See how long Jira issues spend in each status, week by week

Every Monday: the average time Jira issues spent in each status last week, the issues waiting longest in each one, and the status that slowed down.

Runs
Mondays at 9:00
Uses
Jira
Posts
Report card

From your apps to your board

How the skill works: your agent reads issues that moved from Jira; jira projects from What you tell it, mondays at 9:00, and gives you report card and the report in the chat.

Reads

  • JiraIssues that moved
  • What you tell itJira projects
reads
Your agentClaude Code, Codex, Cursor or GeminiMondays at 9:00
posts

You get

  • Report cardOn your board, updated in place every run
  • The report in the chatEvery run, with or without Briefkin

What you get

  • Average time in each status last week, with the change on the week before.
  • Longest current wait in each status, with the issue and assignee.
  • Stints ended per status, as a measure of flow.
  • One line on the status that slowed down, for example "In Review up from 1.9 to 2.8 days".

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

What lands on your board

AcmeJira time in status report · Claude Code

Code review waits grew to 2.8 days

Issues spent an average of 2.8 days in In Review last week, up from 1.9. ACME-482 has been waiting there for 9 days.

To Do4.1 days
In Progress2.3 days
In Review2.8 days
QA1.2 days
Blocked3.5 days
StatusAvg daysvs last weekLeft statusLongest now
To Do4.1-0.331ACME-455, 21 days
In Progress2.3+0.128ACME-470, 8 days
In Review2.8+0.924ACME-482, 9 days
QA1.2-0.219ACME-488, 4 days
Blocked3.5+0.44ACME-431, 12 days

6 issues waited more than 4 days in review, and 5 of them were assigned to the same two reviewers.

Done
An example with made-up numbers. Your agent posts your real ones.

What it does

Cycle time says work is slow; time in status says where. Jira Cloud shows days in column on board cards, but the full picture across a project usually takes a marketplace app or an afternoon with a changelog export.

Every Monday the agent reads the status history of every issue that moved, works out how long each one sat in each status, and reports the averages and the longest waits. Product managers and engineering leads see that review grew from 1.9 to 2.8 days, and which issues are sitting there right now.

How it works

  1. 1Find the issues that moved

    Call GET /rest/api/3/search/jql with jql=project = ACME AND (status CHANGED DURING (-7d, now()) OR statusCategory = "In Progress"), fields=summary,status,assignee,issuetype and maxResults=100, following nextPageToken.

  2. 2Pull their status history

    Call POST /rest/api/3/changelog/bulkfetch with up to 1,000 keys in issueIdsOrKeys and fieldIds: ["status"], following nextPageToken. Each history entry has created and items with fromString and toString. An Atlassian MCP server may offer a per-issue changelog tool instead; the bulk endpoint is the one that scales.

  3. 3

    3Work out each stint

    Turn the transitions into stints: entered a status at one timestamp, left it at the next. Stints that ended in the last 7 days give the average per status; stints still open give the longest current waits. Count calendar time unless working days were asked for.

  4. 4

    4Compare and write

    Save the averages to a JSON file and compare with last week. Write one row per status (average, stints that ended, longest open wait and its issue), then name the status whose average grew most.

  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/jira-time-in-status-report/install | sh
  2. Run it

    Ask Claude Code:

    promptRun the jira-time-in-status-report skill

    Or paste the prompt instead of installing:

    promptUsing the Jira Cloud REST API, find the issues in project ACME whose status changed in the last 7 days or that are in progress now. Fetch their status changelogs (POST /rest/api/3/changelog/bulkfetch with fieldIds ["status"]), and work out how long each issue spent in each status. For stints that ended in the last 7 days, give me the average time per status; for stints still open, the longest current wait per status with its issue key. Compare with last week if you have it, and tell me which status slowed down the most.
  3. Put it on a schedule

    Mondays at 9:00, from cron on any machine where Claude Code is signed in:

    crontab0 9 * * 1 claude -p "Run the jira-time-in-status-report 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 report card. How setup works

View the SKILL.mdRaw file
SKILL.md---
name: jira-time-in-status-report
description: "Every Monday: the average time Jira issues spent in each status last week, the issues waiting longest in each one, and the status that slowed down. Use when the user asks for this, or when it runs on a schedule."
---

# Jira time in status report

Every Monday: the average time Jira issues spent in each status last week, the issues waiting longest in each one, and the status that slowed down.

