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.
git clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWrote 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/commands/parkerm2/create-claude-workflow/alert-to-ticket)<a href="https://agentmods.dev/commands/parkerm2/create-claude-workflow/alert-to-ticket"><img src="https://agentmods.dev/badge/commands/parkerm2/create-claude-workflow/alert-to-ticket.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.04026 |
| Opus 5 | $0.00008 | $0.02013 |
| Sonnet 5 | $0.00003 | $0.00805 |
| Haiku 4.5 | $0.00002 | $0.00403 |
Grade A, and why
alert-to-ticket scanned grade A with 2 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(url); Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
const deploys = execSync( How it starts
The opening of the file, as written. The whole thing — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alert-to-Ticket Automation
Converts monitoring alerts (text, URL, or structured) into properly formatted Jira tickets. Enriches with context (past incidents, recent deploys), maps severity, and links to runbooks and related tickets.
Usage
/alert-to-ticket [<alert-description>] [--url <url>] [--json <file>] [--service <name>] [--severity <level>] [--dry-run]
<alert-description>: Paste alert text directly--url <url>: Fetch alert from monitoring dashboard--json <file>: Parse structured alert JSON--service <name>: Override service detection--severity <level>: Override auto-detected severity--dry-run: Preview ticket without creating
Workflow
Phase 1: Alert Intake & Parsing
Ingests alert data from multiple sources and extracts key information.
class AlertParser {
constructor() {
this.alert = {
service: null,
metric: null,
threshold: null,
currentValue: null,
timestamp: new Date(),
environment: "production",
message: "",
source: null
};
}
async parseInput(input, url, jsonFile) {
if (jsonFile) {
return this.parseJSON(jsonFile);
}
if (url) {
return this.parseFromURL(url);
}
if (input) {
return this.parseText(input);
}
throw new Error("No alert input provided");
}
parseText(text) {
// Extract common alert patterns
const patterns = {
service: /(?:Service|Alert|Service Name):\s*([^\n,]+)/i,
metric: /(?:Metric|Condition):\s*([^\n,]+)/i,
threshold: /(?:Threshold|Trigger|Limit):\s*([\d.]+[a-z%]*)/i,
currentValue: /(?:Current|Actual|Value):\s*([\d.]+[a-z%]*)/i,
timestamp: /(?:Time|Occurred|Triggered):\s*([^\n,]+)/i,
environment: /(?:Environment|Env):\s*([\w-]+)/i
};
for (const [key, pattern] of Object.entries(patterns)) {
const match = text.match(pattern);
if (match) {
this.alert[key] = match[1];
}
}
// Fallback: look for common service names
if (!this.alert.service) {
const serviceMatch = text.match(/\b(api|web|database|cache|queue|scheduler|worker)\b/i);
if (serviceMatch) this.alert.service = serviceMatch[1];
}
this.alert.message = text;
this.alert.source = "text";
return this.alert;
}
async parseFromURL(url) {
try {
const response = await fetch(url);
const html = await response.text();
// Extract alert data from HTML (Datadog, New Relic, etc.)
const serviceMatch = html.match(
/<span[^>]*class="[^"]*service[^"]*"[^>]*>([^<]+)<\/span>/i
);
const metricMatch = html.match(
/<span[^>]*class="[^"]*metric[^"]*"[^>]*>([^<]+)<\/span>/i
);
const valueMatch = html.match(/(?:Value|Current):\s*([\d.]+)/);
if (serviceMatch) this.alert.service = serviceMatch[1].trim();
if (metricMatch) this.alert.metric = metricMatch[1].trim();
if (valueMatch) this.alert.currentValue = valueMatch[1];
this.alert.message = html;
this.alert.source = url;
console.log(`✓ Parsed alert from URL: ${url}`);
return this.alert;
} catch (err) {
console.error(`ERROR: Failed to fetch alert from URL: ${err.message}`);
return gracefulFailure("Unable to fetch alert from URL");
}
}
parseJSON(jsonFile) {
try {
const data = JSON.parse(fs.readFileSync(jsonFile, "utf-8"));
// Map common alert JSON structures
this.alert.service = data.service || data.serviceName || data.source || null;
this.alert.metric = data.metric || data.check || data.condition || null;
this.alert.currentValue = data.value || data.currentValue || null;
this.alert.threshold = data.threshold || data.limit || null;
this.alert.environment = data.environment || data.env || "production";
this.alert.timestamp = new Date(data.timestamp || new Date());
this.alert.message = JSON.stringify(data, null, 2);
this.alert.source = jsonFile;
console.log(`✓ Parsed structured alert from ${jsonFile}`);
return this.alert;
} catch (err) {
console.error(`ERROR: Failed to parse JSON alert: ${err.message}`);
return gracefulFailure("Invalid JSON alert file");
}
}
validate() {
if (!this.alert.service) {
throw new Error("Could not determine service from alert; use --service");
}
if (!this.alert.metric && !this.alert.message) {
throw new Error("No metric or message found in alert");
}
return true;
}
}
const parser = new AlertParser();
const alert = await parser.parseInput(
argv._[0], // positional text arg
argv.url,
argv.json
);
parser.validate();
console.log(`✓ Alert parsed`);
console.log(` Service: ${alert.service}`);
console.log(` Metric: ${alert.metric || "(not specified)"}`);
console.log(` Value: ${alert.currentValue || "(not specified)"}`);
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.
- 6d ago First seen · 578 lines · 15 tokens per session scan A 0d78d70eda52
alert-to-ticket is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 4,026 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.