da-express-milo: Command for Claude Code

.claude/commands/start-ticket.md

start-ticket is a command for Claude Code from adobecom/da-express-milo. It costs 42 tokens per session (1,623 once invoked), scanned A, original, Apache-2.0.

A ticket-starting command that gathers the working context for a Jira issue, a work-tracking ticket system. It finds the ticket and related content, switches to its Git branch, checks the local AEM server, and opens linked design and review pages.

In plain words
What is it for?
Use it when starting work from a Jira ID or description to open the relevant content, Figma design, pull request, branch, and local server.
Why use it?
It removes the repeated setup work before coding on a ticket and helps reveal whether the local development environment is ready.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is adobecom/da-express-milo's own configuration. It tells Claude Code how to work on da-express-milo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything da-express-milo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adobecom/da-express-milo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/adobecom/da-express-milo/stage/.claude/commands/start-ticket.md
Clone the repo
git clone --depth 1 https://github.com/adobecom/da-express-milo

Made for: Claude Code.

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 start-ticket

README.md
[![agentmods](https://agentmods.dev/badge/commands/adobecom/da-express-milo/start-ticket/github.svg)](https://agentmods.dev/commands/adobecom/da-express-milo/start-ticket)
Your own site
<a href="https://agentmods.dev/commands/adobecom/da-express-milo/start-ticket"><img src="https://agentmods.dev/badge/commands/adobecom/da-express-milo/start-ticket/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 start-ticket

Your own site · 80×15
<a href="https://agentmods.dev/commands/adobecom/da-express-milo/start-ticket"><img src="https://agentmods.dev/badge/commands/adobecom/da-express-milo/start-ticket.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,623 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00042 $0.01623
Opus 5 $0.00021 $0.00812
Sonnet 5 $0.00008 $0.00325
Haiku 4.5 $0.00004 $0.00162

Measured today against content hash 4fc2c59b65bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

start-ticket scanned grade A with 1 finding 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 today.

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.

1. Check whether something is listening on port `3000` and whether it actually responds: `curl -s -o /dev/null -w "%{http_code}" --max-time 2 http://localhost:3000/`.
.claude/commands/start-ticket.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

start-ticket

Orchestrates the "get set up for this ticket" ritual: resolve the Jira issue, open its content and design links, switch to its branch, make sure the local dev server is actually usable, and surface the latest PR.

Argument: $ARGUMENTS — a Jira ticket ID (e.g. MWPW-123456) or a free-text description of the ticket.


Configuration (defaults — adjust inline if the user says otherwise)

Setting Default
Jira base URL https://jira.corp.adobe.com/browse/
Default Jira project (when a bare description is given, no project prefix) MWPW
GitHub repo adobecom/da-express-milo
AEM dev server port 3000
Browser open command open <url> (macOS default-app open; swap for open -na "Google Chrome" --args --new-window <url> if the user wants forced new windows in a specific browser)
DA org/repo for drafts adobecom / da-express-milo, path prefix drafts/

Phase A — Resolve the Jira ticket

  1. If $ARGUMENTS matches a ticket-key pattern ([A-Z]+-[0-9]+), use it directly.
  2. Otherwise treat it as free text: use the mcp__corp-jira__search_jira_issues tool with a JQL query scoped to the default project first (e.g. project = MWPW AND text ~ "<keywords>" ORDER BY updated DESC), and widen the search (drop the project filter) if nothing relevant comes back. Confirm the match with the user if more than one issue looks plausible — don't guess silently between two unrelated tickets.
  3. Pull the full issue: summary, description, and comments (mcp__corp-jira__get_jira_comments) — the description/PR/Figma links are often only in a comment, not the description field.
  4. Open the ticket: open "https://jira.corp.adobe.com/browse/<KEY>".

Keep the resolved key (<KEY>) and the collected description + comment text handy for the rest of the phases — you'll scan that text for URLs repeatedly below.


Phase B — Open the draft or primary content page

Scan the description + comments for URLs and classify them:

  • Draft page: a DA/edit link or preview URL whose path contains /drafts/ (e.g. da.live/edit#/adobecom/da-express-milo/drafts/... or *.aem.page/drafts/...).
  • Primary page: any other content URL being modified (e.g. main--da-express-milo--adobecom.aem.live/express/... or a adobe.com/express/... prod URL).

Read the full file on GitHub · 92 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. today First seen · 92 lines · 42 tokens per session scan A 4fc2c59b65bd

Subscribe to this mod's changes

start-ticket is a command published in the GitHub repository adobecom/da-express-milo (6 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,623 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.