Catch Zendesk tickets about to breach SLA, and the escalations, every hour

Every business hour: Zendesk tickets that breached or will soon breach an SLA target, plus escalated tickets, and who takes each one.

Runs
Weekdays, hourly 9:00 to 18:00
Uses
Zendesk
Posts
Asks you

From your apps to your board

How the skill works: your agent reads open tickets with their slas from Zendesk; zendesk subdomain from What you tell it, weekdays, hourly 9:00 to 18:00, and gives you a question for you and a telegram ping and the report in the chat.

Reads

  • ZendeskOpen tickets with their SLAs
  • What you tell itZendesk subdomain
reads
Your agentClaude Code, Codex, Cursor or GeminiWeekdays, hourly 9:00 to 18:00
posts

You get

  • A question for youOn your board, answered with a tap
  • A Telegram pingOnly when it needs your answer, if you connect Telegram
  • The report in the chatEvery run, with or without Briefkin

What you get

  • Breached tickets, with the SLA target and how long ago it passed.
  • At risk: tickets that breach within the hour.
  • Escalated tickets and how long they have waited.
  • The ask: who takes the unassigned ones, or an all-clear when there are none.

The card on the right is a sample. Yours shows your own numbers and updates in place every run.

What lands on your board

Acme SupportZendesk SLA breaches and escalations · Claude Code

3 tickets breached SLA, 5 more within the hour

Who takes the 4 unassigned tickets?

3 tickets have breached their SLA and 5 will within 60 minutes. 2 escalated tickets are also waiting, one of them unassigned.

TicketSubjectTargetBreachAssignee
#48213Cannot export invoicesFirst reply42 min agoUnassigned
#48198SSO login loopNext reply18 min agoAna
#48230Charged twiceFirst reply5 min agoUnassigned
#48241API returns 500 errorsFirst replyIn 12 minUnassigned
#48176Data import stuckNext replyIn 25 minBen
#48244Change billing emailFirst replyIn 31 minBen
#48239Webhook not firingNext replyIn 44 minAna
#48250Add seats to planFirst replyIn 55 minChris
#48102Outage credit requestEscalatedWaiting 3 hUnassigned
#48155Contract terms questionEscalatedWaiting 1 hDana
Resolve
An example with made-up numbers. Your agent posts your real ones.

What it does

Zendesk shows an SLA badge on each ticket, but a view sorted by next breach only helps if someone is looking at it at the right moment. Support leads find out about a breach in the weekly report, after the customer has already noticed.

Every hour during the working day the agent lists the tickets whose SLA target has passed or will pass within the hour, adds the escalated tickets, and asks who takes the unassigned ones. When everything is on time, the card says so and stays quiet.

How it works

  1. 1Search open tickets with their SLAs

    Call GET /api/v2/search.json?query=type:ticket status<solved&include=tickets(slas), following next_page. Each ticket's slas.policy_metrics lists its targets with metric (such as first_reply_time or next_reply_time), stage and breach_at.

  2. 2

    2Sort breached from at risk

    A target with stage active and breach_at in the past is breached; one with breach_at within the next 60 minutes is at risk. Paused and achieved targets are left out. Sort by breach_at, oldest first.

  3. 3Add the escalations

    Run a second search, type:ticket status<solved tags:escalated (or the group, tag or priority:urgent your team uses), and keep the ones not already on the list, with how long each has waited.

  4. 4Ask, then assign

    Post the list as an ask when anything is breached, at risk or escalated without an owner. On an answer, set assignee_id with PUT /api/v2/tickets/{id} (or update_many for several). When nothing is at risk, post an all-clear instead.

  5. Post it to the board

    With BRIEFKIN_TOKEN set, the agent sends the result as one card that updates in place every run. Without it, you get the report in the chat.

Install and run it

Pick your agent, where the data comes from and how to schedule it; the commands below follow.

