fix(keyword-detector): yield to slash commands so /hyperplan executes its template

When user types /hyperplan something, two pipelines race for the message:
  1. keyword-detector hook (chat.message): the regex \b(hyperplan|hpp)\b
     matches /hyperplan because \b is satisfied by the / boundary, so the
     hook prepends <hyperplan-mode> to the text part.
  2. auto-slash-command hook (chat.message, runs immediately after):
     detectSlashCommand() checks `text.trimStart().startsWith("/")`. After
     keyword-detector's prepend, the part now starts with <hyperplan-mode>
     and the slash check fails, so the builtin command template
     (with $ARGUMENTS substituted) is never injected.

The visible symptom: /hyperplan refactor X never runs the actual
HYPERPLAN_TEMPLATE - the user sees only the keyword-detector wrapper, which
is similar but not identical, and the slash command's $ARGUMENTS payload
is silently lost.

Fix: at the top of the keyword-detector hook, after isSystemDirective() but
before any keyword scan, bail out if the prompt text starts with a slash
command (^\s*\/[a-zA-Z][\w-]*\b). Slash commands are explicit invocations
and own their own mode-injection path; the keyword detector must not race
them. Free-form mentions like "hyperplan: refactor X" still trigger
keyword detection - only the leading-slash form is suppressed.

Lock the contract with three regression tests:
  - /hyperplan refactor ... must NOT inject <hyperplan-mode>
  - /hpp investigate ... must NOT inject (shorthand slash command)
  - "hyperplan: refactor src/auth/handler.ts" still injects (free-form)

Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode).

src/hooks/keyword-detector/hook.ts

@@ -1,7 +1,7 @@
 import type { PluginInput } from "@opencode-ai/plugin"
 import type { KeywordDetectorConfig } from "../../config/schema/keyword-detector"
 import type { DetectedKeyword } from "./detector"
-import { detectKeywordsWithType, extractPromptText } from "./detector"
+import { detectKeywordsWithType, extractPromptText, looksLikeSlashCommand } from "./detector"
 import { isPlannerAgent, isNonOmoAgent } from "./constants"
 import { log } from "../../shared"
 import {
@@ -58,6 +58,11 @@ export function createKeywordDetectorHook(
         return
       }
 
+      if (looksLikeSlashCommand(promptText)) {
+        log(`[keyword-detector] Skipping slash command invocation`, { sessionID: input.sessionID })
+        return
+      }
+
       const currentAgent = getSessionAgent(input.sessionID) ?? input.agent
 
       // Skip all keyword injection for non-OMO agents (e.g., OpenCode-Builder, Plan)