Add a parallel mode to my /factory skill and its mod.

When the verified work splits into two or more pull requests that don't depend on each
other, run them in parallel:

1. Verify and plan once, for the whole batch, in the main session. The plan has a section
   for each PR: what it builds, its branch, the files it expects to touch, and its tests.
   Add a collision table listing any file two PRs both touch, plus the order to merge them.
   I approve the batch once.
2. Give each PR to its own background subagent, which runs build, review, QA, the QA
   report and the risk report for that PR alone. Run at most 2 at a time (raise this if your
   machine can handle more), and start the next one when a slot opens.
3. Anything only one agent can use at a time (the browser, a shared dev database) needs a
   lock: take it with mkdir before using it, and remove it after.
4. If an agent is blocked on a decision, it stops and reports why. The main session asks me,
   then passes my answer back to that agent.
5. When every agent is done, give me one summary: each PR with its QA and risk reports,
   the collision table, and the order to merge.

In the mod, show a parallel batch as a boxed table above the prompt: one row per agent, one
column per step from Build to Done, then the PR and CI. Use one mark per cell: a filled
dot for done, a spinning dot for the step in progress, a hollow dot for not started, and a
triangle when the agent needs me. Under the table, list what needs me first, then a short
note from each running agent. Show links as short labels (O-1234, #567) that open when
clicked, so rows never wrap. Add a demo that plays three fake agents through the table.
