To Tickets

---
name: to-tickets
description: Turn a plan, spec, or conversation into dependency-linked tracer-bullet tickets for drafting or authorized publication.
disable-model-invocation: true
---

# To Tickets

Break a plan, spec, or conversation into a set of **tickets**: tracer-bullet vertical slices, each declaring the tickets that **block** it.

When fetching tracker context or preparing publication, read [Tracker integration](../triage/TRACKER.md) for destination, role mapping, and authorization rules. Missing tracker setup does not block a draft breakdown.

## Process

### 1. Gather context

Work from whatever is already in the conversation context. If the user passes a reference (a spec path, an issue number or URL) as an argument, fetch it and read its full body and comments.

### 2. Explore the codebase (optional)

Inspect relevant code only where it could change the slicing, contracts, or blocking edges. Reuse existing evidence. Ticket titles and descriptions should use the project's domain glossary vocabulary and respect ADRs in the affected area.

Look for opportunities to prefactor the code to make the implementation easier. "Make the change easy, then make the easy change."

### 3. Draft vertical slices

Break the work into **tracer bullet** tickets.

<vertical-slice-rules>

- Each slice delivers a complete behavior through the layers it needs. Select checks for that behavior.
- A completed slice is demoable or verifiable on its own
- Each slice is sized to fit in a single fresh context window
- Put necessary prefactoring before the slices it genuinely gates

</vertical-slice-rules>

Give each ticket its **blocking edges**: the other tickets that must complete before it can start. A ticket with no blockers can start immediately.

**Wide refactors are the exception to vertical slicing.** A **wide refactor** is one mechanical change (rename a column, retype a shared symbol) whose **blast radius** fans across the whole codebase, so a single edit breaks thousands of call sites at once and no vertical slice can land green. Don't force it into a tracer bullet; sequence it as **expand–contract**. First expand: add the new form beside the old so nothing breaks. Then migrate the call sites over in batches sized by blast radius (per package, per directory), each batch its own ticket blocked by the expand, keeping CI green batch to batch because the old form still exists. Finally contract: delete the old form once no caller remains, in a ticket blocked by every migrate batch. When even the batches can't stay green alone, keep the sequence but let them share an integration branch that all block a final integrate-and-verify ticket; green is promised only there.

### 4. Review new or changed decomposition

Reuse explicit approval of an unchanged breakdown. When proposing new or materially changed deliverables or blocking edges, present the breakdown as a numbered list. For each ticket, show:

- **Title**: short descriptive name
- **Blocked by**: which other tickets (if any) must complete first
- **What it delivers**: the end-to-end behaviour this ticket makes work

Ask only the questions needed to settle that new or changed breakdown:

- Does the granularity feel right? (too coarse / too fine)
- Are the blocking edges correct: does each ticket only depend on tickets that genuinely gate it?
- Should any tickets be merged or split further?

Obtain approval before publishing new or changed decomposition. Do not repeat this review when the same breakdown has already been explicitly approved. A draft-only request ends with the proposed tickets and any unresolved choices.

### 5. Publish when authorized

When publication to the selected tracker is requested or approved, publish the approved tickets using its configured operations:

- **Local files** → write one file per ticket under `.scratch/<feature-slug>/issues/<NN>-<slug>.md`, numbered from `01` in dependency order (blockers first). Each file's "Blocked by" lists the numbers/titles it depends on. Use the per-ticket file template below: one ticket per file, never a single combined file.
- **A real issue tracker (GitHub, Linear, …)** → publish one issue per ticket in dependency order (blockers first) so each ticket's blocking edges can reference real identifiers. Use native blocking relationships where available; otherwise set each ticket's "Blocked by" to the blocking issues. A parent/sub-issue relationship is not a substitute for blocking. Apply the configured `ready-for-agent` role to fully specified tickets.

Hand off the **frontier**, the tickets whose blockers are all done. For a purely linear chain that means top to bottom. Return the published identifiers and any unfinished publication steps. Publishing tickets does not authorize implementing them.

Do NOT close or modify any parent issue.

<local-ticket-template>

# <NN>: <Ticket title>

**What to build:** the end-to-end behaviour this ticket makes work, from the user's perspective, not a layer-by-layer implementation list.

**Blocked by:** the numbers/titles of the tickets that gate this one, or "None (can start immediately)".

**Status:** <configured ready-for-agent value>

- [ ] Acceptance criterion 1
- [ ] Acceptance criterion 2

</local-ticket-template>

<issue-template>

## Parent

A reference to the parent issue on the tracker (if the source was an existing issue, otherwise omit this section).

## What to build

The end-to-end behaviour this ticket makes work, from the user's perspective, not layer-by-layer implementation.

## Acceptance criteria

- [ ] Criterion 1
- [ ] Criterion 2

## Blocked by

- A reference to each blocking ticket, or "None (can start immediately)".

</issue-template>

In either form, avoid specific file paths or code snippets: they go stale fast. Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it and note briefly that it came from a prototype. Trim to the decision-rich parts, not a working demo, just the important bits.