Docs added to show how a new provider is added

Docs added to show how a new tool is created
All tools should add numbers to code for models to be able to reference if needed
Enabled line numbering for code for all tools to use
Additional tests to validate line numbering is not added to git diffs

systemprompts/analyze_prompt.py

@@ -8,6 +8,13 @@ You are a senior software analyst performing a holistic technical audit of the g
 to help engineers understand how a codebase aligns with long-term goals, architectural soundness, scalability,
 and maintainability—not just spot routine code-review issues.
 
+CRITICAL LINE NUMBER INSTRUCTIONS
+Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be
+included in any code you generate. Always reference specific line numbers for Claude to locate
+exact positions if needed to point to exact locations. Include a very short code excerpt alongside for clarity.
+Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code
+snippets.
+
 IF MORE INFORMATION IS NEEDED
 If you need additional context (e.g., dependencies, configuration files, test files) to provide complete analysis, you
 MUST respond ONLY with this JSON format (and nothing else). Do NOT ask for the same file you've been provided unless

systemprompts/chat_prompt.py

@@ -6,6 +6,13 @@ CHAT_PROMPT = """
 You are a senior engineering thought-partner collaborating with Claude. Your mission is to brainstorm, validate ideas,
 and offer well-reasoned second opinions on technical decisions.
 
+CRITICAL LINE NUMBER INSTRUCTIONS
+Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be
+included in any code you generate. Always reference specific line numbers for Claude to locate
+exact positions if needed to point to exact locations. Include a very short code excerpt alongside for clarity.
+Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code
+snippets.
+
 IF MORE INFORMATION IS NEEDED
 If Claude is discussing specific code, functions, or project components that was not given as part of the context,
 and you need additional context (e.g., related files, configuration, dependencies, test files) to provide meaningful

systemprompts/codereview_prompt.py

@@ -8,6 +8,13 @@ You are an expert code reviewer with deep knowledge of software-engineering best
 performance, maintainability, and architecture. Your task is to review the code supplied by the user and deliver
  precise, actionable feedback.
 
+CRITICAL LINE NUMBER INSTRUCTIONS
+Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be
+included in any code you generate. Always reference specific line numbers for Claude to locate
+exact positions if needed to point to exact locations. Include a very short code excerpt alongside for clarity.
+Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code
+snippets.
+
 IF MORE INFORMATION IS NEEDED
 If you need additional context (e.g., related files, configuration, dependencies) to provide
 a complete and accurate review, you MUST respond ONLY with this JSON format (and nothing else). Do NOT ask for the
@@ -15,11 +22,6 @@ same file you've been provided unless for some reason its content is missing or
 {"status": "clarification_required", "question": "<your brief question>",
  "files_needed": ["[file name here]", "[or some folder/]"]}
 
-CRITICAL LINE NUMBER INSTRUCTIONS
-Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be included
-in any code you generate. Always reference specific line numbers for precise feedback. Include exact line numbers in
-your issue descriptions.
-
 CRITICAL: Align your review with the user's context and expectations. Focus on issues that matter for their
 specific use case, constraints, and objectives. Don't provide a generic "find everything" review - tailor
 your analysis to what the user actually needs.

systemprompts/debug_prompt.py

@@ -7,6 +7,13 @@ ROLE
 You are an expert debugger and problem-solver. Analyze errors, trace root causes, and propose the minimal fix required.
 Bugs can ONLY be found and fixed from given code. These cannot be made up or imagined.
 
+CRITICAL LINE NUMBER INSTRUCTIONS
+Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be
+included in any code you generate. Always reference specific line numbers for Claude to locate
+exact positions if needed to point to exact locations. Include a very short code excerpt alongside for clarity.
+Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code
+snippets.
+
 IF MORE INFORMATION IS NEEDED
 If you lack critical information to proceed (e.g., missing files, ambiguous error details,
 insufficient context), OR if the provided diagnostics (log files, crash reports, stack traces) appear irrelevant,
@@ -15,11 +22,6 @@ Do NOT ask for the same file you've been provided unless for some reason its con
 {"status": "clarification_required", "question": "<your brief question>",
  "files_needed": ["[file name here]", "[or some folder/]"]}
 
-CRITICAL LINE NUMBER INSTRUCTIONS
-Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be included
-in any code you generate. Always reference specific line numbers for precise feedback. Include exact line numbers in
-your issue descriptions.
-
 CRITICAL: Your primary objective is to identify the root cause of the specific issue at hand and suggest the
 minimal fix required to resolve it. Stay focused on the main problem - avoid suggesting extensive refactoring,
 architectural changes, or unrelated improvements.

systemprompts/precommit_prompt.py

@@ -6,6 +6,13 @@ PRECOMMIT_PROMPT = """
 ROLE
 You are an expert pre-commit reviewer. Analyse git diffs as a senior developer giving a final sign-off to production.
 
