Agent Report — Development skill for Claude Code
Where the tokens go - main conversation vs subagents, by effort level and by role.
How to install Agent Report
Installs to ~/.claude/skills/danielcurly-danielcurly-claude-code-suite-agent-report/SKILL.md
mkdir -p ~/.claude/skills/danielcurly-danielcurly-claude-code-suite-agent-report && curl -fsSL https://raw.githubusercontent.com/Danielcurly/danielcurly-claude-code-suite/HEAD/commands/agent-report.md -o ~/.claude/skills/danielcurly-danielcurly-claude-code-suite-agent-report/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Agent Report does
description: Where the tokens go - main conversation vs subagents, by effort level and by role argument-hint: "[--days N | --since YYYY-MM-DD] [--project name]" allowed-tools: Bash(node:*) disable-model-invocation: true
!`node "__CLAUDE_DIR__/agent-report.js" $ARGUMENTS`
The user ran /agent-report. The report above comes from Claude Code's own transcripts, priced at API rates as a stand-in for quota. Explain it to the user in plain words and briefly: where most of the cost goes, what t
Alternatives in Development
- Agent.System.Main.Communication — Communication 19k ★
- Analyze Feature Requests — Prioritize feature requests by theme, impact, effort, and risk 7.8k ★
- 01 Main System Prompt — Main System Prompt 2.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Diagnose Usage
Claude Code skill that works out why your usage limit drained fast. Reads your /usage paste, checks the heavy-
History Compressor
You are a conversation history compressor for Omux's Main Agent.
Delegate First
Keep the main conversation clean by forking implementation work to sub-agents. Use when you want ongoing conve
Detailed Planning Agent
You are an expert detailed planning agent specializing in converting coarse implementation tasks into step-by-
Report 3D Showcase
Claude Code skill: turn a report script into a local 3D interactive presentation (Blender GLB + three.js main.
Review Team
Run review-team skill: parallel multi-role review with consensusLevel and Tech Lead report
Related Agents
Codex Run
Runs a Codex job through the codex-run skill scripts and returns only the final report, so the launch, polling
Main
Mercury orchestrator role definition. NOT meant to be spawned as a sub-agent — this file documents the behavio
Conversation Compacter
Compacts long conversations into ~300 token summaries preserving critical context, todos, file paths, and deci