agent loop commands

24 tagged agent loop, measured the same way as everything else here.

Browse within: AI Safety 10architecture 10rust-lang 10

ds

01

PsChina/deepseek-as-subagent

Command

A command that explicitly sends a coding task to a DeepSeek sub-agent, an additional AI worker, instead of letting the main agent decide whether to delegate it.

30 3d ago A 26 tokens original MIT

sruja-ai/sruja

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.

22 8d ago A 0 tokens original Apache-2.0

sruja-ai/sruja

Command Cursor

Structured review workflow before merging changes. Produces actionable feedback with architecture grounding.

22 8d ago A 0 tokens original Apache-2.0

sruja-ai/sruja

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.

22 8d ago A 0 tokens original Apache-2.0

harvest

08

Bogzx/seeks

Command

List finished + wound-down seeks loops with summary + branch diff for review.

4 15d ago A 15 tokens original MIT

start

09

Bogzx/seeks

Command

Arm and run a seeks loop (the most-recent one if no name given); refreshes a stale base on re-run.

4 15d ago A 26 tokens original MIT

why

10

Bogzx/seeks

Command

Replay why seeks allowed or denied an action — the loop's decision log.

4 15d ago A 15 tokens original MIT