Agent
Data
Schedule
  1. Install the skill

    One command. It puts the SKILL.md in ~/.claude/skills and in ~/.agents/skills, which Codex, Cursor, Gemini CLI, Copilot CLI and OpenCode read too.

    shellcurl -fsSL https://briefkin.dev/skills/zendesk-sla-breaches/install | sh
  2. Run it

    Ask Claude Code:

    promptRun the zendesk-sla-breaches skill

    Or paste the prompt instead of installing:

    promptUsing the Zendesk API, search unsolved tickets with their SLA data (include=tickets(slas)). List tickets with an active SLA target whose breach_at has passed, then those breaching within the next 60 minutes, each with subject, target (first reply, next reply...), time to or since breach, and assignee. Add unsolved tickets tagged escalated with how long they have waited. Then ask me who should take the unassigned ones. Assign only after I answer.
  3. Put it on a schedule

    Weekdays, hourly 9:00 to 18:00, from cron on any machine where Claude Code is signed in:

    crontab0 9-18 * * 1-5 claude -p "Run the zendesk-sla-breaches skill"

    Add it with crontab -e. A laptop asleep at that time runs it when it wakes if you use launchd or Task Scheduler instead; GitHub Actions works for the API route.

  4. Send it to your board

    Connect Briefkin once with curl -fsSL https://briefkin.dev/install | sh and every run lands on your board as a question for you. How setup works

View the SKILL.mdRaw file
SKILL.md---
name: zendesk-sla-breaches
description: "Every business hour: Zendesk tickets that breached or will soon breach an SLA target, plus escalated tickets, and who takes each one. Use when the user asks for this, or when it runs on a schedule."
---

# Zendesk SLA breaches and escalations

Every business hour: Zendesk tickets that breached or will soon breach an SLA target, plus escalated tickets, and who takes each one.

Zendesk shows an SLA badge on each ticket, but a view sorted by next breach only helps if someone is looking at it at the right moment. Support leads find out about a breach in the weekly report, after the customer has already noticed.

Every hour during the working day the agent lists the tickets whose SLA target has passed or will pass within the hour, adds the escalated tickets, and asks who takes the unassigned ones. When everything is on time, the card says so and stays quiet.

## Two ways to get the data

Use the API or MCP route when you have an MCP server, a CLI or an API token for the app. Otherwise, if you can drive a browser the user is signed in to (Claude in Chrome, a Playwright or Chrome DevTools MCP server), use the browser route. Say which one you used.

## Route A: API or MCP server

### What you need

- A Zendesk agent account with an API token (`ZENDESK_EMAIL`, `ZENDESK_API_TOKEN` and your subdomain), or a Zendesk MCP server or connector with ticket read and update access.
- SLA policies set up in Zendesk, and how your team marks an escalation (tag, group or priority).

If something is missing, say what and stop; do not invent numbers.

### Steps

1. **Search open tickets with their SLAs** (Zendesk): Call `GET /api/v2/search.json?query=type:ticket status<solved&include=tickets(slas)`, following `next_page`. Each ticket's `slas.policy_metrics` lists its targets with `metric` (such as `first_reply_time` or `next_reply_time`), `stage` and `breach_at`.
2. **Sort breached from at risk**: A target with `stage` `active` and `breach_at` in the past is breached; one with `breach_at` within the next 60 minutes is at risk. Paused and achieved targets are left out. Sort by `breach_at`, oldest first.
3. **Add the escalations** (Zendesk): Run a second search, `type:ticket status<solved tags:escalated` (or the group, tag or `priority:urgent` your team uses), and keep the ones not already on the list, with how long each has waited.
4. **Ask, then assign** (Zendesk): Post the list as an ask when anything is breached, at risk or escalated without an owner. On an answer, set `assignee_id` with `PUT /api/v2/tickets/{id}` (or `update_many` for several). When nothing is at risk, post an all-clear instead.

## Route B: the browser

### What you need

- Signed in to Zendesk Support as an agent who can see the SLA views and change the assignee on tickets in those groups; the Next SLA breach column only appears on accounts with SLA policies.

If something is missing, say what and stop; do not invent numbers.

