Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsAgentNavigator – Pre-Refactoring Project Stage Auditor
Diagnoses repository scale metrics and error patterns to provide a single, clear next-step action plan for your codebase. Returns JSON.
$5
AgentNavigator – Pre-Refactoring Project Stage Auditor
Example session with this skill installed
Run AgentNavigator to audit our repository layout and generate the next valid engineering step.
- Read your context and instructions
- Compiled the agentnavigator
🔍 ARCHITECTURAL COMPLIANCE SECURED. ENFORCING LIFECYCLE DISPATCHER BLUEPRINT ONLY.
{
"stage": 2,
"signals_used": [
"monolithic_file_volume:1800_lines",
"agent_behavior:function_dropping",
"database_type:sqlite"
],
"what_is_happening": "The repository architecture has reached Stage 2. The single-file volume limits context tracking stability during developer sessions.",
"what_breaks_if_skipped": "The system will execute silent data deletions, duplicate existing functions, and introduce regression loops inside deep dependency tracks.",
"recommended_action": "Split the main module tree using a modular file split pass.",
"specialized_skill": "FileTreeArchitect",
"what_comes_after": "Context stabilization must occur first. Database migration sequences (Stage 3) will remain locked until file separation is complete."
}
Connects securely to your tools. The creator never sees your data.
About this skill
Stop fighting chaotic codebase expansion and blind feature deployment. AgentNavigator is a static repository evaluation product built to analyze file scale, database limits, and agent performance to enforce a clean, structured development track.
Most codebases degrade because teams add features until the architecture hits a wall—triggering sudden context drops, database write locks, or config state pollution. This product evaluates real structural parameters, isolates the explicit lifecycle stage (Stages 0–7), and delivers a definitive technical step to keep your repository stable.
Core Capabilities
- Step-by-Step Architecture Diagnostics: Evaluates file lengths and dependency setups against a strict 7-stage engineering matrix to isolate hidden technical debt.
- Context Decay Preemption: Pinpoints exact token thresholds and file sizes that cause AI models like Cursor or Claude Code to repeat or truncate functions.
- Premature Refactoring Interception: Forces a rigid, logical development roadmap, blocking high-risk infrastructure migrations until they are genuinely required.
- 100% Local Operations: Generates diagnostic roadmap telemetry completely offline (file_system_write: false) with zero data tracking or repository leakage risks.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
Context-advisory guardrail only — functions via repository scale metrics and structural telemetry evaluation without running local binary test protocols. Safely validated through extensive execution-flow logic. Requires a minimum of 3 verifiable technical environment signals to compute an accurate triage state. Out of scope for small codebases under 300 lines or projects with an already established next action path.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 28 days ago
- Software
Python
Permissions
File Scopes
Read access safely scans project structures to isolate metadata signals and structural footprints prior to triage. Zero filesystem writes — this advisory gate locks down exactly one logical execution path and manages hand-offs without running scripts or modifying files.