← 返回 Skills 市场
dagangtj

AI Economic Tracker

作者 dagangtj · GitHub ↗ · v1.0.1
cross-platform ✓ 安全检测通过
445
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install ai-economic-tracker
功能描述
Track AI agents' daily finances, classify survival status, estimate service value, and recommend work or learn tasks based on economic runway.
使用说明 (SKILL.md)

AI Economic Tracker

Track daily costs, income, and net worth for AI agents. Implements economic pressure-driven decision making: "work or learn" based on financial runway.

Inspired by HKUDS/ClawWork research on economic incentives for AI agents.

Features

  • Balance Tracking: Monitor current balance, total income, and total costs
  • Survival Status: Automatic status classification (thriving/stable/struggling/critical/bankrupt)
  • Runway Calculation: Days remaining before funds run out
  • Service Valuation: Estimate task value using BLS wage data
  • Work/Learn Decision: Economic pressure-driven task prioritization
  • Daily Reports: Formatted economic status reports
  • JSONL Logs: Append-only transaction history

Use Cases

  1. Agent Cost Management: Track API costs, compute resources, and operational expenses
  2. Revenue Tracking: Log income from completed tasks or services
  3. Economic Decision Making: Decide whether to work (earn) or learn (invest) based on financial status
  4. Service Pricing: Estimate fair pricing using US Bureau of Labor Statistics wage data
  5. Financial Monitoring: Daily/weekly economic health checks

Installation

clawhub install ai-economic-tracker

Usage

Command Line

# View current status
python3 ~/.openclaw/workspace/skills/ai-economic-tracker/tracker.py status

# Daily report
python3 ~/.openclaw/workspace/skills/ai-economic-tracker/tracker.py report

# Initialize balance
python3 ~/.openclaw/workspace/skills/ai-economic-tracker/tracker.py init 1000.0

# Record income
python3 ~/.openclaw/workspace/skills/ai-economic-tracker/tracker.py income 50.0 "task_completion" "Completed data analysis"

# Record cost
python3 ~/.openclaw/workspace/skills/ai-economic-tracker/tracker.py cost 15.0 "api_usage" "OpenAI API calls"

# Estimate service value
python3 ~/.openclaw/workspace/skills/ai-economic-tracker/tracker.py estimate software_developer 2.5

# Get work/learn decision
python3 ~/.openclaw/workspace/skills/ai-economic-tracker/tracker.py decide

From OpenClaw Agent

# In your agent workflow
exec("python3 ~/.openclaw/workspace/skills/ai-economic-tracker/tracker.py report")

Cron Integration

Add to your OpenClaw cron for daily monitoring:

openclaw cron add "0 9 * * *" "python3 ~/.openclaw/workspace/skills/ai-economic-tracker/tracker.py report" --label "daily-economic-report"

Configuration

Set environment variables to customize:

# Data directory (default: ~/.openclaw/workspace/data/economics)
export ECONOMIC_TRACKER_DATA_DIR="/custom/path/to/data"

# Daily costs (default values shown)
export ECONOMIC_TRACKER_ELECTRICITY_DAILY=0.50
export ECONOMIC_TRACKER_INTERNET_DAILY=1.50

# Survival thresholds (default values shown)
export ECONOMIC_TRACKER_THRIVING=5000
export ECONOMIC_TRACKER_STABLE=1500
export ECONOMIC_TRACKER_STRUGGLING=500
export ECONOMIC_TRACKER_CRITICAL=0

Data Storage

All data stored in JSONL format (append-only):

  • balance.jsonl: Balance snapshots with timestamps
  • daily_log.jsonl: Cost transactions
  • income_log.jsonl: Income transactions

Default location: ~/.openclaw/workspace/data/economics/

Status Levels

Status Balance Range Meaning
🟢 Thriving > $5,000 Healthy runway, can invest in learning
🔵 Stable $1,500 - $5,000 Comfortable, balanced work/learn
🟡 Struggling $500 - $1,500 Low runway, prioritize income
🔴 Critical $0 - $500 Emergency mode, work only
💀 Bankrupt \x3C $0 Out of funds

BLS Wage Reference

Built-in hourly wage data for service valuation:

  • Computer Systems Manager: $90.38/hr
  • Financial Manager: $86.76/hr
  • Software Developer: $69.50/hr
  • Financial Analyst: $47.16/hr
  • Market Research: $38.71/hr
  • Data Analyst: $52.00/hr
  • General Operations: $64.00/hr
  • Customer Service: $22.00/hr

Work/Learn Decision Logic

The tracker implements economic pressure-driven decision making:

  • Critical/Struggling (\x3C $1,500): Must work to earn money
  • Stable ($1,500 - $5,000): 70% work, 30% learn
  • Thriving (> $5,000): 50% work, 50% learn

Use decide command to get recommendation based on current balance.

