create-merlin-brain 3.17.0 → 3.18.0

package/dist/server/tools/challenge.js

@@ -0,0 +1,251 @@
+/**
+ * Challenge Tracking Tools
+ * MCP tools for recording and analyzing dialectic challenge outcomes
+ * (Insider vs Academic vs Synthesis approach comparisons)
+ */
+import { z } from 'zod';
+// ── In-memory store + file persistence ──────────────────────────────
+// Challenges are stored locally in ~/.claude/merlin/challenges.jsonl
+// and optionally synced to cloud via agent state API
+import { existsSync, mkdirSync, appendFileSync, readFileSync } from 'fs';
+import { join } from 'path';
+import { homedir } from 'os';
+function getChallengesPath() {
+    const dir = join(homedir(), '.claude', 'merlin');
+    if (!existsSync(dir)) {
+        mkdirSync(dir, { recursive: true });
+    }
+    return join(dir, 'challenges.jsonl');
+}
+function loadChallenges() {
+    const path = getChallengesPath();
+    if (!existsSync(path))
+        return [];
+    try {
+        const lines = readFileSync(path, 'utf-8').split('\n').filter(Boolean);
+        return lines.map(line => JSON.parse(line));
+    }
+    catch {
+        return [];
+    }
+}
+function appendChallenge(record) {
+    const path = getChallengesPath();
+    appendFileSync(path, JSON.stringify(record) + '\n');
+}
+function updateChallenge(id, updates) {
+    const path = getChallengesPath();
+    const challenges = loadChallenges();
+    const idx = challenges.findIndex(c => c.id === id);
+    if (idx === -1)
+        return false;
+    challenges[idx] = { ...challenges[idx], ...updates };
+    // Rewrite file
+    const content = challenges.map(c => JSON.stringify(c)).join('\n') + '\n';
+    const { writeFileSync } = require('fs');
+    writeFileSync(path, content);
+    return true;
+}
+export function registerChallengeTools(ctx) {
+    const { server } = ctx;
+    // ── DEFERRED tool: Record a challenge outcome ─────────────────────
+    server.tool('merlin_record_challenge', 'Record the outcome of a dialectic challenge (Insider vs Academic approach comparison). Called automatically by /merlin:challenge after the Arbiter produces a verdict. Stores results locally for long-term trend analysis.', {
+        task: z.string().describe('Task that was challenged'),
+        insiderScore: z.number().describe('Insider weighted score (0-110)'),
+        academicScore: z.number().describe('Academic weighted score (0-110)'),
+        verdict: z.enum(['insider', 'academic', 'synthesis']).describe('Arbiter recommendation'),
+        synthesisRatio: z.number().describe('How much came from Academic (0=all insider, 1=all academic, 0.5=equal)'),
+        confidence: z.enum(['high', 'medium', 'low']).describe('Arbiter confidence level'),
+        keyInsight: z.string().describe('One-sentence insight from the challenge'),
+        phase: z.string().optional().describe('Phase number if part of planning pipeline'),
+        repoUrl: z.string().optional().describe('GitHub URL of the repository'),
+    }, async ({ task, insiderScore, academicScore, verdict, synthesisRatio, confidence, keyInsight, phase, repoUrl }) => {
+        try {
+            const record = {
+                id: `ch_${Date.now()}_${Math.random().toString(36).slice(2, 8)}`,
+                timestamp: new Date().toISOString(),
+                repoUrl: repoUrl || undefined,
+                task,
+                phase: phase || undefined,
+                insiderScore,
+                academicScore,
+                verdict,
+                synthesisRatio,
+                confidence,
+                keyInsight,
+            };
+            appendChallenge(record);
+            const delta = insiderScore - academicScore;
+            const winner = delta > 0 ? 'Insider' : delta < 0 ? 'Academic' : 'Tie';
+            let response = `# Challenge Recorded\n\n`;
+            response += `**ID:** ${record.id}\n`;
+            response += `**Task:** ${task}\n`;
+            if (phase)
+                response += `**Phase:** ${phase}\n`;
+            response += `**Scores:** Insider ${insiderScore} vs Academic ${academicScore} (${winner} by ${Math.abs(delta)})\n`;
+            response += `**Verdict:** ${verdict}${verdict === 'synthesis' ? ` (ratio: ${synthesisRatio})` : ''}\n`;
+            response += `**Confidence:** ${confidence}\n`;
+            response += `**Insight:** ${keyInsight}\n\n`;
+            response += `_Use \`merlin_rate_challenge("${record.id}", rating, notes)\` after implementation to track outcome quality._`;
+            return { content: [{ type: 'text', text: response }] };
+        }
+        catch (error) {
+            return {
+                content: [{ type: 'text', text: `Error recording challenge: ${error instanceof Error ? error.message : 'Unknown'}` }],
+                isError: true,
+            };
+        }
+    });
+    // ── DEFERRED tool: Rate a past challenge outcome ──────────────────
+    server.tool('merlin_rate_challenge', 'Rate the outcome of a previously recorded challenge after implementation is complete. This closes the feedback loop — did the chosen approach actually work well? Enables long-term performance tracking of the challenge system itself.', {
+        challengeId: z.string().describe('Challenge ID (ch_...) to rate'),
+        rating: z.number().min(1).max(10).describe('How well did the chosen approach work? (1=terrible, 10=perfect)'),
+        notes: z.string().optional().describe('What went well or poorly with the chosen approach'),
+        implementedApproach: z.enum(['insider', 'academic', 'synthesis']).optional().describe('Which approach was actually implemented (may differ from verdict)'),
+    }, async ({ challengeId, rating, notes, implementedApproach }) => {
+        try {
+            const updated = updateChallenge(challengeId, {
+                outcomeRating: rating,
+                outcomeNotes: notes,
+                implementedApproach,
+            });
+            if (!updated) {
+                return {
+                    content: [{ type: 'text', text: `Challenge ${challengeId} not found.` }],
+                    isError: true,
+                };
+            }
+            let response = `# Challenge Rated\n\n`;
+            response += `**ID:** ${challengeId}\n`;
+            response += `**Rating:** ${rating}/10\n`;
+            if (implementedApproach)
+                response += `**Implemented:** ${implementedApproach}\n`;
+            if (notes)
+                response += `**Notes:** ${notes}\n`;
+            response += `\n_This data improves challenge accuracy over time._`;
+            return { content: [{ type: 'text', text: response }] };
+        }
+        catch (error) {
+            return {
+                content: [{ type: 'text', text: `Error rating challenge: ${error instanceof Error ? error.message : 'Unknown'}` }],
+                isError: true,
+            };
+        }
+    });
+    // ── DEFERRED tool: Get challenge statistics ───────────────────────
+    server.tool('merlin_get_challenge_stats', 'Analyze challenge history to measure the impact of the dialectic challenge system. Shows: win rates (insider vs academic vs synthesis), average scores, confidence calibration, outcome ratings, trend analysis, and insights surfaced. Use to evaluate whether challenges are improving decisions.', {
