Add new agents and skills for enhanced project orchestration and review processes

- Introduced `critic`, an independent adversarial reviewer for security and correctness.
- Added `fable-orchestrator` to manage task routing and verification.
- Implemented `gauntlet-critic` for fresh-context evaluation of gauntlet rounds.
- Created `planner` for generating executable implementation plans with dependencies.
- Developed `security-auditor` for application security reviews and audits.
- Established `system-steward` to improve agent prompts and skills based on verified failures.
- Added `dev-loop` skill for autonomous development loops over repositories.
- Implemented `gauntlet-loop` skill for iterative quality benchmarking against reference standards.
- Updated project settings to utilize the new orchestrator agent.
- Created documentation for `GAUNTLET.md`, `PROGRESS.md`, and `REFERENCE_BAR.md` to track project status and quality benchmarks.
- Added detailed prompting style guide to enhance understanding of prompt patterns and agentic loops.

entrypoints/background.ts

@@ -1,9 +1,9 @@
 import { defineBackground } from 'wxt/utils/define-background';
 import { CONFIG_STORAGE_KEYS } from '@lib/types';
 import type { AnalyzePayload, LexAIConfig, LexAIResponse } from '@lib/types';
-import { CONTEXT_MENU_ENTRIES, findContextMenuEntry, resolvePromptPersona } from '@lib/actions';
+import { CONTEXT_MENU_ENTRIES, findContextMenuEntry, resolvePromptPersona, resolvePromptPattern } from '@lib/actions';
 import { decryptApiKey, migratePlaintextApiKey } from '@lib/crypto';
-import { callProvider, getSystemPrompt, listModels, providerLabel } from '@lib/providers';
+import { callProvider, defaultMaxTokens, getSystemPrompt, listModels, providerLabel } from '@lib/providers';
 
 // Resolve the usable API key from stored config: prefer the encrypted path,
 // fall back to plaintext for backward compat. Returns null if none is set.
@@ -37,12 +37,12 @@ async function handleAnalyzeText(payload: AnalyzePayload): Promise<LexAIResponse
   // points behave the same. The popup still overrides by sending its own.
   if (payload.action === 'prompt' && !payload.promptParams) {
     const saved = (await chrome.storage.local.get([
-      'promptStyle', 'promptPersona', 'customPersona', 'promptFormat', 'promptModel',
+      'promptPattern', 'promptStyle', 'promptPersona', 'customPersona', 'promptFormat', 'promptModel',
     ])) as Record<string, string | undefined>;
     payload = {
       ...payload,
       promptParams: {
-        promptStyle: saved.promptStyle,
+        pattern: resolvePromptPattern(saved.promptPattern, saved.promptStyle),
         persona: resolvePromptPersona(saved.promptPersona, saved.customPersona),
         format: saved.promptFormat,
       },
@@ -64,7 +64,13 @@ async function handleAnalyzeText(payload: AnalyzePayload): Promise<LexAIResponse
     ...(payload.model ? { model: payload.model } : {}),
   };
   const systemPrompt = getSystemPrompt(payload.action, payload.style, payload.promptParams);
-  return callProvider(resolvedConfig, payload.text, systemPrompt);
+  // The Prompt Builder's engineered prompts (react/pev/gauntlet skeletons
+  // especially) run well past defaultMaxTokens' input-scaled floor for a
+  // short input idea — give the 'prompt' action a higher floor.
+  const callOpts = payload.action === 'prompt'
+    ? { maxTokens: Math.max(2048, defaultMaxTokens(payload.text)) }
+    : undefined;
+  return callProvider(resolvedConfig, payload.text, systemPrompt, callOpts);
 }
 
 // ─── Background entry ─────────────────────────────────────────────────────────