Cycle time says work is slow; time in status says where. Jira Cloud shows days in column on board cards, but the full picture across a project usually takes a marketplace app or an afternoon with a changelog export.

Every Monday the agent reads the status history of every issue that moved, works out how long each one sat in each status, and reports the averages and the longest waits. Product managers and engineering leads see that review grew from 1.9 to 2.8 days, and which issues are sitting there right now.

## 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

- Browse permission on the projects, through an Atlassian API token with your email (`JIRA_EMAIL`, `JIRA_API_TOKEN`) or the Atlassian Rovo MCP server.
- Which projects or board filter to measure, and whether to count calendar or working days.

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

### Steps

1. **Find the issues that moved** (Jira): Call `GET /rest/api/3/search/jql` with `jql=project = ACME AND (status CHANGED DURING (-7d, now()) OR statusCategory = "In Progress")`, `fields=summary,status,assignee,issuetype` and `maxResults=100`, following `nextPageToken`.
2. **Pull their status history** (Jira): Call `POST /rest/api/3/changelog/bulkfetch` with up to 1,000 keys in `issueIdsOrKeys` and `fieldIds: ["status"]`, following `nextPageToken`. Each history entry has `created` and items with `fromString` and `toString`. An Atlassian MCP server may offer a per-issue changelog tool instead; the bulk endpoint is the one that scales.
3. **Work out each stint**: Turn the transitions into stints: entered a status at one timestamp, left it at the next. Stints that ended in the last 7 days give the average per status; stints still open give the longest current waits. Count calendar time unless working days were asked for.
4. **Compare and write**: Save the averages to a JSON file and compare with last week. Write one row per status (average, stints that ended, longest open wait and its issue), then name the status whose average grew most.

## Route B: the browser

### What you need

- Signed in to Atlassian with Browse projects permission on the project and access to the board; the Control chart exists on company-managed (Scrum and Kanban) boards.

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

### Steps

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

1. **Open the board's Control chart**: Jira URLs include your site, so start at start.atlassian.com, open the Jira site, then the project's board and **Reports > Control chart**. Set the time range to the last 7 days (the **Last week** quick filter or a custom range) and, under **Columns**, tick one column at a time.
2. **Read the average per status**: With one column selected, the chart's rolling average line and the summary give the average time issues spent in that status for stints that ended in the range, and the count of issues that left it. Repeat for each column and write one row per status.
3. **Find the longest current waits**: Open **Filters > View all issues**, run `project = ACME AND status = "In Review" ORDER BY updated ASC` for each status, open the top issue and read the **History** tab for the date it entered the status. The board itself also shows days in column as dots on each card.
4. **Compare and write**: Change the Control chart range to the week before and read the same averages, so each row has its change. Name the status whose average grew most and the issues sitting in it now.

Note: The Control chart is only on company-managed boards; team-managed projects have a Cycle time report that measures start to done, not time per status, so there this route is a stopgap and the API or a marketplace time-in-status app does the job. Control chart averages follow the board's column mapping, so a status that sits in no column does not appear.

## The report

- **Average time in each status** last week, with the change on the week before.
- **Longest current wait** in each status, with the issue and assignee.
- **Stints ended** per status, as a measure of flow.
- One line on the status that slowed down, for example "In Review up from 1.9 to 2.8 days".