Example Output

📊 经济日报 | 2026-02-26
========================================
💰 余额: $1,234.56
📈 总收入: $2,500.00
📉 总支出: $1,265.44
💵 净利润: $1,234.56
🔥 日消耗: $2.00
⏳ 跑道: 617 天
🔵 状态: STABLE
========================================

Dependencies

Zero external dependencies. Uses only Python standard library:

  • json
  • os
  • datetime
  • pathlib

Security

  • No API keys required
  • All data stored locally
  • No network requests
  • Configurable via environment variables (no hardcoded paths)

Inspiration

Based on research from HKUDS/ClawWork on economic incentives for AI agents. Adapted for OpenClaw agent systems.

License

MIT

Author

OpenClaw Community

Version

1.0.0

安全使用建议
This skill appears coherent and low-risk: it stores data locally in ~/.openclaw/workspace/data/economics (or a custom path you set), requires no API keys, and makes no network calls. Before installing, consider: (1) confirm you are comfortable with JSONL transaction logs being written under your home directory, and (2) if you plan to have an agent call exec(...) to run the script, be aware that the agent will spawn a subprocess to run the CLI (normal for CLI skills). If either behavior is unacceptable, change the ECONOMIC_TRACKER_DATA_DIR or avoid autorunning the skill with cron/automated agent workflows.
功能分析
Type: OpenClaw Skill Name: ai-economic-tracker Version: 1.0.1 The OpenClaw AI Economic Tracker skill is benign. It adheres strictly to its stated purpose of tracking economic data for AI agents. The code confirms the `SKILL.md` claims of no external dependencies, no network requests, and local data storage. Input arguments are handled as data, not executed, preventing shell injection. There is no evidence of data exfiltration, malicious execution, persistence mechanisms beyond a benign daily report cron job (managed by OpenClaw), or prompt injection attempts against the agent.
能力评估
✓ Purpose & Capability
Name/description match the included tracker.py and SKILL.md: the skill tracks balance, logs income/costs, estimates service value from built-in wage data, and recommends work/learn decisions. No unrelated privileges (cloud credentials, network access) are requested.
ℹ Instruction Scope
SKILL.md instructs running the bundled tracker.py (CLI examples, cron entry, and an example exec() call from an agent). Those instructions run only the local script which reads/writes JSONL files in the specified data directory and reads optional environment variables. The exec() example asks the agent to run a shell command — this is expected for a CLI skill but means the agent will execute a subprocess when invoked.
✓ Install Mechanism
No install spec is provided (instruction-only install). Files are present in the package but nothing is downloaded or extracted at install time. tracker.py uses only Python standard library.
✓ Credentials
No required environment variables or secrets. Several optional ENV vars control data location and thresholds which are proportional to the skill's configuration needs. No credentials or unrelated service keys are requested.
✓ Persistence & Privilege
The skill is not always-enabled, can be invoked by the user/agent, and only writes to its own data directory (default under ~/.openclaw/workspace/data/economics). It does not modify other skills or system-wide configs.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install ai-economic-tracker
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /ai-economic-tracker 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
Bug fixes and macOS compatibility improvements
v1.0.0
AI Economic Tracker 1.0.0 – Initial release - Track daily costs, income, and net worth for AI agents - Automatic economic status classification and runway calculation - Service value estimation using built-in BLS wage data - Economic pressure-driven work/learn decision-making logic - Append-only JSONL transaction logs and daily formatted reports - Fully local, zero dependencies beyond Python standard library
元数据
Slug ai-economic-tracker
版本 1.0.1
许可证 —
累计安装 1
当前安装数 1
历史版本数 2
常见问题

AI Economic Tracker 是什么？

Track AI agents' daily finances, classify survival status, estimate service value, and recommend work or learn tasks based on economic runway. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 445 次。

如何安装 AI Economic Tracker？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-economic-tracker」即可一键安装，无需额外配置。

AI Economic Tracker 是免费的吗？

是的，AI Economic Tracker 完全免费（开源免费），可自由下载、安装和使用。

AI Economic Tracker 支持哪些平台？

AI Economic Tracker 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 AI Economic Tracker？

由 dagangtj（@dagangtj）开发并维护，当前版本 v1.0.1。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论