transit
Transit Ticket Router
Route Transit tickets to the appropriate workflow based on their task type.
Workflow
1. Extract Ticket Reference
Parse the T-[number] reference from the user input. Extract the numeric display ID (e.g., T-42 -> display ID 42).
If no valid T-[number] reference is found, ask the user which ticket they want to work on.
2. Fetch Task Details
Query Transit for the task using mcp__transit__query_tasks. Match the task by its display ID from the results.
If task is not found: Stop and inform the user that the ticket could not be found in Transit. Do not proceed.
If task status is done or abandoned: Warn the user that the ticket is already marked as {status} and ask whether they still want to proceed. Stop if they decline.
3. Route by Task Type
Based on the task's type field, route to the appropriate workflow:
| Type | Action |
|---|---|
bug |
Invoke /fix-bug and pass the ticket reference (T-{number}) and task context (name, description) |
feature |
Invoke /starwave:creating-spec and pass the ticket reference (T-{number}) and task context (name, description) |
research |
Enter planning mode with the research question from the task description |
chore |
Ask the user to clarify: is this closer to a bug fix or a feature? Route accordingly |
documentation |
Ask the user to clarify the scope, then route to the appropriate workflow |
4. Handoff
When routing to a skill, include:
- The Transit ticket reference (e.g.,
T-42) - The task name and description from Transit as context
- Any relevant metadata from the task
The target skill is responsible for managing Transit status transitions from that point forward.
Edge Cases
- Ambiguous type: If the task type doesn't clearly map to a workflow, ask a single clarifying question before routing.
- Missing description: If the task has no description, ask the user to provide context about what needs to be done.
More from arjenschwarz/agentic-coding
ui-ux-reviewer
Evaluate and improve user experience of interfaces (CLI, web, mobile)
120efficiency-optimizer
Analyze code for performance and efficiency improvements
41design-critic
Critical review of design documents, architecture proposals, and requirements
26fix-bug
Systematic bug investigation, resolution, and documentation. Use when fixing bugs that need thorough analysis, test coverage, and a formal bugfix report. Applies systematic debugging methodology, creates regression tests, and generates a standardized report in specs/bugfixes/<bug-name>/. For complex bugs, spawns competing implementation agents (including alternative harnesses like Kiro) and selects the best solution. Triggers on requests like "fix this bug", "debug and document this issue", or when a bug needs both resolution and documentation.
22permission-analyzer
Generate Claude Code permissions config from session history. Use when setting up autonomous mode, configuring .claude/settings.json, avoiding --dangerously-skip-permissions, or analyzing what permissions a project needs. Reads session logs to extract Bash commands and MCP tools actually used, then generates appropriate allow/deny rules.
22performing-systematic-debugging-for-stubborn-problems
Applies a modified Fagan Inspection methodology to systematically resolve persistent bugs and complex issues. Use when multiple previous fix attempts have failed repeatedly, when dealing with intricate system interactions, or when a methodical root cause analysis is needed. Do not use for simple troubleshooting. Triggers after multiple failed debugging attempts on the same complex issue.
20