Suggest Changes — Development skill for Claude Code
Analyze the agent-monitor debug logs and codebase to discover concrete improvements, fixes, and optimizations.
How to install Suggest Changes
Installs to ~/.claude/commands/roylet-gs-agent-monitor-suggest-changes.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/roylet-gs/agent-monitor/HEAD/.claude/commands/suggest-changes.md -o ~/.claude/commands/roylet-gs-agent-monitor-suggest-changes.md Restart Claude Code, or start a new session, for it to be picked up.
What Suggest Changes does
Analyze the agent-monitor debug logs and codebase to discover concrete improvements, fixes, and optimizations. Follow this structured process:
Step 1: Gather logs
Run `am logs --level debug --lines 500` to capture recent log output. If the log file is empty or too short, tell the user and ask them to run the TUI with active agents first, then retry.
Step 2: Identify patterns
Analyze the logs for these categories of issues:
- Performance problems: Repeated API calls, redundant DB w
Alternatives in Development
- Browser Tools MCP — Monitor browser logs directly from Cursor and other MCP compatible IDEs 7.2k ★
- Review Claudemd — Review recent conversations to find improvements for CLAUDE.md files 6.5k ★
- Om Prep 1on1 — Prep for an upcoming 1:1 — load person context, surface open items, suggest agenda based on vault state 4.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Retrospect
Analysis for a run and its results, process, suggestions for process improvements, process optimizations, fixe
Dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised wi
Review Local
Review current working tree changes (diff) and suggest fixes
Context Analyze
Analyze Claude Code context usage and suggest optimizations
Refresh Command
Turn your experience running a Writ command into concrete improvements to that command file. The learning loop
Daily Review
Once per day, read the last 24h of state and propose 1-3 concrete improvements. Don't just report — recommend.
Related Agents
Improver
Dispatched by self-improve, self-lint, self-perf, and refactor workflows to apply targeted code improvements (
Critic
You are a specialized code reviewer for features and implementations. Your job is to analyze code quality, ide
Diagnostics Agent
Analyze MCMC diagnostics from ArviZ output, identify convergence issues, and suggest fixes