+        window: z.enum(['7d', '30d', '90d', 'all']).optional().describe('Time window for analysis (default: all)'),
+        repoUrl: z.string().optional().describe('Filter by repository'),
+    }, async ({ window, repoUrl }) => {
+        try {
+            let challenges = loadChallenges();
+            // Filter by repo if specified
+            if (repoUrl) {
+                challenges = challenges.filter(c => c.repoUrl === repoUrl);
+            }
+            // Filter by time window
+            if (window && window !== 'all') {
+                const days = window === '7d' ? 7 : window === '30d' ? 30 : 90;
+                const cutoff = new Date(Date.now() - days * 24 * 60 * 60 * 1000).toISOString();
+                challenges = challenges.filter(c => c.timestamp >= cutoff);
+            }
+            if (challenges.length === 0) {
+                return {
+                    content: [{ type: 'text', text: `No challenges recorded${window ? ` in the last ${window}` : ''}.` }],
+                };
+            }
+            // ── Compute statistics ──────────────────────────────────────
+            const total = challenges.length;
+            const verdicts = { insider: 0, academic: 0, synthesis: 0 };
+            const confidences = { high: 0, medium: 0, low: 0 };
+            let totalInsiderScore = 0;
+            let totalAcademicScore = 0;
+            let totalSynthesisRatio = 0;
+            let ratedChallenges = 0;
+            let totalRating = 0;
+            const insights = [];
+            for (const c of challenges) {
+                verdicts[c.verdict]++;
+                confidences[c.confidence]++;
+                totalInsiderScore += c.insiderScore;
+                totalAcademicScore += c.academicScore;
+                totalSynthesisRatio += c.synthesisRatio;
+                if (c.keyInsight)
+                    insights.push(c.keyInsight);
+                if (c.outcomeRating !== undefined) {
+                    ratedChallenges++;
+                    totalRating += c.outcomeRating;
+                }
+            }
+            const avgInsider = (totalInsiderScore / total).toFixed(1);
+            const avgAcademic = (totalAcademicScore / total).toFixed(1);
+            const avgSynthesisRatio = (totalSynthesisRatio / total).toFixed(2);
+            const avgRating = ratedChallenges > 0 ? (totalRating / ratedChallenges).toFixed(1) : 'N/A';
+            // ── Compute value metrics ──────────────────────────────────
+            // How often did the challenge change the approach?
+            const academicWins = verdicts.academic;
+            const synthesisWithAcademic = challenges.filter(c => c.verdict === 'synthesis' && c.synthesisRatio > 0.3).length;
+            const approachChanged = academicWins + synthesisWithAcademic;
+            const changeRate = ((approachChanged / total) * 100).toFixed(0);
+            // Confidence calibration: do high-confidence verdicts get better ratings?
+            const highConfRated = challenges.filter(c => c.confidence === 'high' && c.outcomeRating !== undefined);
+            const lowConfRated = challenges.filter(c => c.confidence === 'low' && c.outcomeRating !== undefined);
+            const avgHighConfRating = highConfRated.length > 0
+                ? (highConfRated.reduce((s, c) => s + c.outcomeRating, 0) / highConfRated.length).toFixed(1)
+                : 'N/A';
+            const avgLowConfRating = lowConfRated.length > 0
+                ? (lowConfRated.reduce((s, c) => s + c.outcomeRating, 0) / lowConfRated.length).toFixed(1)
+                : 'N/A';
+            // ── Build report ────────────────────────────────────────────
+            let report = `# Challenge System Analytics\n\n`;
+            report += `**Period:** ${window || 'all time'} · **Challenges:** ${total}\n\n`;
+            report += `## Verdict Distribution\n`;
+            report += `| Verdict | Count | Rate |\n|---------|-------|------|\n`;
+            report += `| Insider wins | ${verdicts.insider} | ${((verdicts.insider / total) * 100).toFixed(0)}% |\n`;
+            report += `| Academic wins | ${verdicts.academic} | ${((verdicts.academic / total) * 100).toFixed(0)}% |\n`;
+            report += `| Synthesis | ${verdicts.synthesis} | ${((verdicts.synthesis / total) * 100).toFixed(0)}% |\n\n`;
+            report += `## Scores\n`;
+            report += `- Avg Insider score: **${avgInsider}**/110\n`;
+            report += `- Avg Academic score: **${avgAcademic}**/110\n`;
+            report += `- Avg synthesis ratio: **${avgSynthesisRatio}** (0=all insider, 1=all academic)\n\n`;
+            report += `## Impact\n`;
+            report += `- **${changeRate}%** of challenges changed the approach (academic win or significant synthesis)\n`;
+            report += `- This means ${changeRate}% of the time, the system caught a better path that single-track planning would have missed.\n\n`;
+            report += `## Confidence Distribution\n`;
+            report += `- High: ${confidences.high} · Medium: ${confidences.medium} · Low: ${confidences.low}\n\n`;
+            if (ratedChallenges > 0) {
+                report += `## Outcome Quality (${ratedChallenges} rated)\n`;
+                report += `- Average outcome rating: **${avgRating}**/10\n`;
+                report += `- High-confidence outcomes: **${avgHighConfRating}**/10\n`;
+                report += `- Low-confidence outcomes: **${avgLowConfRating}**/10\n`;
+                if (avgHighConfRating !== 'N/A' && avgLowConfRating !== 'N/A') {
+                    const calibrated = parseFloat(avgHighConfRating) > parseFloat(avgLowConfRating);
+                    report += `- Confidence calibration: ${calibrated ? '✅ Well-calibrated (high confidence → better outcomes)' : '⚠️ Miscalibrated (low confidence outcomes not worse — arbiter may be too cautious)'}\n`;
+                }
+                report += `\n`;
+            }
+            // Recent insights (last 5)
+            const recentInsights = insights.slice(-5);
+            if (recentInsights.length > 0) {
+                report += `## Recent Insights\n`;
+                for (const insight of recentInsights) {
+                    report += `- ${insight}\n`;
+                }
+                report += `\n`;
+            }
+            // Unrated challenges reminder
+            const unrated = challenges.filter(c => c.outcomeRating === undefined);
+            if (unrated.length > 0) {
+                report += `---\n_${unrated.length} challenges awaiting outcome rating. Rate them with \`merlin_rate_challenge\` after implementation._\n`;
+            }
+            return { content: [{ type: 'text', text: report }] };
+        }
+        catch (error) {
+            return {
+                content: [{ type: 'text', text: `Error computing stats: ${error instanceof Error ? error.message : 'Unknown'}` }],
+                isError: true,
+            };
+        }
+    });
+}
+//# sourceMappingURL=challenge.js.map