### Steps

Start at https://www.zendesk.com/login/. The user is signed in already; never type passwords or codes, and ask if a sign-in page appears.

1. **Open your agent workspace**: Enter your subdomain on the login page; sign-in is already done, so it opens `https://<subdomain>.zendesk.com/agent/`. Click **Views** in the left sidebar.
2. **Sort unsolved tickets by SLA**: Open a view of unsolved tickets (the default **All unsolved tickets**, or one your team uses) and click the **Next SLA breach** column header to sort by it. If the column is missing, an admin adds it under the view's **Formatting options**.
3. **Read breached and at-risk tickets**: Tickets whose SLA badge is red have breached; read the ticket number, subject, which target it is (first reply, next reply, or another) and how long ago. Then read the ones whose next breach is within 60 minutes, with the time left and the assignee.
4. **Add the escalations**: In the search box at the top, run `type:ticket status<solved tags:escalated` (or your team's group or `priority:urgent`), and note the escalated tickets not already on the list with how long each has waited.
5. **Assign only after an answer**: Report the list and ask who takes the unassigned tickets. After the answer, open each ticket, set **Assignee** in the left panel and click **Submit**. If nothing is breached, at risk or escalated without an owner, report an all-clear.

Note: Views show at most 30 tickets per page and the SLA badge rounds to minutes, so check the ticket itself when a breach is close. Paused targets (for example on pending tickets) show no badge and are left out, the same as in the API route.

## The report

- **Breached** tickets, with the SLA target and how long ago it passed.
- **At risk**: tickets that breach within the hour.
- **Escalated** tickets and how long they have waited.
- The ask: who takes the unassigned ones, or an all-clear when there are none.

## Post it to Briefkin

When `BRIEFKIN_TOKEN` is set, or `~/.config/briefkin/env` exists (the installer from https://briefkin.dev/docs writes it), also send the result to the user's Briefkin board as one card. Keep the `item_key` the same on every run so the card updates in place, use a new `event_id` per run, and put today's real numbers in place of the example ones. If the request fails, say so once and carry on.

```bash
[ -n "${BRIEFKIN_TOKEN:-}" ] || . ~/.config/briefkin/env
curl -sS -X POST "${BRIEFKIN_URL:-https://briefkin.dev}/v1/events" \
  -H "authorization: Bearer $BRIEFKIN_TOKEN" \
  -H "content-type: application/json" \
  -d @- <<'JSON'
{
  "v": 1,
  "event_id": "zendesk-sla-breaches/<date of this run, e.g. 2026-10-16>",
  "item_key": "zendesk-sla-breaches",
  "project": "Acme Support",
  "source": "Zendesk SLA breaches and escalations skill",
  "kind": "action",
  "title": "3 tickets breached SLA, 5 more within the hour",
  "summary": "**3 tickets** have breached their SLA and **5** will within 60 minutes. **2 escalated** tickets are also waiting, one of them unassigned.",
  "action": {
    "request": "Who takes the 4 unassigned tickets?",
    "options": [
      "Assign to the on-call agent",
      "Split across Tier 2",
      "I will take them",
      "Leave as is"
    ]
  },
  "widget": [
    {
      "type": "Table",
      "props": {
        "columns": [
          "Ticket",
          "Subject",
          "Target",
          "Breach",
          "Assignee"
        ],
        "align": [
          "left",
          "left",
          "left",
          "left",
          "left"
        ],
        "rows": [
          [
            "#48213",
            "Cannot export invoices",
            "First reply",
            "42 min ago",
            "Unassigned"
          ],
          [
            "#48198",
            "SSO login loop",
            "Next reply",
            "18 min ago",
            "Ana"
          ],
          [
            "#48230",
            "Charged twice",
            "First reply",
            "5 min ago",
            "Unassigned"
          ],
          [
            "#48241",
            "API returns 500 errors",
            "First reply",
            "In 12 min",
            "Unassigned"
          ],
          [
            "#48176",
            "Data import stuck",
            "Next reply",
            "In 25 min",
            "Ben"
          ],
          [
            "#48244",
            "Change billing email",
            "First reply",
            "In 31 min",
            "Ben"
          ],
          [
            "#48239",
            "Webhook not firing",
            "Next reply",
            "In 44 min",
            "Ana"
          ],
          [
            "#48250",
            "Add seats to plan",
            "First reply",
            "In 55 min",
            "Chris"
          ],
          [
            "#48102",
            "Outage credit request",
            "Escalated",
            "Waiting 3 h",
            "Unassigned"
          ],
          [
            "#48155",
            "Contract terms question",
            "Escalated",
            "Waiting 1 h",
            "Dana"
          ]
        ]
      }
    }
  ]
}
JSON
```

