api-monitoring-bots

api-monitoring-bots is a skill for Claude Code, Codex from kevinnft/ai-agent-skills. It costs 28 tokens per session (5,400 once invoked), scanned B, original, MIT.

A pattern for bots that repeatedly check an application programming interface, or API, and notify you when tracked data changes. An API is a programmed way for one service to provide data to another.

In plain words
What is it for?
Watching for new items, price changes, threshold crossings, and service-status transitions while storing the previous state for comparison.
Why use it?
It avoids manual checking and keeps notifications quiet when nothing has changed.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: built for hermes-agent.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/ubuntu/.hermes/scripts/monitor_realtime.py.

Good fit Watching for new items, price changes, threshold crossings, and service-status transitions while storing the previous state for comparison.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for api-monitoring-bots

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/api-monitoring-bots/github.svg)](https://agentmods.dev/skills/kevinnft/ai-agent-skills/api-monitoring-bots)
Your own site
<a href="https://agentmods.dev/skills/kevinnft/ai-agent-skills/api-monitoring-bots"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/api-monitoring-bots/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.

agentmods 80×15 button for api-monitoring-bots

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevinnft/ai-agent-skills/api-monitoring-bots"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/api-monitoring-bots.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.05400
Opus 5 $0.00014 $0.02700
Sonnet 5 $0.00006 $0.01080
Haiku 4.5 $0.00003 $0.00540

Measured 12d ago against content hash 94982f8760df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

api-monitoring-bots scanned grade B with 3 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo nano /etc/systemd/system/api-monitor.service

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

r = requests.get(API_URL, timeout=10)

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run(["hermes", "send", "-t", chat_id, "-m", message])
skills/devops/api-monitoring-bots/SKILL.md · 756 lines

How it starts

The opening of the file, as written. The whole thing — 756 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API Monitoring Bots

Build lightweight monitoring bots that poll REST APIs and send notifications when state changes (new items, price alerts, status updates).

When to Use

  • User wants notifications for new listings/posts/items
  • Need to track price changes or threshold alerts
  • Monitor API for specific conditions
  • Watchdog for service status changes

Architecture Pattern

Stateful polling bot:

  1. Fetch current state from API
  2. Compare with last known state (stored in file)
  3. Detect changes (new IDs, price deltas, status transitions)
  4. Format and send notifications
  5. Update state file

Key principle: Silent when no changes (watchdog pattern, no spam).

Implementation

1. Core Script Structure

#!/usr/bin/env python3
import requests
import json
from pathlib import Path
from datetime import datetime

API_URL = "https://api.example.com/items"
STATE_FILE = Path.home() / ".hermes" / "monitor_state.json"

def load_state():
    """Load last seen state"""
    if STATE_FILE.exists():
        with open(STATE_FILE) as f:
            return json.load(f)
    return {"seen_ids": [], "last_check": None}

def save_state(state):
    """Save current state"""
    STATE_FILE.parent.mkdir(parents=True, exist_ok=True)
    with open(STATE_FILE, "w") as f:
        json.dump(state, f, indent=2)

def fetch_items():
    """Fetch current items from API"""
    try:
        r = requests.get(API_URL, timeout=10)
        r.raise_for_status()
        return r.json()
    except Exception as e:
        return None

def check_new_items():
    """Check for new items and return notifications"""
    state = load_state()
    items = fetch_items()
    
    if not items:
        return []
    
    seen_ids = set(state["seen_ids"])
    new_items = []
    
    for item in items:
        if item["id"] not in seen_ids:
            new_items.append(item)
            seen_ids.add(item["id"])
    
    # Update state (keep last 1000 IDs to prevent bloat)
    state["seen_ids"] = list(seen_ids)[-1000:]
    state["last_check"] = datetime.now().isoformat()
    save_state(state)
    
    return new_items

# Initialize state on first run (don't notify)
state = load_state()
if not state["seen_ids"]:
    items = fetch_items()
    if items:
        state["seen_ids"] = [item["id"] for item in items]
        state["last_check"] = datetime.now().isoformat()
        save_state(state)
        print(f"Initialized with {len(state['seen_ids'])} existing items")

# Check for new items
new_items = check_new_items()

if new_items:
    for item in new_items:
        print(format_notification(item))
# Silent when no new items (watchdog pattern)

Read the full file on GitHub · 756 lines

Changes

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.

  1. 12d ago First seen · 756 lines · 28 tokens per session scan B 94982f8760df

Subscribe to this mod's changes

api-monitoring-bots is a skill published in the GitHub repository kevinnft/ai-agent-skills (14 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 5,400 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

tactical-ddd

Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object', 'repository', 'bounded context', 'domain event', 'domain service', code touching domain/ directories, rich domain model…

NoesisVision/nasde-toolkit · 70 tokens

convex-cron-jobs

Scheduled function patterns for background tasks including interval scheduling, cron expressions, job monitoring, retry strategies, and best practices for long-running tasks.

waynesutton/convexskills · 33 tokens

csharp-api-controller-standards

Defines the coding standards, patterns, and conventions for ASP.NET Core REST API controllers. Rules cover routing, HTTP verbs, response types, XML documentation, dependency injection, and asynchronous execution. Apply these rules uniformly to ensure a consistent, predictable, and well-documented API surface.

linuxchata/ai-playbook · 63 tokens

n8n-trigger-testing-strategies

Webhook testing, schedule validation, event-driven triggers, and polling mechanism testing for n8n workflows. Use when testing how workflows are triggered.

summarybotng/summarybot-ng · 37 tokens

060103-better-auth

Better Auth integration for Next.js — setup, API endpoints, client SDK, React Context provider, and Organization plugin for multi-tenant auth.

natuleadan/skills · 34 tokens

070101-prisma-database

Prisma 7 setup with PostgreSQL driver adapters and Better Auth schema models (User, Session, Account, Verification).

natuleadan/skills · 31 tokens