Command Cursor
Systematic workflow for triaging and fixing bugs with architecture grounding.
A CLI-first autonomous coding agent where the actor never grades itself. Every edit is grounded in your repo's real topology and verified by an independent deterministic grader (drift, lint, verify-task, intent) before it ships. Closed-loop: comprehend → plan → execute → critique → replan. Also a passive MCP harness.
Command Cursor
Systematic workflow for triaging and fixing bugs with architecture grounding.
Command Cursor
Generate a post-AI-edit confidence report showing what changed, what evidence was checked, what risks remain, and what to inspect at 3AM.
Command Cursor
After an agent mistake, improve repo AI guidance (Sruja).
Command Cursor
Implement from a frozen plan in a focused session (Sruja).
Command Cursor
Produce a task-level implementation plan (Sruja).
Command Cursor
Structured review workflow before merging changes. Produces actionable feedback with architecture grounding.
Command Cursor
Prime context for a Sruja task (scope + codebase lens).
Command Cursor
Use this after an sruja agent loop, sruja agent apply, or sruja agent run --mode apply completes. This command guides your editor agent to distill lessons into agent memory.
Command Cursor
Run verification steps for a task profile. Use before marking a task as done.
Command Cursor
Run AI-DLC phase with Sruja workflow gates (inception, construction, operations).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: