菜单
Monitor MiniMax API usage, track session token counts, generate daily/weekly cost reports, and alert on budget thresholds for Hermes.
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。
基于 SOC 职业分类
| name | cost-monitor |
| version | 1.0.0 |
| description | Monitor MiniMax API usage, track session token counts, generate daily/weekly cost reports, and alert on budget thresholds for Hermes. |
| emoji | 💰 |
| tags | ["cost","monitoring","minimax","tokens","budget","api-usage","reports"] |
Track MiniMax API usage, session token counts, and generate cost reports for Hermes.
Running Hermes with MiniMax API key-based pricing can be opaque:
When triggered (via cron or manually), the skill:
Ask Hermes (or any agent with this skill):
"Give me a cost report for MiniMax API usage"
"How many sessions did I run today?"
"Am I going to hit my budget this week?"
"Show me TTS usage stats"
{
"name": "Daily Cost Report",
"schedule": { "kind": "cron", "expr": "0 20 * * *", "tz": "Europe/Berlin" },
"payload": {
"kind": "agentTurn",
"message": "Run a MiniMax cost report. Check session logs and usage data. Report: total sessions, avg context size, TTS calls, total tokens, estimated cost. Send summary to user."
},
"sessionTarget": "isolated",
"delivery": { "mode": "announce" }
}
{
"name": "Weekly Cost Summary",
"schedule": { "kind": "cron", "expr": "0 9 * * 1", "tz": "Europe/Berlin" },
"payload": {
"kind": "agentTurn",
"message": "Generate weekly cost summary for MiniMax API. Include: 7-day trend, daily averages, projected monthly cost, budget status."
},
"sessionTarget": "isolated",
"delivery": { "mode": "announce" }
}
When generating a report, use this structure:
## 💰 Hermes Cost Report — [Date]
### Session Overview
| Metric | Value |
|--------|-------|
| Sessions Today | 12 |
| Avg Context Size | 4.2K tokens |
| Total API Calls | 48 |
| TTS Calls | 23 |
### Token Usage Breakdown
| Type | Count | Est. Cost |
|------|-------|-----------|
| Text API (input) | 125K | — |
| Text API (output) | 89K | — |
| TTS (chars) | 12.5K | — |
| **Total** | 226K | Unknown* |
### Budget Status
- **Daily Budget:** $5.00 (warn at 80% = $4.00)
- **Current Spend:** ~$2.50 (50%)
- **Weekly Budget:** $30.00 (warn at 70% = $21.00)
- **Current Week:** ~$15.00 (50%)
### Trends
- Sessions: ↑ 12% from yesterday
- Avg context size: ↓ 5% from last week
- TTS usage: ↑ 8% from yesterday
### Recommendations
1. Consider reducing session context window for routine tasks
2. TTS usage is elevated — check if all calls are necessary
3. Enable context pruning for idle sessions
*Note: MiniMax M2.7 Plus has no public pricing. Cost estimation is based on API key billing.
Configure in your monitoring settings:
## Budget Alerts
- Daily budget: $5.00 (warn at 80% = $4.00)
- Weekly budget: $30.00 (warn at 70% = $21.00)
- Monthly budget: $100.00 (warn at 75% = $75.00)
- TTS daily max: 50,000 chars (warn at 80%)
If you have a DevOps/monitoring agent, add to its configuration:
## Cost Monitoring
- Run daily cost report at 20:00
- Alert if daily spend exceeds $4.00
- Weekly summary every Monday 09:00
- Track trends: is usage going up or down?
Located in ~/.hermes/scripts/cost_monitor/:
tracker.py — Tracks and stores usage metricsreporter.py — Generates daily/weekly reportsalerts.py — Checks thresholds and sends alertsconfig.py — Configuration management# Get current usage stats
python3 ~/.hermes/scripts/cost_monitor/tracker.py
# Generate daily report
python3 ~/.hermes/scripts/cost_monitor/reporter.py --period daily
# Generate weekly report
python3 ~/.hermes/scripts/cost_monitor/reporter.py --period weekly
# Check alerts
python3 ~/.hermes/scripts/cost_monitor/alerts.py
# Update configuration
python3 ~/.hermes/scripts/cost_monitor/config.py --set daily_budget=5.00
Q: How accurate are cost estimates? A: MiniMax M2.7 Plus has no public pricing. Estimates are based on observed API key billing patterns and should be treated as indicators, not exact figures.
Q: What data sources are used?
A: The tracker reads Hermes session logs (~/.hermes/sessions/) and any available usage telemetry.
Q: How do I set up alerts?
A: Configure thresholds in ~/.hermes/scripts/cost_monitor/config.json. Alerts are checked on each tracker run.
Q: Can I track historical data?
A: Yes, the tracker maintains a SQLite database at ~/.hermes/cost_data.db with historical usage.
Transforms the Hermes agent from a reactive question-answerer into a proactive autonomous executor. ARCHITECT takes any high-level goal, decomposes it into a dependency-aware task graph, executes each step with validation, self-corrects on failure, and delivers results — all without hand-holding. The missing execution layer for personal AI agents. Zero dependencies. Zero config. Works with any model. Pairs with apex-agent and agent-memoria for the complete autonomous agent stack.
Auto-reflective self-improvement skill — extracts learnings from corrections and success patterns, permanently encodes them into memory and skills. Philosophy: Correct once, never again.
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.
Integrate existing autonomous agents (like Hermes) into multi-agent orchestration platforms (AionUI, LangChain, etc.) via ACP over stdio.
MiniMax Agent Platform (agent.minimax.io) — MaxHermes, MaxClaw, Skills marketplace. Relacao com Hermes Agent (NousResearch) e OpenClaw.
Paperclip AI agent operations — creating agents with hierarchy, autonomous operation via hierarchical issues, and troubleshooting. Use when: creating agents, setting up org hierarchy, recovering from errors, or monitoring agent health.