ticket-new

A command that drafts and creates an issue-tracker ticket from the current conversation. The ticket can include context, the current problem, the desired result, acceptance checks, and technical notes.

In plain words
What is it for?
Use it to create concise, specific tickets with verifiable acceptance criteria and relevant code references.
Why use it?
It turns an informal request into a ticket that another developer can start implementing. The required sections make the work and its success conditions clearer.

Command

Install

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.

agentmods
npx agentmods add commands/fprochazka/claude-code-plugins/ticket-new
Clone the repo
git clone --depth 1 https://github.com/fprochazka/claude-code-plugins
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,309 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00010 $0.01309
Opus 5 $0.00005 $0.00655
Sonnet 5 $0.00002 $0.00262
Haiku 4.5 $0.00001 $0.00131

Measured 2d ago against content hash 2f7c83ff231d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ticket-new scanned grade A with 0 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/sdlc/commands/ticket-new.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a Ticket

Use the conversation context to draft and create a ticket in the issue tracker.

$ARGUMENTS

Ticket title

Short, imperative, specific (e.g., "Add retry logic to payment webhook handler")

Ticket Description

  • Context: 1-2 sentences on why this matters
  • Problem / Current behavior: What's wrong or missing today
  • Desired outcome: What should be true after this is done
  • Acceptance criteria: Concrete, verifiable checklist items
  • Technical notes (optional): Code pointers, implementation hints, constraints

Writing Style

  • Write like a "Product Engineer", not a PM writing a PRD. Be direct and specific, but make sure the business context and "WHY" is captured.
  • Prefer concrete code references over abstract descriptions (e.g., "processWebhook() in src/webhooks/handler.ts" not "the webhook processing logic").
  • Omit sections that have no content — don't include empty headings or filler.
  • A good ticket is one a developer can pick up and start working on without asking follow-up questions.
  • Make sure to not dictate to the implementor details how to solve it, at most point at relevant areas of the system
  • Write the description as if nothing has been implemented yet — even when the work is already underway or finished in this session. This is not a formality: a ticket that narrates its own progress is unreadable a week later, and the board already tracks progress in the status field.
    • Describe the problem and the desired outcome. Never the work done against them.
    • Banned: "already done in branch X", "remaining work", "we changed Y", "this fixed Z", past tense about the fix, links to the session's branch or MR, and any "as discussed" framing.
    • Acceptance criteria are written as still-open, never pre-checked.
    • If the session revealed a constraint or a code pointer worth keeping, state it as a technical note about the system, not as a report of what we tried.

Division of labor

You (the orchestrator) write the ticket body yourself — never a subagent. The title and the description come from the conversation you are holding, and no subagent can see it.

Read the full file on GitHub · 77 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. 2d ago First seen · 77 lines · 10 tokens per session scan A 2f7c83ff231d

Subscribe to this mod's changes

ticket-new is a command published in the GitHub repository fprochazka/claude-code-plugins (11 stars, last pushed 5d ago), licensed MIT. It adds 10 tokens to every session and 1,309 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.