Created: $POLLUTION_CHECK"
+    echo ""
+    echo "Pollution details:"
+    ls -la "$POLLUTION_CHECK"
+    echo ""
+    echo "To investigate:"
+    echo "  npm test $TEST_FILE    # Run just this test"
+    echo "  cat $TEST_FILE         # Review test code"
+    exit 1
+  fi
+done
+
+echo ""
+echo "✅ No polluter found - all tests clean!"
+exit 0