fix: numeric skill names, ultrawork missing run_in_background, ZWSP agent lookups

- #3354: Coerce data.name to String in loadSkillFromPath/loadSkillFromPathAsync
  to prevent crash when YAML parses numeric skill names (e.g., name: 12306)

- #3416: Add required run_in_background parameter to all task() examples in
  ultrawork prompts (default, gpt, gemini, planner) to match tool schema

- #3379/#3417/#3418/#3337/#3335: Strip ZWSP (U+200B) before agent name
  comparisons in agent-tool-restrictions, sync-prompt-sender, tool-execute-after,
  tool-execute-before, oracle-verification-detector, call-omo-agent,
  recovery-prompt-config, and agent-variant to prevent ZWSP-prefixed display
  names from breaking exact-match lookups

src/plugin/tool-execute-after.ts

@@ -1,6 +1,7 @@
 import { consumeToolMetadata } from "../features/tool-metadata-store"
 import type { CreatedHooks } from "../create-hooks"
 import { log } from "../shared"
+import { stripInvisibleAgentCharacters } from "../shared/agent-display-names"
 import type { PluginContext } from "./types"
 import { readState, writeState } from "../hooks/ralph-loop/storage"
 
@@ -60,7 +61,7 @@ export function createToolExecuteAfterHandler(args: {
       const verificationAttemptId = prompt?.match(VERIFICATION_ATTEMPT_PATTERN)?.[1]?.trim()
       const loopState = directory ? readState(directory) : null
       const isVerificationContext =
-        agent === "oracle"
+        (agent ? stripInvisibleAgentCharacters(agent) : agent) === "oracle"
         && !!sessionId
         && !!directory
         && loopState?.active === true