Pesquisa e Web

Formats review deliverables with consistent structure for comparable findings. Use when finalizing any review or analysis that must be shared or compared.

Compresses verbose responses by removing filler and framing to save 200-400 tokens. Use when responses feel bloated or context is filling fast.

Optimizes context window via MECW principles and memory tiering. Use when context exceeds 30% or before long multi-step tasks.

Creates behavioral rules in markdown to block dangerous commands or restrict AI behavior. Use when adding safety guardrails or preventing specific commands.

Searches the code knowledge graph by function, class, or type using FTS5 full-text search. Use when locating code entities by name or qualified path.

Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

Detects time and space complexity hotspots via AST scan. Use when code feels slow, before performance-sensitive merges, or to find O(n²) regressions.

Defines the contract for deferred-item capture across plugins. Use when building or validating a plugin's deferred-capture wrapper or adding source labels.

Web shell samples for detection and analysis: PHP, ASP, ASPX, JSP, Python, Perl shells. Use for security research and detection system testing.

Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.

Manages context overflow by handing off to a fresh subagent at 80% usage. Use when context pressure is critical and work must continue uninterrupted.

Curate the web-capture index. Use when the capture backlog grows, captures sit unprocessed at seedling/pending, or to surface stored research during work.