package/dist/server/tools/challenge.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"challenge.js","sourceRoot":"","sources":["../../../src/server/tools/challenge.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAGxB,uEAAuE;AACvE,qEAAqE;AACrE,qDAAqD;AAErD,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,cAAc,EAAE,YAAY,EAAE,MAAM,IAAI,CAAC;AACzE,OAAO,EAAE,IAAI,EAAE,MAAM,MAAM,CAAC;AAC5B,OAAO,EAAE,OAAO,EAAE,MAAM,IAAI,CAAC;AAmB7B,SAAS,iBAAiB;IACxB,MAAM,GAAG,GAAG,IAAI,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,QAAQ,CAAC,CAAC;IACjD,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;QACrB,SAAS,CAAC,GAAG,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;IACtC,CAAC;IACD,OAAO,IAAI,CAAC,GAAG,EAAE,kBAAkB,CAAC,CAAC;AACvC,CAAC;AAED,SAAS,cAAc;IACrB,MAAM,IAAI,GAAG,iBAAiB,EAAE,CAAC;IACjC,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC;QAAE,OAAO,EAAE,CAAC;IACjC,IAAI,CAAC;QACH,MAAM,KAAK,GAAG,YAAY,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC;QACtE,OAAO,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC;IAC7C,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,EAAE,CAAC;IACZ,CAAC;AACH,CAAC;AAED,SAAS,eAAe,CAAC,MAAuB;IAC9C,MAAM,IAAI,GAAG,iBAAiB,EAAE,CAAC;IACjC,cAAc,CAAC,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC,CAAC;AACtD,CAAC;AAED,SAAS,eAAe,CAAC,EAAU,EAAE,OAAiC;IACpE,MAAM,IAAI,GAAG,iBAAiB,EAAE,CAAC;IACjC,MAAM,UAAU,GAAG,cAAc,EAAE,CAAC;IACpC,MAAM,GAAG,GAAG,UAAU,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC;IACnD,IAAI,GAAG,KAAK,CAAC,CAAC;QAAE,OAAO,KAAK,CAAC;IAE7B,UAAU,CAAC,GAAG,CAAC,GAAG,EAAE,GAAG,UAAU,CAAC,GAAG,CAAC,EAAE,GAAG,OAAO,EAAE,CAAC;IAErD,eAAe;IACf,MAAM,OAAO,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,IAAI,CAAC;IACzE,MAAM,EAAE,aAAa,EAAE,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC;IACxC,aAAa,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC;IAC7B,OAAO,IAAI,CAAC;AACd,CAAC;AAED,MAAM,UAAU,sBAAsB,CAAC,GAAgB;IACrD,MAAM,EAAE,MAAM,EAAE,GAAG,GAAG,CAAC;IAEvB,qEAAqE;IACrE,MAAM,CAAC,IAAI,CACT,yBAAyB,EACzB,6NAA6N,EAC7N;QACE,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,0BAA0B,CAAC;QACrD,YAAY,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,gCAAgC,CAAC;QACnE,aAAa,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,iCAAiC,CAAC;QACrE,OAAO,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,UAAU,EAAE,WAAW,CAAC,CAAC,CAAC,QAAQ,CAAC,wBAAwB,CAAC;QACxF,cAAc,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,wEAAwE,CAAC;QAC7G,UAAU,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,QAAQ,EAAE,KAAK,CAAC,CAAC,CAAC,QAAQ,CAAC,0BAA0B,CAAC;QAClF,UAAU,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,yCAAyC,CAAC;QAC1E,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,QAAQ,CAAC,2CAA2C,CAAC;QAClF,OAAO,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,QAAQ,CAAC,8BAA8B,CAAC;KACxE,EACD,KAAK,EAAE,EAAE,IAAI,EAAE,YAAY,EAAE,aAAa,EAAE,OAAO,EAAE,cAAc,EAAE,UAAU,EAAE,UAAU,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE,EAAE;QAC/G,IAAI,CAAC;YACH,MAAM,MAAM,GAAoB;gBAC9B,EAAE,EAAE,MAAM,IAAI,CAAC,GAAG,EAAE,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE;gBAChE,SAAS,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;gBACnC,OAAO,EAAE,OAAO,IAAI,SAAS;gBAC7B,IAAI;gBACJ,KAAK,EAAE,KAAK,IAAI,SAAS;gBACzB,YAAY;gBACZ,aAAa;gBACb,OAAO;gBACP,cAAc;gBACd,UAAU;gBACV,UAAU;aACX,CAAC;YAEF,eAAe,CAAC,MAAM,CAAC,CAAC;YAExB,MAAM,KAAK,GAAG,YAAY,GAAG,aAAa,CAAC;YAC3C,MAAM,MAAM,GAAG,KAAK,GAAG,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,KAAK,CAAC;YAEtE,IAAI,QAAQ,GAAG,0BAA0B,CAAC;YAC1C,QAAQ,IAAI,WAAW,MAAM,CAAC,EAAE,IAAI,CAAC;YACrC,QAAQ,IAAI,aAAa,IAAI,IAAI,CAAC;YAClC,IAAI,KAAK;gBAAE,QAAQ,IAAI,cAAc,KAAK,IAAI,CAAC;YAC/C,QAAQ,IAAI,uBAAuB,YAAY,gBAAgB,aAAa,KAAK,MAAM,OAAO,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC;YACnH,QAAQ,IAAI,gBAAgB,OAAO,GAAG,OAAO,KAAK,WAAW,CAAC,CAAC,CAAC,YAAY,cAAc,GAAG,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC;YACvG,QAAQ,IAAI,mBAAmB,UAAU,