Agent
Extends the core team with specialists when the goal benefits from domain expertise beyond what the generic agents provide. Runs once after the planner. Never executes the goal itself.
3 1mo ago A 37 tokens
3Stars on the repository
29Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
auditor
02Agent
Catches problems the verifier wouldn't — things that work but aren't done the right way. Uses researcher-defined quality standards to judge output. Non-blocking unless critical.
3 1mo ago A 35 tokens
executor
03Agent
Completes exactly one task and moves the loop forward. Derives execution method from the goal and researcher findings. Output goes to the project directory, never inside loop-stack. Never marks tasks complete.
3 1mo ago A 41 tokens
Agent
This is a reference for the researcher agent. Read the goal and current task, identify which categories apply, then pull sources from those sections only. Ignore irrelevant categories — don't load noise.
3 1mo ago A 0 tokens
Agent
Makes the loop smarter over time by capturing what was learned. Runs after each auditor pass.
3 1mo ago A 22 tokens
planner
06Agent
Turns the goal and research findings into a clear, executable task plan. Runs once after researcher and resource-scout during loop startup. Never executes the goal itself.
3 1mo ago A 34 tokens
researcher
07Agent
Maps what's known, what's needed, and what could go wrong before the executor acts. Also surfaces existing tools, MCPs, skills, and libraries that eliminate work. Writes structured findings for executor and verifier/auditor. Runs before every executor pass. Never executes the goal itself.
3 1mo ago A 59 tokens
Agent
Maps everything available and connected in this environment before the loop starts. Provides exact usage syntax for every resource found. Runs once at loop start. Writes loop-stack/TOOLS.md. Never executes the goal itself.
3 1mo ago B 45 tokens
Agent
Extends the core team with specialists when the goal benefits from domain expertise beyond what the generic agents provide. Runs once after the planner. Never executes the goal itself.
3 1mo ago A 40 tokens
Agent
Catches problems the verifier wouldn't — things that work but aren't done the right way. Uses researcher-defined quality standards to judge output. Non-blocking unless critical.
3 1mo ago A 39 tokens
Agent
Completes exactly one task and moves the loop forward. Derives execution method from the goal and researcher findings. Output goes to the project directory, never inside loop-stack. Never marks tasks complete.
3 1mo ago A 45 tokens
Agent
Makes the loop smarter over time by capturing what was learned. Runs after each auditor pass.
3 1mo ago A 25 tokens
Agent
Turns the goal and research findings into a clear, executable task plan. Runs once after researcher and resource-scout during loop startup. Never executes the goal itself.
3 1mo ago A 38 tokens
Agent
Maps what's known, what's needed, and what could go wrong before the executor acts. Also surfaces existing tools, MCPs, skills, and libraries that eliminate work. Writes structured findings for executor and verifier/auditor. Runs before every executor pass. Never executes the goal itself.
3 1mo ago A 63 tokens
Agent
Maps everything available and connected in this environment before the loop starts. Provides exact usage syntax for every resource found. Runs once at loop start. Writes loop-stack/TOOLS.md. Never executes the goal itself.
3 1mo ago A 48 tokens
Agent
Checks output against researcher-defined criteria, then runs the stop condition. Marks tasks done or failed. Never writes application code.
3 1mo ago A 30 tokens