$ loading_
Preflight checks vague prompts and improves AI coding workflows with less token waste.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "preflight" yet — see the docs or source repo.
Check whether this prompt for Claude Code is vague and rewrite it more clearly: 'Help me fix the login API issue and improve performance too.'
Highlights ambiguity and missing context, then returns a clearer, actionable rewritten prompt.
Triage this request: 'Production errors show intermittent payment callback failures, possibly related to retry logic.' Provide priority, investigation steps, and missing information needed.
Provides a structured triage result with risk level, investigation path, and follow-up questions.
Score this development prompt and explain how to reduce wasted tokens: 'Build me a user system.'
Returns a prompt quality score, reasons for deductions, and concrete improvement suggestions.
Delegate coding tasks to Codex via MCP with security and result checks.
Reduce LLM token usage by lazy-loading tools and routing repetitive subtasks.
Quickly trace code relationships and execution paths with a single AI tool call.
Securely run Claude Code CLI via MCP for tasks, memory, and IDE integration.
Aggregate coding plan services for code review, plan review, and AI coding dialogue.
Provide project knowledge search and failure analysis for Claude Code workflows.