IAAI,CAAC;YAC9C,QAAQ,IAAI,gBAAgB,UAAU,MAAM,CAAC;YAC7C,QAAQ,IAAI,iCAAiC,MAAM,CAAC,EAAE,qEAAqE,CAAC;YAE5H,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,QAAQ,EAAE,CAAC,EAAE,CAAC;QAClE,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,OAAO;gBACL,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,8BAA8B,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC;gBAC9H,OAAO,EAAE,IAAI;aACd,CAAC;QACJ,CAAC;IACH,CAAC,CACF,CAAC;IAEF,qEAAqE;IACrE,MAAM,CAAC,IAAI,CACT,uBAAuB,EACvB,0OAA0O,EAC1O;QACE,WAAW,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,+BAA+B,CAAC;QACjE,MAAM,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,QAAQ,CAAC,iEAAiE,CAAC;QAC7G,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,QAAQ,CAAC,mDAAmD,CAAC;QAC1F,mBAAmB,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,UAAU,EAAE,WAAW,CAAC,CAAC,CAAC,QAAQ,EAAE,CAAC,QAAQ,CAAC,mEAAmE,CAAC;KAC3J,EACD,KAAK,EAAE,EAAE,WAAW,EAAE,MAAM,EAAE,KAAK,EAAE,mBAAmB,EAAE,EAAE,EAAE;QAC5D,IAAI,CAAC;YACH,MAAM,OAAO,GAAG,eAAe,CAAC,WAAW,EAAE;gBAC3C,aAAa,EAAE,MAAM;gBACrB,YAAY,EAAE,KAAK;gBACnB,mBAAmB;aACpB,CAAC,CAAC;YAEH,IAAI,CAAC,OAAO,EAAE,CAAC;gBACb,OAAO;oBACL,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,aAAa,WAAW,aAAa,EAAE,CAAC;oBACjF,OAAO,EAAE,IAAI;iBACd,CAAC;YACJ,CAAC;YAED,IAAI,QAAQ,GAAG,uBAAuB,CAAC;YACvC,QAAQ,IAAI,WAAW,WAAW,IAAI,CAAC;YACvC,QAAQ,IAAI,eAAe,MAAM,OAAO,CAAC;YACzC,IAAI,mBAAmB;gBAAE,QAAQ,IAAI,oBAAoB,mBAAmB,IAAI,CAAC;YACjF,IAAI,KAAK;gBAAE,QAAQ,IAAI,cAAc,KAAK,IAAI,CAAC;YAC/C,QAAQ,IAAI,sDAAsD,CAAC;YAEnE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,QAAQ,EAAE,CAAC,EAAE,CAAC;QAClE,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,OAAO;gBACL,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,2BAA2B,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC;gBAC3H,OAAO,EAAE,IAAI;aACd,CAAC;QACJ,CAAC;IACH,CAAC,CACF,CAAC;IAEF,qEAAqE;IACrE,MAAM,CAAC,IAAI,CACT,4BAA4B,EAC5B,qSAAqS,EACrS;QACE,MAAM,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC,CAAC,CAAC,QAAQ,EAAE,CAAC,QAAQ,CAAC,yCAAyC,CAAC;QAC1G,OAAO,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,QAAQ,CAAC,sBAAsB,CAAC;KAChE,EACD,KAAK,EAAE,EAAE,MAAM,EAAE,OAAO,EAAE,EAAE,EAAE;QAC5B,IAAI,CAAC;YACH,IAAI,UAAU,GAAG,cAAc,EAAE,CAAC;YAElC,8BAA8B;YAC9B,IAAI,OAAO,EAAE,CAAC;gBACZ,UAAU,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,OAAO,KAAK,OAAO,CAAC,CAAC;YAC7D,CAAC;YAED,wBAAwB;YACxB,IAAI,MAAM,IAAI,MAAM,KAAK,KAAK,EAAE,CAAC;gBAC/B,MAAM,IAAI,GAAG,MAAM,KAAK,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,KAAK,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;gBAC9D,MAAM,MAAM,GAAG,IAAI,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,GAAG,IAAI,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,IAAI,CAAC,CAAC,WAAW,EAAE,CAAC;gBAC/E,UAAU,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,SAAS,IAAI,MAAM,CAAC,CAAC;YAC7D,CAAC;YAED,IAAI,UAAU,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;gBAC5B,OAAO;oBACL,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,yBAAyB,MAAM,CAAC,CAAC,CAAC,gBAAgB,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,CAAC;iBAC/G,CAAC;YACJ,CAAC;YAED,+DAA+D;YAC/D,MAAM,KAAK,GAAG,UAAU,CAAC,MAAM,CAAC;YAChC,MAAM,QAAQ,GAAG,EAAE,OAAO,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,CAAC;YAC3D,MAAM,WAAW,GAAG,EAAE,IAAI,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,CAAC;YACnD,IAAI,iBAAiB,GAAG,CAAC,CAAC;YAC1B,IAAI,kBAAkB,GAAG,CAAC,CAAC;YAC3B,IAAI,mBAAmB,GAAG,CAAC,CAAC;YAC5B,IAAI,eAAe,GAAG,CAAC,CAAC;YACxB,IAAI,WAAW,GAAG,CAAC,CAAC;YACpB,MAAM,QAAQ,GAAa,EAAE,CAAC;YAE9B,KAAK,MAAM,CAAC,IAAI,UAAU,EAAE,CAAC;gBAC3B,QAAQ,CAAC,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC;gBACtB,WAAW,CAAC,CAAC,CAAC,UAAU,CAAC,EAAE,CAAC;gBAC5B,iBAAiB,IAAI,CAAC,CAAC,YAAY,CAAC;gBACpC,kBAAkB,IAAI,CAAC,CAAC,aAAa,CAAC;gBACtC,mBAAmB,IAAI,CAAC,CAAC,cAAc,CAAC;gBACxC,IAAI,CAAC,CAAC,UAAU;oBAAE,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC;gBAC9C,IAAI,CAAC,CAAC,aAAa,KAAK,SAAS,EAAE,CAAC;oBAClC,eAAe,EAAE,CAAC;oBAClB,WAAW,IAAI,CAAC,CAAC,aAAa,CAAC;gBACjC,CAAC;YACH,CAAC;YAED,MAAM,UAAU,GAAG,CAAC,iBAAiB,GAAG,KAAK,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;YAC1D,MAAM,WAAW,GAAG,CAAC,kBAAkB,GAAG,KAAK,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;YAC5D,MAAM,iBAAiB,GAAG,CAAC,mBAAmB,GAAG,KAAK,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;YACnE,MAAM,SAAS,GAAG,eAAe,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,WAAW,GAAG,eAAe,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC;YAE3F,8DAA8D;YAC9D,mDAAmD;YACnD,MAAM,YAAY,GAAG,QAAQ,CAAC,QAAQ,CAAC;YACvC,MAAM,qBAAqB,GAAG,UAAU,CAAC,MAAM,CAC7C,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,OAAO,KAAK,WAAW,IAAI,CAAC,CAAC,cAAc,GAAG,GAAG,CACzD,CAAC,MAAM,CAAC;YACT,MAAM,eAAe,GAAG,YAAY,GAAG,qBAAqB,CAAC;YAC7D,MAAM,UAAU,GAAG,CAAC,CAAC,eAAe,GAAG,KAAK,CAAC,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;YAEhE,0EAA0E;YAC1E,MAAM,aAAa,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,UAAU,KAAK,MAAM,IAAI,CAAC,CAAC,aAAa,KAAK,SAAS,CAAC,CAAC;YACvG,MAAM,YAAY,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,UAAU,KAAK,KAAK,IAAI,CAAC,CAAC,aAAa,KAAK,SAAS,CAAC,CAAC;YACrG,MAAM,iBAAiB,GAAG,aAAa,CAAC,MAAM,GAAG,CAAC;gBAChD,CAAC,CAAC,CAAC,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,aAAc,EAAE,CAAC,CAAC,GAAG,aAAa,CAAC,MAAM,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC;gBAC7F,CAAC,CAAC,KAAK,CAAC;YACV,MAAM,gBAAgB,GAAG,YAAY,CAAC,MAAM,GAAG,CAAC;gBAC9C,CAAC,CAAC,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,aAAc,EAAE,CAAC,CAAC,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC;gBAC3F,CAAC,CAAC,KAAK,CAAC;YAEV,+DAA+D;YAC/D,IAAI,MAAM,GAAG,kCAAkC,CAAC;YAChD,MAAM,IAAI,eAAe,MAAM,IAAI,UAAU,sBAAsB,KAAK,MAAM,CAAC;YAE/E,MAAM,IAAI,2BAA2B,CAAC;YACtC,MAAM,IAAI,0DAA0D,CAAC;YACrE,MAAM,IAAI,oBAAoB,QAAQ,CAAC,OAAO,MAAM,CAAC,CAAC,QAAQ,CAAC,OAAO,GAAG,KAAK,CAAC,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,OAAO,CAAC;YACzG,MAAM,IAAI,qBAAqB,QAAQ,CAAC,QAAQ,MAAM,CAAC,CAAC,QAAQ,CAAC,QAAQ,GAAG,KAAK,CAAC,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,OAAO,CAAC;YAC5G,MAAM,IAAI,iBAAiB,QAAQ,CAAC,SAAS,MAAM,CAAC,CAAC,QAAQ,CAAC,SAAS,GAAG,KAAK,CAAC,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC;YAE5G,MAAM,IAAI,aAAa,CAAC;YACxB,MAAM,IAAI,0BAA0B,UAAU,UAAU,CAAC;YACzD,MAAM,IAAI,2BAA2B,WAAW,UAAU,CAAC;YAC3D,MAAM,IAAI,4BAA4B,iBAAiB,wCAAwC,CAAC;YAEhG,MAAM,IAAI,aAAa,CAAC;YACxB,MAAM,IAAI,OAAO,UAAU,kFAAkF,CAAC;YAC9G,MAAM,IAAI,gBAAgB,UAAU,kGAAkG,CAAC;YAEvI,MAAM,IAAI,8BAA8B,CAAC;YACzC,MAAM,IAAI,WAAW,WAAW,CAAC,IAAI,cAAc,WAAW,CAAC,MAAM,WAAW,WAAW,CAAC,GAAG,MAAM,CAAC;YAEtG,IAAI,eAAe,GAAG,CAAC,EAAE,CAAC;gBACxB,MAAM,IAAI,uBAAuB,eAAe,WAAW,CAAC;gBAC5D,MAAM,IAAI,+BAA+B,SAAS,SAAS,CAAC;gBAC5D,MAAM,IAAI,iCAAiC,iBAAiB,SAAS,CAAC;gBACtE,MAAM,IAAI,gCAAgC,gBAAgB,SAAS,CAAC;gBACpE,IAAI,iBAAiB,KAAK,KAAK,IAAI,gBAAgB,KAAK,KAAK,EAAE,CAAC;oBAC9D,MAAM,UAAU,GAAG,UAAU,CAAC,iBAAiB,CAAC,GAAG,UAAU,CAAC,gBAAgB,CAAC,CAAC;oBAChF,MAAM,IAAI,6BAA6B,UAAU,CAAC,CAAC,CAAC,uDAAuD,CAAC,CAAC,CAAC,oFAAoF,IAAI,CAAC;gBACzM,CAAC;gBACD,MAAM,IAAI,IAAI,CAAC;YACjB,CAAC;YAED,2BAA2B;YAC3B,MAAM,cAAc,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;YAC1C,IAAI,cAAc,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAC9B,MAAM,IAAI,sBAAsB,CAAC;gBACjC,KAAK,MAAM,OAAO,IAAI,cAAc,EAAE,CAAC;oBACrC,MAAM,IAAI,KAAK,OAAO,IAAI,CAAC;gBAC7B,CAAC;gBACD,MAAM,IAAI,IAAI,CAAC;YACjB,CAAC;YAED,8BAA8B;YAC9B,MAAM,OAAO,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,aAAa,KAAK,SAAS,CAAC,CAAC;YACtE,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACvB,MAAM,IAAI,SAAS,OAAO,CAAC,MAAM,wGAAwG,CAAC;YAC5I,CAAC;YAED,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE,CAAC;QAChE,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,OAAO;gBACL,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,0BAA0B,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,EAAE,EAAE,CAAC;gBAC1H,OAAO,EAAE,IAAI;aACd,CAAC;QACJ,CAAC;IACH,CAAC,CACF,CAAC;AACJ,CAAC"}

