Agent Improver — Development agent for Claude Code
Use this agent to analyze agent performance, identify patterns in agent outputs, and generate improvement recommendations.
How to install Agent Improver
Installs to ~/.claude/agents/kentin0-fiz0l-claude-agents-agent-improver.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/kentin0-fiz0l/claude-agents/HEAD/.claude/agents/agent-improver.md -o ~/.claude/agents/kentin0-fiz0l-claude-agents-agent-improver.md Restart Claude Code, or start a new session, for it to be picked up.
What Agent Improver does
name: agent-improver description: Use this agent to analyze agent performance, identify patterns in agent outputs, and generate improvement recommendations. This meta-agent makes the agent ecosystem self-improving by learning from successes and failures.\n\n\nContext: User notices an agent could have performed better.\nuser: "The code-reviewer missed some obvious issues in my last review"\nassistant: "I'll use the agent-improver agent to analyze the code-reviewer's performance and s
Alternatives in Development
- Profiler — You are a specialized performance profiling agent 3.6k ★
- Context Engineering Kit — by Vlad Goncharov - Hand-crafted collection of advanced context engineering techniques and patterns with minim 679 ★
- PM — Use this agent when you need to identify, analyze, and propose new features or functionalities for the faker l 646 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Learner Diagnostic
Assesses learning approach across 5 dimensions from Justin Sung's methodology. Use when user wants to evaluate
Meta Performance
Campaign performance analyst. Analyzes spend, ROAS, CPA, CTR, CPM trends across campaigns, ad sets, and ads. D
Learning Adapter
Use this agent for dynamic improvement through experience and feedback. Specializes in continuous learning, st
Code Improvement Agent
Use this agent when you want to analyze and improve existing code for readability, performance, and best pract
Improver
Dispatched by self-improve, self-lint, self-perf, and refactor workflows to apply targeted code improvements (
Aro:Plan Reviewer
Reviews development plans against best practices, standards, and feasibility criteria. Evaluates technical dec
Related Skills
Weak Spot Hunter
Analyze Anki review data (exported stats, deck performance) to identify weak spots — cards with low retention,
Developer Growth Analysis
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for imp
Tokopt Upload
TokOpt — LLM Cost Intelligence Platform. Analyze LLM API logs to identify token waste and deliver actionable c