## 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": "jira-time-in-status-report/<date of this run, e.g. 2026-10-16>",
  "item_key": "jira-time-in-status-report",
  "project": "Acme",
  "source": "Jira time in status report skill",
  "kind": "update",
  "title": "Code review waits grew to 2.8 days",
  "summary": "Issues spent an average of **2.8 days** in **In Review** last week, up from 1.9. ACME-482 has been waiting there for 9 days.",
  "widget": [
    {
      "type": "Bars",
      "props": {
        "unit": "days",
        "items": [
          {
            "label": "To Do",
            "value": 4.1
          },
          {
            "label": "In Progress",
            "value": 2.3
          },
          {
            "label": "In Review",
            "value": 2.8
          },
          {
            "label": "QA",
            "value": 1.2
          },
          {
            "label": "Blocked",
            "value": 3.5
          }
        ]
      }
    },
    {
      "type": "Table",
      "props": {
        "columns": [
          "Status",
          "Avg days",
          "vs last week",
          "Left status",
          "Longest now"
        ],
        "align": [
          "left",
          "right",
          "right",
          "right",
          "left"
        ],
        "rows": [
          [
            "To Do",
            4.1,
            "-0.3",
            31,
            "ACME-455, 21 days"
          ],
          [
            "In Progress",
            2.3,
            "+0.1",
            28,
            "ACME-470, 8 days"
          ],
          [
            "In Review",
            2.8,
            "+0.9",
            24,
            "ACME-482, 9 days"
          ],
          [
            "QA",
            1.2,
            "-0.2",
            19,
            "ACME-488, 4 days"
          ],
          [
            "Blocked",
            3.5,
            "+0.4",
            4,
            "ACME-431, 12 days"
          ]
        ]
      }
    },
    {
      "type": "Callout",
      "props": {
        "text": "6 issues waited more than 4 days in review, and 5 of them were assigned to the same two reviewers.",
        "tone": "warn"
      }
    }
  ]
}
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: Mondays at 9:00 (`0 9 * * 1`). From cron, with the agent signed in on that machine:

```bash
0 9 * * 1 claude -p "Run the jira-time-in-status-report 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/jira-time-in-status-report#schedule

Source: https://briefkin.dev/skills/jira-time-in-status-report

What your agent needs

  • Browse permission on the projects, through an Atlassian API token with your email (JIRA_EMAIL, JIRA_API_TOKEN) or the Atlassian Rovo MCP server.

  • Which projects or board filter to measure, and whether to count calendar or working days.

Connecting Jira

  1. Atlassian Rovo MCP Server, Atlassian's official remote server for Jira and Confluence at https://mcp.atlassian.com/v2/mcp. In Claude, add the Atlassian connector from the directory; in Claude Code, run claude mcp add --transport http atlassian https://mcp.atlassian.com/v2/mcp and authenticate with /mcp. It signs in with OAuth 2.1 or an API token and respects your Jira permissions (getting started).
  2. Atlassian CLI. After acli jira auth login, acli jira workitem search --jql "sprint in openSprints()" --json returns the same issues from a terminal.
  3. REST API with an API token. Create a token at id.atlassian.com under Security > API tokens. The skill reads JIRA_EMAIL, JIRA_API_TOKEN and JIRA_BASE_URL (https://acme.atlassian.net) and uses basic auth. A scoped token limited to read:jira-work and read:jira-user is narrower; scoped tokens call https://api.atlassian.com/ex/jira/{cloudId} instead of your site URL.

A classic token can do anything your account can, so prefer a scoped token with read scopes only, or an account that just has Browse permission on the projects in the report.

Questions

Does it count weekends?

By default it counts calendar time, the way the changelog records it. Ask for working days and it leaves out Saturdays and Sundays (and any holidays you list), which makes a Friday-to-Monday review read as one day instead of three.

Why the bulk changelog endpoint instead of expanding the search?

The changelog that comes back with a search can be cut short on issues with long histories, which loses the early transitions. The bulk endpoint takes up to 1,000 issues per call, filters to the status field, and pages through the full history.

Do I need Briefkin to use the Jira time in status report 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 report card, 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 Jira pages themselves: the agent opens start.atlassian.com 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.

Read this report on your board, not in a chat log

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.