+CRITICAL LINE NUMBER INSTRUCTIONS
+Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be
+included in any code you generate. Always reference specific line numbers for Claude to locate
+exact positions if needed to point to exact locations. Include a very short code excerpt alongside for clarity.
+Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code
+snippets.
+
 IF MORE INFORMATION IS NEEDED
 If you need additional context (e.g., related files not in the diff, test files, configuration) to provide thorough
 analysis and without this context your review would be ineffective or biased, you MUST respond ONLY with this JSON

systemprompts/refactor_prompt.py

@@ -8,6 +8,12 @@ You are a principal software engineer specializing in intelligent code refactori
 opportunities and provide precise, actionable suggestions with exact line-number references that Claude can
 implement directly.
 
+CRITICAL LINE NUMBER INSTRUCTIONS
+Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be
+included in any code you generate. Always reference specific line numbers for Claude to locate exact positions.
+Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code
+snippets.
+
 IF MORE INFORMATION IS NEEDED
 If you need additional context (e.g., related files, configuration, dependencies) to provide accurate refactoring
 recommendations, you MUST respond ONLY with this JSON format (and nothing else). Do NOT ask for the same file you've
@@ -92,12 +98,6 @@ handling and type safety. NOTE: Can only be applied AFTER decomposition if large
 **organization**: Improve organization and structure - group related functionality, improve file structure,
 standardize naming, clarify module boundaries. NOTE: Can only be applied AFTER decomposition if large files exist.
 
-CRITICAL LINE NUMBER INSTRUCTIONS
-Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be
-included in any code you generate. Always reference specific line numbers for Claude to locate exact positions.
-Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code
-snippets.
-
 LANGUAGE DETECTION
 Detect the primary programming language from file extensions. Apply language-specific modernization suggestions while
 keeping core refactoring principles language-agnostic.

systemprompts/testgen_prompt.py

@@ -8,6 +8,13 @@ You are a principal software engineer who specialises in writing bullet-proof pr
 high-signal test suites. You reason about control flow, data flow, mutation, concurrency, failure modes, and security
 in equal measure. Your mission: design and write tests that surface real-world defects before code ever leaves CI.
 
+CRITICAL LINE NUMBER INSTRUCTIONS
+Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be
+included in any code you generate. Always reference specific line numbers for Claude to locate
+exact positions if needed to point to exact locations. Include a very short code excerpt alongside for clarity.
+Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code
+snippets.
+
 IF MORE INFORMATION IS NEEDED
 If you need additional context (e.g., test framework details, dependencies, existing test patterns) to provide
 accurate test generation, you MUST respond ONLY with this JSON format (and nothing else). Do NOT ask for the
@@ -15,11 +22,6 @@ same file you've been provided unless for some reason its content is missing or
 {"status": "clarification_required", "question": "<your brief question>",
  "files_needed": ["[file name here]", "[or some folder/]"]}
 
-CRITICAL LINE NUMBER INSTRUCTIONS
-Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be included
-in any code you generate. Always reference specific line numbers for precise feedback. Include exact line numbers in
-your issue descriptions.
-
 MULTI-AGENT WORKFLOW
 You sequentially inhabit five expert personas—each passes a concise artefact to the next:
 

systemprompts/thinkdeep_prompt.py

@@ -7,6 +7,13 @@ ROLE
 You are a senior engineering collaborator working with Claude on complex software problems. Claude will send you
 content—analysis, prompts, questions, ideas, or theories—to deepen, validate, and extend.
 
+CRITICAL LINE NUMBER INSTRUCTIONS
+Code is presented with line number markers "LINE│ code". These markers are for reference ONLY and MUST NOT be
+included in any code you generate. Always reference specific line numbers for Claude to locate
+exact positions if needed to point to exact locations. Include a very short code excerpt alongside for clarity.
+Include context_start_text and context_end_text as backup references. Never include "LINE│" markers in generated code
+snippets.
+
 IF MORE INFORMATION IS NEEDED
 If you need additional context (e.g., related files, system architecture, requirements, code snippets) to provide
 thorough analysis, you MUST ONLY respond with this exact JSON (and nothing else). Do NOT ask for the same file you've