Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add yedanyagamiai-cmd/openclaw-mcp-servers --skill openclaw-api-monitorgit clone --depth 1 https://github.com/yedanyagamiai-cmd/openclaw-mcp-serversWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-api-monitor)<a href="https://agentmods.dev/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-api-monitor"><img src="https://agentmods.dev/badge/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-api-monitor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-api-monitor"><img src="https://agentmods.dev/badge/skills/yedanyagamiai-cmd/openclaw-mcp-servers/openclaw-api-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00125 | $0.02662 |
| Opus 5 | $0.00063 | $0.01331 |
| Sonnet 5 | $0.00025 | $0.00532 |
| Haiku 4.5 | $0.00013 | $0.00266 |
Grade A, and why
openclaw-api-monitor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw API Monitor v2.0
API monitoring, cost tracking, and intelligent routing for AI providers. 5 tools. Real-time status. Budget alerts.
| Tool | Purpose | Free |
|---|---|---|
check_api_status |
Real-time status check for 20+ AI API providers | Yes |
get_usage_stats |
Token usage, call counts, and costs across all connected providers | Yes |
set_budget_alert |
Telegram alert when spending crosses a daily/monthly threshold | Pro |
get_cost_breakdown |
Detailed cost analysis by provider, model, and time period | Yes |
optimize_routing |
Recommend the best provider for a given task based on cost, speed, and availability | Yes |
What's New in v2.0
- APIWatch Engine -- Real-time status monitoring for 20+ AI providers using official status pages + synthetic probes every 2 minutes.
- CostLens -- Unified cost tracking across OpenAI, Anthropic, Groq, DeepInfra, and 16 more providers. See your true total AI spend in one number.
- SmartRoute -- Recommends the optimal provider for each task type based on current uptime, latency, rate limit headroom, and cost-per-token.
- BudgetGuard -- Hard and soft limits. Soft limit sends Telegram alert. Hard limit automatically routes calls away from the over-budget provider.
Quick Start
{
"openclaw-api-monitor": {
"type": "streamable-http",
"url": "https://openclaw-api-monitor-mcp.yagami8095.workers.dev/mcp"
}
}
Add to Claude Desktop, Cursor, Windsurf, VS Code, or any MCP-compatible client. Zero install. Works immediately.
Detection Triggers
This skill activates when a user says any of these:
- "is OpenAI down", "Anthropic API status", "check Groq", "provider status", "API outage"
- "how many tokens used", "API usage stats", "calls today", "usage this month", "token count"
- "alert at $50", "budget limit", "notify when spend hits", "API budget", "spending alert"
- "cost breakdown", "spending per provider", "GPT-4 cost", "API cost analysis", "cost per model"
- "cheapest model for this", "fastest API", "route to best provider", "optimize API selection"
- "rate limit", "rate limit remaining", "quota", "how many calls left today"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 212 lines · 125 tokens per session scan A 3a180bb7a9c1
openclaw-api-monitor is a skill published in the GitHub repository yedanyagamiai-cmd/openclaw-mcp-servers (3 stars, last pushed 5mo ago), licensed MIT. It adds 125 tokens to every session and 2,662 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
a-share-swing-sniper
A rule-based method for selecting Chinese stocks near the market close and deciding whether to trade or sell on the following day.
you-finance
Answer finance questions through the You.com you-finance MCP tool, with payment-aware fallbacks for keyless hosts.
search-deals
Search for free tiers, startup credits, and developer tool deals.
delegacion-local
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
class-management
Use when the user wants to create a new class, group, or course in Zooza — e.g. "set up a Monday yoga class", "add a new group", "schedule a course". Guides through programme selection, venue, trainer, session pattern, and commits.
feedback-nudge
Use when the user wants to report a bug, request a feature, or send feedback to the Zooza engineering team. Also offer proactively after a successful commit operation (max once per week).