Widgets come from the Briefkin catalog (https://briefkin.dev/v1/catalog). Without a token, just give the user the report.

## Run it on a schedule

Suggested: Weekdays, hourly 9:00 to 18:00 (`0 9-18 * * 1-5`). From cron, with the agent signed in on that machine:

```bash
0 9-18 * * 1-5 claude -p "Run the zendesk-sla-breaches skill"
# Codex: codex exec, Gemini CLI: gemini -p, Copilot CLI: copilot -p, OpenCode: opencode run
```

Or use the agent's own scheduler (Claude Code routines, Codex automations, Claude or ChatGPT scheduled tasks): https://briefkin.dev/skills/zendesk-sla-breaches#schedule

Source: https://briefkin.dev/skills/zendesk-sla-breaches

What your agent needs

  • A Zendesk agent account with an API token (ZENDESK_EMAIL, ZENDESK_API_TOKEN and your subdomain), or a Zendesk MCP server or connector with ticket read and update access.

  • SLA policies set up in Zendesk, and how your team marks an escalation (tag, group or priority).

Connecting Zendesk

  1. MCP server. Zendesk doesn't list an official one; community MCP servers exist, and they need the same subdomain, email and API token as a direct API call.
  2. API with an API token. An admin enables token access in Admin Center under Apps and integrations > APIs and creates a token. The skill reads ZENDESK_SUBDOMAIN, ZENDESK_EMAIL and ZENDESK_API_TOKEN and sends basic auth as {email}/token:{token}.
  3. OAuth client. For a narrower credential, register an OAuth client in Admin Center and request the read scope.

An API token acts as the user who made it, with that agent's full rights; an OAuth token with only read can't update, assign or close tickets.

Questions

What counts as a breach?

An SLA target that is still active and whose breach_at time has passed. Targets that are paused (for example while a ticket is pending) and targets already achieved are left out, the same way Zendesk's own SLA badges treat them.

Will it alert me every hour?

The card updates in place every hour under the same item_key. When nothing is breached, at risk or escalated without an owner, the skill posts an all-clear update instead of an ask, so the card only asks for you when there is something to do.

Do I need Briefkin to use the Zendesk SLA breaches and escalations skill?

No. The skill runs with your own agent and gives you the report in the chat. With a Briefkin token set, each run also posts it to your board as a asks you, so you can glance at it instead of asking again.

Which agents can run it?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, OpenCode, Windsurf and Amp all read SKILL.md files. The install command puts it in ~/.claude/skills and ~/.agents/skills, where they look. ChatGPT, the Claude app and Grok take the prompt instead. Pick your agent under "Install and run it" and the commands change to match.

Can it work without an API or MCP server, from my browser?

Yes. Switch the data source to "Your browser" and the steps change to the Zendesk pages themselves: the agent opens www.zendesk.com/login in a browser you are signed in to and reads the numbers off the page. Claude Code, Codex, Cursor, Claude app and ChatGPT can drive a browser out of the box; Gemini CLI, Copilot CLI and OpenCode need a Playwright or Chrome DevTools MCP server first. It is slower than the API and needs you signed in, so it suits a report you run by hand or from a scheduler on your own computer.

Answer your agents from one board, or from Telegram

Skills are free to use with any agent. Briefkin is where their results land: one board for every report, number and question your agents send, with a ping when something needs you.

Free during the open beta. No card.