
Temper
This is the antidote to over-engineering. It catches you when you've built a six-agent pipeline for what should be a single prompt, or abstracted a config system before writing any actual features. The best part is the Complexity Test: four questions that force you to justify every component, especially "would removing this break anything?" It's opinionated about what not to cut (error handling, logging, your golden test set) and what usually goes first (premature optimization, abstraction layers with one implementation). Pairs well with evaluate to prove you didn't sacrifice quality while simplifying. Honestly, most teams should run this before their first demo.
- skills.sh installs
- 336
- GitHub stars
- 602
- last updated
- Aug 21, 2026
Install
$ npx -y skills add sharpdeveye/maestro --skill temper --agent claude-codeInstalls into .claude/skills of the current project.
Files
MANDATORY PREPARATION
Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the agent-architecture reference in the agent-workflow skill for topology patterns and when multi-agent is justified.
Pull back from over-engineering. The most common mistake isn't building too little — it's building too much.
Over-Engineering Detection
Signs you've over-engineered:
- Multi-agent for a single-agent problem
- Premature optimization before you have performance data
- Abstraction layers with one implementation
- Configuration for things that never change
- Evaluation loops on non-critical outputs
- Framework before features
The Complexity Test
For each component:
- Is this solving a problem we actually have? (not "might have")
- Is this the simplest solution that works?
- Would removing this break anything? (if not, remove it)
- Can someone new understand this in 5 minutes? (if not, simplify)
Tempering Strategies
Collapse Unnecessary Agents
Sponsors
Details
- Repository
- github.com/sharpdeveye/maestro
- Category
- Automation & Workflows
- First seen
- Jun 3, 2026