wycats/vscode-ai-plugin

wycats/vscode-ai-plugin

Agent

Makes controlled forward progress on a plan, reading how reality responds to each change and adjusting course without losing contact with actual workspace state.

wycats/vscode-ai-plugin

Agent

Pre-read agent for session handoffs. Maps the relevant codebase terrain so the next working agent can orient quickly instead of discovering the landscape from scratch.

wycats/vscode-ai-plugin

Agent

Forms falsifiable predictions about the codebase and the plan, producing hypotheses that execution will test and review will evaluate.

wycats/vscode-ai-plugin

Agent

Bounded codebase investigator dispatched by Recon for parallel sub-investigations needing rich tools (git, terminal, exo). Returns grounded findings with sourcing, not raw data. For simple search fan-out, use Explore instead.

wycats/vscode-ai-plugin

Agent

Adaptive codebase investigator — follows leads, uses tools interactively, and synthesizes findings. Use when each result may change what to search next. For known searches, use Explore instead.

wycats/vscode-ai-plugin

Agent

Evaluates what happened against what was predicted, reading the gap between expectation and outcome to judge what the divergences mean and whether the result warrants confidence.

wycats/vscode-ai-plugin

Agent

Identifies and removes slop from documents.