package/dist/server/tools/index.d.ts

@@ -18,4 +18,5 @@ export { registerSessionRestoreTools } from './session-restore.js';
 export { registerSessionSearchTools } from './session-search.js';
 export { registerPromoteTools } from './promote.js';
 export { registerLearningTools } from './learning.js';
+export { registerChallengeTools } from './challenge.js';
 //# sourceMappingURL=index.d.ts.map

package/dist/server/tools/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/server/tools/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,YAAY,EAAE,WAAW,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AAC1D,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,gBAAgB,CAAC;AACvD,OAAO,EAAE,yBAAyB,EAAE,MAAM,mBAAmB,CAAC;AAC9D,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AACtD,OAAO,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC;AACjD,OAAO,EAAE,sBAAsB,EAAE,MAAM,kBAAkB,CAAC;AAC1D,OAAO,EAAE,kBAAkB,EAAE,MAAM,YAAY,CAAC;AAChD,OAAO,EAAE,wBAAwB,EAAE,MAAM,mBAAmB,CAAC;AAC7D,OAAO,EAAE,wBAAwB,EAAE,MAAM,mBAAmB,CAAC;AAC7D,OAAO,EAAE,2BAA2B,EAAE,MAAM,sBAAsB,CAAC;AACnE,OAAO,EAAE,0BAA0B,EAAE,MAAM,qBAAqB,CAAC;AACjE,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/server/tools/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,YAAY,EAAE,WAAW,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AAC1D,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,gBAAgB,CAAC;AACvD,OAAO,EAAE,yBAAyB,EAAE,MAAM,mBAAmB,CAAC;AAC9D,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AACtD,OAAO,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC;AACjD,OAAO,EAAE,sBAAsB,EAAE,MAAM,kBAAkB,CAAC;AAC1D,OAAO,EAAE,kBAAkB,EAAE,MAAM,YAAY,CAAC;AAChD,OAAO,EAAE,wBAAwB,EAAE,MAAM,mBAAmB,CAAC;AAC7D,OAAO,EAAE,wBAAwB,EAAE,MAAM,mBAAmB,CAAC;AAC7D,OAAO,EAAE,2BAA2B,EAAE,MAAM,sBAAsB,CAAC;AACnE,OAAO,EAAE,0BAA0B,EAAE,MAAM,qBAAqB,CAAC;AACjE,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AACtD,OAAO,EAAE,sBAAsB,EAAE,MAAM,gBAAgB,CAAC"}

package/dist/server/tools/index.js

@@ -17,4 +17,5 @@ export { registerSessionRestoreTools } from './session-restore.js';
 export { registerSessionSearchTools } from './session-search.js';
 export { registerPromoteTools } from './promote.js';
 export { registerLearningTools } from './learning.js';
+export { registerChallengeTools } from './challenge.js';
 //# sourceMappingURL=index.js.map

package/dist/server/tools/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/server/tools/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAGH,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,gBAAgB,CAAC;AACvD,OAAO,EAAE,yBAAyB,EAAE,MAAM,mBAAmB,CAAC;AAC9D,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AACtD,OAAO,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC;AACjD,OAAO,EAAE,sBAAsB,EAAE,MAAM,kBAAkB,CAAC;AAC1D,OAAO,EAAE,kBAAkB,EAAE,MAAM,YAAY,CAAC;AAChD,OAAO,EAAE,wBAAwB,EAAE,MAAM,mBAAmB,CAAC;AAC7D,OAAO,EAAE,wBAAwB,EAAE,MAAM,mBAAmB,CAAC;AAC7D,OAAO,EAAE,2BAA2B,EAAE,MAAM,sBAAsB,CAAC;AACnE,OAAO,EAAE,0BAA0B,EAAE,MAAM,qBAAqB,CAAC;AACjE,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/server/tools/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAGH,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,gBAAgB,CAAC;AACvD,OAAO,EAAE,yBAAyB,EAAE,MAAM,mBAAmB,CAAC;AAC9D,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AACtD,OAAO,EAAE,kBAAkB,EAAE,MAAM,aAAa,CAAC;AACjD,OAAO,EAAE,sBAAsB,EAAE,MAAM,kBAAkB,CAAC;AAC1D,OAAO,EAAE,kBAAkB,EAAE,MAAM,YAAY,CAAC;AAChD,OAAO,EAAE,wBAAwB,EAAE,MAAM,mBAAmB,CAAC;AAC7D,OAAO,EAAE,wBAAwB,EAAE,MAAM,mBAAmB,CAAC;AAC7D,OAAO,EAAE,2BAA2B,EAAE,MAAM,sBAAsB,CAAC;AACnE,OAAO,EAAE,0BAA0B,EAAE,MAAM,qBAAqB,CAAC;AACjE,OAAO,EAAE,oBAAoB,EAAE,MAAM,cAAc,CAAC;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,eAAe,CAAC;AACtD,OAAO,EAAE,sBAAsB,EAAE,MAAM,gBAAgB,CAAC"}

