keyword-detector

Imported from willhama/md-file-study (corpus/code-yeongyu__oh-my-openagent/files/packages/omo-opencode/src/hooks/keyword-detector/AGENTS.md). Install upstream with npx skills add willhama/md-file-study --skill keyword-detector. Copyright stays with the author.

src/hooks/keyword-detector/ -- Mode Keyword Injection

Generated: 2026-07-17

OVERVIEW

Transform Tier hook on messages.transform. Scans the first user message for mode keywords and injects mode-specific system prompts. The detector and routing logic stay in src/hooks/keyword-detector/; prompt bodies now live in packages/prompts-core/prompts/ so they can be shared by future harness adapters.

This matches the package layering direction in ROADMAP.md: packages/prompts-core owns static prompt content, while this OpenCode hook owns keyword detection, model routing, and message injection.

KEYWORDS

STRUCTURE

keyword-detector/
├── index.ts           # Barrel export
├── hook.ts            # createKeywordDetectorHook() chat.message handler
├── detector.ts        # detectKeywordsWithType() + extractPromptText()
├── constants.ts       # KEYWORD_DETECTORS array, re-exports from submodules
├── types.ts           # KeywordDetector, DetectedKeyword types
├── ultrawork/
│   ├── index.ts       # getUltraworkMessage() router
│   ├── source-detector.ts # agent/model routing helpers
│   ├── default.ts     # thin loader for prompts-core/prompts/ultrawork/default.md
│   ├── gpt.ts         # thin loader for prompts-core/prompts/ultrawork/gpt.md
│   ├── gemini.ts      # thin loader for prompts-core/prompts/ultrawork/gemini.md
│   ├── glm.ts         # thin loader for prompts-core/prompts/ultrawork/glm.md
│   └── planner.ts     # thin loader for prompts-core/prompts/ultrawork/planner.md
├── team/
│   ├── index.ts
│   └── default.ts     # TEAM_PATTERN + TEAM_MESSAGE from prompts-core mode prompt
└── hyperplan/
    ├── index.ts
    └── default.ts     # HYPERPLAN_PATTERN + HYPERPLAN_MESSAGE from prompts-core mode prompt

PROMPT CONTENT LOCATIONS

The src/hooks/keyword-detector/{team,hyperplan}/default.ts files keep the regex triggers in the hook layer and import the markdown-backed constants from @oh-my-opencode/prompts-core. The ultrawork files import markdown with Bun's .md text loader so the exact prompt bytes are bundled into dist/index.js.

ULTRAWORK VARIANT ROUTING

ultrawork/source-detector.ts decides the ultrawork source in priority order:

1. Planner agents (prometheus, planner, or normalized plan) route to planner.md.
2. GPT family models, as detected by isGptModel(modelID), route to gpt.md.
3. Gemini family models, as detected by isGeminiModel(modelID), route to gemini.md.
4. GLM family models, as detected by isGlmModel(modelID), route to glm.md.
5. Everything else routes to default.md.

ultrawork/index.ts exposes getUltraworkMessage(agentName, modelID), switches on that source, and returns the loaded markdown body.

DETECTION LOGIC

chat.message (user input)
  -> extractPromptText(parts)
  -> isSystemDirective? skip
  -> removeSystemReminders(text)  # strip <SYSTEM_REMINDER> blocks
  -> detectKeywordsWithType(cleanText, agentName, modelID, disabledKeywords)
  -> isNonOmoAgent(agentName)? filter keyword injection
  -> isPlannerAgent(agentName)? filter standalone ultrawork
  -> for each detected keyword: inject mode message into output

CONFIG

{
  "keyword_detector": {
    // Skip injection for any keyword in this list.
    "disabled_keywords": ["team", "hyperplan"]
  }
}

Default: empty/missing means every detector is active. Schema lives at src/config/schema/keyword-detector.ts.

GUARDS

• System directive skip: Messages tagged as system directives are not scanned (prevents infinite loops)
• Planner agent filter: Prometheus/plan agents do not receive ultrawork injection
• Non-OMO agent filter: OpenCode built-in Builder/Plan agents do not receive keyword injection
• Session agent tracking: Uses getSessionAgent() to get actual agent (not just input hint)
• Model-aware messages: getUltraworkMessage(agentName, modelID) adapts message to active model
• Ultrawork source routing: ultrawork/ultrawork-source-routing.test.ts pins agent/model-to-prompt-source routing for getUltraworkSource