Agent
brain
The main research brain. Reads RESEARCH.md, surveys literature, decomposes the goal into experiments, delegates each to an experiment agent (which handles…
Content
Agent
worker
Lightweight agent for independent tasks — reading papers, extracting data, downloading files, or any batch of independent work. Returns findings concisely.
Install
$ npx -y skills add Muuuun/luxas --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Lightweight agent for independent tasks — reading papers, extracting data, downloading files, or any batch of independent work. Returns findings concisely.
Agent definition
worker.mdname: worker
description: >
Lightweight agent for independent tasks — reading papers, extracting data,
downloading files, or any batch of independent work. Returns findings concisely.
model: sonnet
thinkingLevel: medium
toolSets: [coding]
spawn: { enabled: false }
templates: [PROJECT_DIR]You are a research worker agent. Complete the assigned task and return your findings clearly and concisely. Focus on extracting and reporting information, not on managing files.
Working directory: {{PROJECT_DIR}} All relative paths refer to this directory. When running bash commands, always cd to this directory first.
Ships withluxas
An autonomous research colleague — from a question to a compiled manuscript, while you sleep.
Get the whole plugin
Stats
1,059
Stars
18
Forks
Active
Maintenance
TypeScript
Language
MIT
License
9d ago
Last commit
5mo ago
Created
Repo: Muuuun/luxas
Other agents on luxas.
Agent
contradiction_auditor
Pre-finish contradiction sweep across the evidence store and the report. Extracts named physical quantities (same quantity, same conditions) from…
Agent
experiment
Research experiment orchestrator. Receives a task from brain, designs what tools/computations the answer needs, spawns impl + review sub-agents to build each…
Agent
experiment_reviewer
Adversarial per-experiment reviewer. Auto-spawned by the harness after an experiment agent completes. Reads the L2 section (matching EXPERIMENT_ID) in…
Agent
figure_auditor
Reads rendered figures with a vision model that can actually see, AFTER the deterministic lint has run, and reports what a referee would reject: claim not…