package/files/CLAUDE.md

@@ -103,6 +103,7 @@ These are commands that NEED user participation. Merlin auto-invokes them when t
 | "create a roadmap" / "plan the phases" / "what's the roadmap" | Roadmap | `Skill("merlin:create-roadmap")` |
 | "verify" / "check if it works" / "does it meet requirements" | Verification | `Skill("merlin:verify-work")` |
 | "debug" / "investigate" / deep technical issue | Debug | `Skill("merlin:debug", args="<issue>")` |
+| "challenge this" / "is this the right approach" / "are we sure" / "alternative approaches" | Challenge | `Skill("merlin:challenge", args="<task>")` |
 | "the plan is wrong" / "we need to change direction" / "pivot" | Course correct | `Skill("merlin:course-correct")` |
 | "what's next" / "where are we" / "what should I do" | Navigation | `Skill("merlin:next")` |
 | "progress" / "status" / "how far along" | Progress | `Skill("merlin:progress")` |

package/files/agents/challenger-academic.md

@@ -0,0 +1,131 @@
+---
+name: challenger-academic
+description: Context-free approach designer that solves the problem from first principles using industry best practices, without anchoring to existing code.
+model: sonnet
+color: purple
+version: "1.0.0"
+tools: Read, WebSearch, Bash
+disallowedTools: [Edit, Write, NotebookEdit, Grep, Glob]
+effort: high
+permissionMode: bypassPermissions
+maxTurns: 40
+---
+
+<role>
+You are the Academic — a senior architect designing a solution from first principles. You have NO knowledge of the current codebase, NO access to search it, and NO attachment to any existing approach. You know only:
+
+1. The problem to solve
+2. The tech stack (languages, frameworks, databases)
+3. The constraints (what must be true)
+
+Your job is to design the BEST theoretical approach as if starting fresh. You draw on industry best practices, published patterns, and your broad knowledge of software architecture. You are not contrarian for its own sake — you genuinely try to find the optimal solution.
+</role>
+
+<information_boundary>
+## CRITICAL: You Have Limited Information
+
+You deliberately DO NOT have access to:
+- The current codebase (no Grep, no Glob, no Merlin Sights)
+- Existing file structure or naming conventions
+- Current implementation details
+- Previous architectural decisions
+
+This is BY DESIGN. Your value comes from not being anchored to what exists. You solve the problem, not the codebase.
+
+You DO have access to:
+- WebSearch for industry best practices and patterns
+- Read for any reference documents provided in your handoff
+- Bash for checking tool versions or running quick experiments
+</information_boundary>
+
+<process>
+
+## When Called
+
+You receive a task description, tech stack, and constraints. Nothing else.
+
+### Step 1: Reframe the Problem
+- Strip away implementation details — what is the core problem?
+- Identify the key quality attributes (performance, maintainability, scalability, simplicity)
+- Rank what matters most for THIS problem
+
+### Step 2: Research Best Practices
+- Use WebSearch to find how top projects solve this class of problem
+- Look for established patterns in the given tech stack
+- Find any relevant architectural guidance (e.g., OWASP for security, 12-factor for services)
+
+### Step 3: Design From Scratch
+Produce a structured proposal:
+
+```markdown
+# Academic Approach: [Task Name]
+
+## Problem Reframed
+[The core problem, stripped of implementation details]
+
+## Key Quality Attributes (ranked)
+1. [Most important]: why
+2. [Second]: why
+3. [Third]: why
+
+## Proposed Architecture
+[Describe the ideal approach — how would the best version of this work?]
+
+## Key Design Decisions
+1. [Decision 1]: [Choice] — because [industry reason / pattern name]
+2. [Decision 2]: [Choice] — because [research finding]
+3. [Decision 3]: [Choice] — because [first-principles reasoning]
+
+## Suggested Structure
+- [module/layer 1] — [responsibility]
+- [module/layer 2] — [responsibility]
+- [module/layer 3] — [responsibility]
+
+## Patterns Applied
+- [Pattern 1] (source: [where you found it]) — [why it fits]
+- [Pattern 2] — [why it fits]
+
+## Data Model
+[If relevant — how data should flow and be stored]
+
+## API Design
+[If relevant — how interfaces should look]
+
+## Risks & Tradeoffs
+- [Risk 1]: [mitigation]
+- [Tradeoff 1]: [what we gain vs what we lose]
+
+## Estimated Complexity
+- Total new code: [rough estimate]
+- Key components: [count]
+- External dependencies: [list]
+
+## Strengths of This Approach
+1. [Why this is theoretically optimal]
+2. [What industry evidence supports it]
+3. [What long-term advantages it provides]
+
+## Honest Weaknesses
+1. [What practical challenges exist for integrating with an existing system]
+2. [What this approach assumes that might not hold]
+3. [Where simpler alternatives might be "good enough"]
+```
+
+### Step 4: Practical Grounding
+Even though you design from scratch, acknowledge practical reality:
+- How hard would this be to integrate into an existing system?
+- What migration path would be needed?
+- Is the theoretical benefit worth the practical cost?
+
+Add these reflections to "Honest Weaknesses."
+
+</process>
+
+<critical_actions>
+1. NEVER try to access the codebase — you work from first principles only
+2. NEVER assume the current approach is wrong — you offer an alternative, not a criticism
+3. NEVER design something impractical just to be different — your approach must be buildable
+4. ALWAYS cite reasoning — "because the React docs recommend" or "because the CAP theorem means"
+5. ALWAYS include practical integration considerations in your weaknesses
+6. ALWAYS research — use WebSearch to ground your approach in real-world evidence
+</critical_actions>

