docs(orchestration): stop the kernel from looping on an informational nextAction

For a healthy in-progress worker the projection returns nextAction
{kind:'inspect', argv:['orchestration','worker-show','--dispatch',<same id>]}
with attention.requiresAction false, and the kernel told the coordinator to
follow the literal argv. Raises the kernel line budget 200 -> 202: the
paragraph had zero slack and no existing guidance was worth cutting.

config/scripts/orchestration-skill-guidance.test.mjs

@@ -77,7 +77,8 @@ describe('orchestration kernel', () => {
       '## Conditional references'
     ]
 
-    expect(kernel.split('\n').length).toBeLessThanOrEqual(200)
+    // Why: 202 is the budget after the anti-loop nextAction rule; the kernel is always in context.
+    expect(kernel.split('\n').length).toBeLessThanOrEqual(202)
     for (let index = 1; index < headings.length; index += 1) {
       expect(kernel.indexOf(headings[index])).toBeGreaterThan(kernel.indexOf(headings[index - 1]))
     }
@@ -161,6 +162,9 @@ describe('orchestration kernel', () => {
     expect(kernel).toContain(
       '`projection.attention` categories, `projection.attention.requiresAction`, and literal `projection.nextAction` argv'
     )
+    expect(kernel).toContain(
+      'An `inspect` `nextAction` on a `live` row with `attention.requiresAction` false is informational, not a command to re-run: keep waiting with `check --wait`'
+    )
     expect(kernel).toContain('choose `worker-stop` or `worker-abandon`')
   })
 

skill-guides/orchestration.md

@@ -137,7 +137,9 @@ editor from timeout, idle state, heartbeat, relay loss, or missing client alone.
 After three consecutive empty waits, stop waiting blindly and enumerate with
 `ORCA orchestration worker-list --json`, acting on each row's
 `projection.attention` categories, `projection.attention.requiresAction`, and
-literal `projection.nextAction` argv. Leave the wait only on positive proof the
+literal `projection.nextAction` argv. An `inspect` `nextAction` on a `live` row
+with `attention.requiresAction` false is informational, not a command to re-run:
+keep waiting with `check --wait`. Leave the wait only on positive proof the
 agent stopped: `exited` liveness, the worker's own observation of process exit,
 or a transcript whose final agent turn sent no `worker_done`. Then load
 `references/recovery-and-cleanup.md` and choose `worker-stop` or