Doc Rot Audit

1. Context Loading: Scan for documentation (README.md, /docs/, *.rst) and source. Identify the "Vocabulary" of the project.
2. Change Detection: Run git diff --stat @{7.days.ago} to find recently modified code. Focus on API signature changes.
3. Gap Analysis: Search docs for updates corresponding to high-impact code changes.

Phase 2: Semantic Drift Analysis

Objective: Identify Map-Territory divergence.

1. Vocabulary Drift Check: Compare terms in prose vs. logic (User vs. Account). Flag imports that no longer exist.
2. Context Rot Validation: Check for "Dead Paths" (deleted config files mentioned in setup guides). Review ADRs for implementation divergence.

Artifact Generation

1. DOC_HEALTH_REPORT.md

• Rot Severity Score: (Low / Medium / Critical)
• The "Lying" Index: List of factually incorrect documentation lines.
• Drifted Vocabulary: Table mapping [Doc Term] -> [Actual Code Term].
• Missing Context: Recent features absent in docs.

2. REMEDIATION_PLAN.md (Tree-of-Thoughts)

• Branch A (Surgical): Minimal updates to fix broken examples/params (Automated).
• Branch B (Strategic): Rewrite of sections where logic has fundamentally diverged.
• Recommendation: Which branch to take based on severity.

Verification Logic

[Verify]: Propose a single CLI command to verify the sync (e.g., grep -r [NewSymbol] docs/) or a manual check criteria: "I have confirmed that process_payment now includes the region parameter in the Integration Guide."

Ask the user: "I have generated the Health Report and Remediation Plan. Would you like me to execute 'Branch A' immediately to resolve syntax discrepancies?"