package/files/agents/challenger-arbiter.md

@@ -0,0 +1,147 @@
+---
+name: challenger-arbiter
+description: Impartial technical judge that compares Insider and Academic approaches on concrete criteria, produces a synthesis recommendation with performance-trackable scoring.
+model: opus
+color: orange
+version: "1.0.0"
+tools: Read, Grep, Glob, Bash
+disallowedTools: [Edit, Write, NotebookEdit]
+effort: high
+permissionMode: bypassPermissions
+maxTurns: 30
+---
+
+<role>
+You are the Arbiter — an impartial technical judge. You receive two approach proposals for the same task: one from the Insider (who knows the codebase) and one from the Academic (who designed from first principles). Your job is to evaluate both on concrete criteria and produce a recommendation.
+
+You have NO ego in either approach. You don't default to "the current way" and you don't default to "the new way." You evaluate purely on merit using explicit criteria.
+
+Your most valuable output is the SYNTHESIS — taking the best ideas from both approaches and combining them into something better than either alone.
+</role>
+
+<evaluation_framework>
+
+## Scoring Criteria (1-10 each)
+
+### Correctness (weight: 3x)
+Does the approach solve the actual problem? Does it handle edge cases? Are there logical flaws?
+
+### Simplicity (weight: 2x)
+How easy is this to understand, maintain, and debug? Fewer moving parts = higher score.
+
+### Integration Cost (weight: 2x)
+How much work to implement given the current codebase? Migration risk? Breaking changes?
+
+### Maintainability (weight: 2x)
+How easy will this be to modify in 6 months? How well does it handle future requirements?
+
+### Performance (weight: 1x)
+Runtime performance, resource usage, scalability characteristics.
+
+### Innovation (weight: 1x)
+Does this bring genuinely new value? Better patterns? Improved developer experience?
+
+**Total possible: 110 points** (sum of weighted scores)
+
+</evaluation_framework>
+
+<process>
+
+## When Called
+
+You receive both the Insider and Academic proposals, plus the original task description.
+
+### Step 1: Understand Both Proposals
+- Read each proposal completely
+- Note where they agree (these are likely correct)
+- Note where they disagree (these are the interesting decisions)
+- Identify any blind spots in either proposal
+
+### Step 2: Score Each Approach
+
+For each criterion, score both approaches 1-10 with a one-line justification:
+
+```markdown
+| Criterion | Weight | Insider | Academic | Notes |
+|-----------|--------|---------|----------|-------|
+| Correctness | 3x | 8 | 7 | Insider handles edge case X; Academic misses Y |
+| Simplicity | 2x | 6 | 8 | Academic is cleaner; Insider has legacy baggage |
+| Integration Cost | 2x | 9 | 4 | Insider fits easily; Academic needs migration |
+| Maintainability | 2x | 6 | 8 | Academic's structure is more modular |
+| Performance | 1x | 7 | 7 | Similar |
+| Innovation | 1x | 5 | 8 | Academic introduces pattern X |
+| **Weighted Total** | | **77** | **72** | |
+```
+
+### Step 3: Identify Synthesis Opportunities
+Look for combinations:
+- Academic's architecture + Insider's integration approach
+- Insider's data model + Academic's API design
+- Academic's pattern + Insider's pragmatic simplification
+
+### Step 4: Produce Recommendation
+
+```markdown
+# Arbiter Verdict: [Task Name]
+
+## Summary
+[One paragraph: who won, by how much, and why — or why a synthesis is better than either]
+
+## Scorecard
+[The scoring table from Step 2]
+
+## Areas of Agreement
+[Where both approaches align — these are high-confidence decisions]
+
+## Key Disagreements
+[Where they differ and which side is right, with reasoning]
+
+## Recommendation: [INSIDER | ACADEMIC | SYNTHESIS]
+
+### If SYNTHESIS (most common):
+**Take from Insider:**
+- [Specific element 1] — because [reason]
+- [Specific element 2] — because [reason]
+
+**Take from Academic:**
+- [Specific element 1] — because [reason]
+- [Specific element 2] — because [reason]
+
+**New from synthesis:**
+- [Element that neither proposed but combining reveals]
+
+### Synthesized Approach
+[Describe the merged approach in enough detail to implement]
+
+## Implementation Guidance
+- Start with: [first step]
+- Key files: [what to create/modify]
+- Migration: [if needed, how]
+- Risk: [primary risk and mitigation]
+
+## Confidence Level
+[HIGH | MEDIUM | LOW] — [why]
+- If HIGH: proceed without hesitation
+- If MEDIUM: proceed but watch for [specific risk]
+- If LOW: consider discussing further before committing
+
+## Performance Tracking Data
+[This section is consumed by the challenge tracking system]
+- insider_score: [weighted total]
+- academic_score: [weighted total]
+- verdict: [insider | academic | synthesis]
+- synthesis_ratio: [0.0-1.0, how much came from academic vs insider. 0 = all insider, 1 = all academic, 0.5 = equal mix]
+- confidence: [high | medium | low]
+- key_insight: [one sentence — what did the challenge process reveal that a single approach would have missed?]
+```
+
+</process>
+
+<critical_actions>
+1. NEVER default to one side — evaluate on merit every time
+2. NEVER skip scoring — numbers create accountability and trackable data
+3. NEVER produce a synthesis that's just "do both" — synthesize means INTEGRATE
+4. ALWAYS explain disagreements with specific technical reasoning
+5. ALWAYS include the Performance Tracking Data section — it feeds the analytics system
+6. ALWAYS state confidence level — LOW confidence means the team should discuss further
+</critical_actions>