Loop Perf Prep — Development agent for Claude Code
Prepare lightweight performance checks (RPS/latency budget assertions) for the current loop iteration.
How to install Loop Perf Prep
Installs to ~/.claude/agents/maister-dev-maister-loop-perf-prep.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/maister-dev/maister/HEAD/.claude/agents/loop-perf-prep.md -o ~/.claude/agents/maister-dev-maister-loop-perf-prep.md Restart Claude Code, or start a new session, for it to be picked up.
What Loop Perf Prep does
name: loop-perf-prep description: Prepare lightweight performance checks (RPS/latency budget assertions) for the current loop iteration. Use proactively within /aif-loop in parallel with producer. tools: Read, Glob, Grep model: haiku permissionMode: plan background: true maxTurns: 4
You are perf-prep.
Input:
- task prompt
- phase
- plan
Output JSON only:
{ "checks": [], "notes": [] }
Rules:
- Prepare perf checks only.
- Keep checks concrete (
RPS,p95, budgets). - No b
Alternatives in Development
- Simple Code Reviewer — Lightweight code reviewer for quick quality checks 5.7k ★
- Review Prep — Aggregate performance review material from the vault for a given period 4.6k ★
- Spark — You are a lightweight implementation agent 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Loop Invariant Prep
Prepare invariant and consistency checks for the current loop iteration. Use proactively within /aif-loop in p
PR Prep
Use this agent when the user wants to prepare a pull request, review changes before PR submission, generate PR
Loop Evaluator
Evaluate artifact strictly against active loop criteria and return structured pass/fail output. Use proactivel
Tb Writer
Use when the user wants UVM 1.2 or SVA testbench files written for a generic FIFO or APB block — agents, seque
Review Sidecar
Reviews diff as an external reviewer with no memory of how the code was written. Catches tautological tests, m
Latency Scanner
Scans codebase for request latency issues including sequential async operations, payload sizes, middleware ove
Related Skills
Auto Swarm Nth
Nth-iteration agent swarm — spawns parallel agent waves, evaluates strictly per wave, re-swarms gaps until 100
AIGuardX
Loss prevention and policy enforcement for generative AI tools (ChatGPT, Gemini, Cursor, Claude, Copilot). Lig
Flow Discovery Track
Orchestrate Discovery Track flow to prepare validated requirements and designs one iteration ahead of delivery