一键在 Manus 中运行任何 Skill

gptme-wrapped

星标1

分支0

更新时间2026年1月15日 21:08

Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns - inspired by Spotify Wrapped.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

HelixDevelopment

HelixDevelopment/HelixAgent

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

gptme Wrapped - Conversation Analytics

Description: Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns - inspired by Spotify Wrapped.

Overview

"gptme Wrapped" provides year-end (or any period) analytics for your gptme usage, similar to Spotify's annual Wrapped feature. It analyzes conversation logs stored locally to provide insights about:

Token usage: Input/output tokens, cache hits
Cost tracking: Spending by model, day, conversation
Model preferences: Most used models, provider breakdown
Usage patterns: Peak hours, conversation lengths, topics
Context efficiency: Average context sizes, compression ratios

Storage Structure

gptme stores conversations in ~/.local/share/gptme/logs/ with this structure:

~/.local/share/gptme/logs/
├── 2025-12-25-running-red-cat/
│   ├── conversation.jsonl    # Messages with metadata
│   ├── config.toml           # Conversation config (model, tools)
│   ├── branches/             # Conversation branches
│   └── workspace -> /path    # Symlink to workspace
└── ...

Message Format (conversation.jsonl)

Each line is a JSON object representing a message:

{
  "role": "assistant",
  "content": "...",
  "timestamp": "2025-12-25T22:47:40.922775",
  "metadata": {
    "model": "anthropic/claude-sonnet-4-20250514",
    "input_tokens": 33970,
    "output_tokens": 50,
    "cache_read_tokens": 30000,
    "cache_creation_tokens": 0,
    "cost": 0.0123
  }
}

Key metadata fields:

model: The model used for generation
input_tokens: Tokens sent to the model
output_tokens: Tokens generated by the model
cache_read_tokens: Tokens read from prompt cache (saves cost)
cache_creation_tokens: Tokens written to prompt cache
cost: Cost in USD (when available)

Note: Token metadata is only populated for assistant messages when the LLM API returns usage data. Historical conversations before this feature may not have metadata.

Config Format (config.toml)

[chat]
name = "Conversation Name"
model = "anthropic/claude-sonnet-4-20250514"
tools = ["shell", "ipython", "save", "patch", ...]
workspace = "~/Programming/project"

Best Practices

Wait for data accumulation: Metadata tracking is recent; 2026 will have fuller data.
Filter by year: Use timestamp filtering to focus on specific periods.
Handle missing metadata: Older conversations may not have token/cost data.
Consider local models: Token counts exist but costs are $0 for local models.
Cache efficiency varies: Depends on conversation patterns and model support.

Plugin Integration

See plugins/wrapped/ for the analytics plugin that provides:

wrapped_stats(year): Get comprehensive year stats
wrapped_report(year): Generate formatted ASCII report
wrapped_export(year, format): Export to HTML/JSON

Related Skills

Cost Tracking: Understanding gptme's cost tracking system
Context Management: Managing token usage efficiently
Model Selection: Choosing the right model for tasks

同仓库更多 Skills

同仓库

onboarding-agent

HelixDevelopment/HelixAgent

Interactive onboarding workflow that interviews users to understand their coding goals and generates PR-ready implementation plans. Use when starting a new development task to ensure clear requirements and structured execution.

2026-05-161

gamma-security-basics

HelixDevelopment/HelixAgent

Implement security best practices for Gamma integration. Use when securing API keys, implementing access controls, or auditing Gamma security configuration. Trigger with phrases like "gamma security", "gamma API key security", "gamma secure", "gamma credentials", "gamma access control".

2026-05-161

documentation

HelixDevelopment/HelixAgent

Write effective technical documentation including READMEs, API docs, architecture decisions, and inline code documentation.

2026-05-061

azure-devops

HelixDevelopment/HelixAgent

Build and manage CI/CD pipelines with Azure DevOps. Configure builds, releases, and automate software delivery workflows.

2026-04-021

azure-functions

HelixDevelopment/HelixAgent

Develop, deploy, and manage Azure Functions for serverless computing. Supports HTTP triggers, timers, queues, and event-driven architectures.

2026-04-021

azure-resource-management

HelixDevelopment/HelixAgent

Manage Azure resources effectively using CLI, Portal, Bicep, and ARM templates. Use for provisioning, organizing, and maintaining cloud infrastructure.

2026-04-021

name	gptme-wrapped
description	Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns - inspired by Spotify Wrapped.
version	1.0.0
category	analytics
allowed-tools	Read, Bash

gptme Wrapped - Conversation Analytics

Description: Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns - inspired by Spotify Wrapped.

Overview

"gptme Wrapped" provides year-end (or any period) analytics for your gptme usage, similar to Spotify's annual Wrapped feature. It analyzes conversation logs stored locally to provide insights about:

Token usage: Input/output tokens, cache hits
Cost tracking: Spending by model, day, conversation
Model preferences: Most used models, provider breakdown
Usage patterns: Peak hours, conversation lengths, topics
Context efficiency: Average context sizes, compression ratios

Storage Structure

gptme stores conversations in ~/.local/share/gptme/logs/ with this structure:

~/.local/share/gptme/logs/
├── 2025-12-25-running-red-cat/
│   ├── conversation.jsonl    # Messages with metadata
│   ├── config.toml           # Conversation config (model, tools)
│   ├── branches/             # Conversation branches
│   └── workspace -> /path    # Symlink to workspace
└── ...

Message Format (conversation.jsonl)

Each line is a JSON object representing a message:

{
  "role": "assistant",
  "content": "...",
  "timestamp": "2025-12-25T22:47:40.922775",
  "metadata": {
    "model": "anthropic/claude-sonnet-4-20250514",
    "input_tokens": 33970,
    "output_tokens": 50,
    "cache_read_tokens": 30000,
    "cache_creation_tokens": 0,
    "cost": 0.0123
  }
}

Key metadata fields:

model: The model used for generation
input_tokens: Tokens sent to the model
output_tokens: Tokens generated by the model
cache_read_tokens: Tokens read from prompt cache (saves cost)
cache_creation_tokens: Tokens written to prompt cache
cost: Cost in USD (when available)

Note: Token metadata is only populated for assistant messages when the LLM API returns usage data. Historical conversations before this feature may not have metadata.

Config Format (config.toml)

[chat]
name = "Conversation Name"
model = "anthropic/claude-sonnet-4-20250514"
tools = ["shell", "ipython", "save", "patch", ...]
workspace = "~/Programming/project"

Best Practices

Wait for data accumulation: Metadata tracking is recent; 2026 will have fuller data.
Filter by year: Use timestamp filtering to focus on specific periods.
Handle missing metadata: Older conversations may not have token/cost data.
Consider local models: Token counts exist but costs are $0 for local models.
Cache efficiency varies: Depends on conversation patterns and model support.

Plugin Integration

See plugins/wrapped/ for the analytics plugin that provides:

wrapped_stats(year): Get comprehensive year stats
wrapped_report(year): Generate formatted ASCII report
wrapped_export(year, format): Export to HTML/JSON

Related Skills

Cost Tracking: Understanding gptme's cost tracking system
Context Management: Managing token usage efficiently
Model Selection: Choosing the right model for tasks