@sun-asterisk/sungen 3.0.0-beta.81 → 3.0.0-beta.82

package/dist/cli/commands/eval.d.ts

@@ -0,0 +1,3 @@
+import { Command } from 'commander';
+export declare function registerEvalCommand(program: Command): void;
+//# sourceMappingURL=eval.d.ts.map

package/dist/cli/commands/eval.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"eval.d.ts","sourceRoot":"","sources":["../../../src/cli/commands/eval.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAGpC,wBAAgB,mBAAmB,CAAC,OAAO,EAAE,OAAO,GAAG,IAAI,CAwB1D"}

package/dist/cli/commands/eval.js

@@ -0,0 +1,37 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.registerEvalCommand = registerEvalCommand;
+const skill_lint_1 = require("../../harness/eval/skill-lint");
+function registerEvalCommand(program) {
+    program
+        .command('eval')
+        .description('Eval harness: quality checks on Sungen\'s own skills/instructions (dev/CI)')
+        .option('--skills', 'Static skill-lint: frontmatter, line budget, claude↔github sync, registration')
+        .option('--dir <path>', 'Templates dir to lint (default: bundled ai-instructions)')
+        .option('--json', 'Output the raw findings JSON')
+        .action((options) => {
+        try {
+            if (!options.skills)
+                throw new Error('Provide --skills (the only eval mode today)');
+            const dir = options.dir || (0, skill_lint_1.defaultSkillDir)();
+            const r = (0, skill_lint_1.lintSkills)(dir);
+            if (options.json) {
+                console.log(JSON.stringify(r, null, 2));
+                process.exit(r.errors > 0 ? 2 : 0);
+            }
+            console.log('');
+            console.log(`━━━ Skill-lint: ${r.checked} skill template(s) ━━━`);
+            if (!r.findings.length)
+                console.log('  ✓ all skills pass (frontmatter · line-budget · variant-sync · registration)');
+            for (const f of r.findings)
+                console.log(`  ${f.level === 'error' ? '✗' : '⚠'} [${f.rule}] ${f.file} — ${f.detail}`);
+            console.log('');
+            process.exit(r.errors > 0 ? 2 : 0);
+        }
+        catch (error) {
+            console.error('Error:', error instanceof Error ? error.message : error);
+            process.exit(1);
+        }
+    });
+}
+//# sourceMappingURL=eval.js.map

package/dist/cli/commands/eval.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"eval.js","sourceRoot":"","sources":["../../../src/cli/commands/eval.ts"],"names":[],"mappings":";;AAGA,kDAwBC;AA1BD,8DAA4E;AAE5E,SAAgB,mBAAmB,CAAC,OAAgB;IAClD,OAAO;SACJ,OAAO,CAAC,MAAM,CAAC;SACf,WAAW,CAAC,4EAA4E,CAAC;SACzF,MAAM,CAAC,UAAU,EAAE,+EAA+E,CAAC;SACnG,MAAM,CAAC,cAAc,EAAE,0DAA0D,CAAC;SAClF,MAAM,CAAC,QAAQ,EAAE,8BAA8B,CAAC;SAChD,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE;QAClB,IAAI,CAAC;YACH,IAAI,CAAC,OAAO,CAAC,MAAM;gBAAE,MAAM,IAAI,KAAK,CAAC,6CAA6C,CAAC,CAAC;YACpF,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,IAAI,IAAA,4BAAe,GAAE,CAAC;YAC7C,MAAM,CAAC,GAAG,IAAA,uBAAU,EAAC,GAAG,CAAC,CAAC;YAC1B,IAAI,OAAO,CAAC,IAAI,EAAE,CAAC;gBAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;gBAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;YAAC,CAAC;YAClG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;YAChB,OAAO,CAAC,GAAG,CAAC,mBAAmB,CAAC,CAAC,OAAO,wBAAwB,CAAC,CAAC;YAClE,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,MAAM;gBAAE,OAAO,CAAC,GAAG,CAAC,+EAA+E,CAAC,CAAC;YACrH,KAAK,MAAM,CAAC,IAAI,CAAC,CAAC,QAAQ;gBAAE,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,KAAK,KAAK,OAAO,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,IAAI,MAAM,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC;YACpH,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;YAChB,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;QACrC,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,OAAO,CAAC,KAAK,CAAC,QAAQ,EAAE,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;YACxE,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;QAClB,CAAC;IACH,CAAC,CAAC,CAAC;AACP,CAAC"}

package/dist/cli/index.js

@@ -17,6 +17,7 @@ const add_flow_1 = require("./commands/add-flow");
 const dashboard_1 = require("./commands/dashboard");
 const audit_1 = require("./commands/audit");
 const ingest_1 = require("./commands/ingest");
+const eval_1 = require("./commands/eval");
 const manifest_1 = require("./commands/manifest");
 const ledger_1 = require("./commands/ledger");
 const feedback_1 = require("./commands/feedback");
@@ -58,6 +59,7 @@ async function main() {
     (0, capability_1.registerCapabilityCommand)(program);
     (0, flow_check_1.registerFlowCheckCommand)(program);
     (0, ingest_1.registerIngestCommand)(program);
+    (0, eval_1.registerEvalCommand)(program);
     await program.parseAsync(process.argv);
 }
 main().catch((error) => {

package/dist/cli/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/cli/index.ts"],"names":[],"mappings":";;AACA;;;GAGG;;AAEH,yCAAoC;AACpC,0CAAsD;AACtD,wCAAoD;AACpD,kDAA8D;AAC9D,kDAA8D;AAC9D,8CAA0D;AAC1D,kDAA8D;AAC9D,4CAAwD;AACxD,kDAA6D;AAC7D,oDAAgE;AAChE,4CAAwD;AACxD,8CAA0D;AAC1D,kDAA8D;AAC9D,8CAA0D;AAC1D,kDAA8D;AAC9D,0DAAqE;AACrE,4CAAwD;AACxD,oDAAgE;AAChE,oDAAgE;AAChE,sDAAkE;AAClE,sDAAiE;AAEjE,wFAAwF;AACxF,MAAM,EAAE,OAAO,EAAE,GAAG,OAAO,CAAC,oBAAoB,CAAwB,CAAC;AAEzE,KAAK,UAAU,IAAI;IACjB,MAAM,OAAO,GAAG,IAAI,mBAAO,EAAE,CAAC;IAE9B,OAAO;SACJ,IAAI,CAAC,QAAQ,CAAC;SACd,WAAW,CAAC,oEAAoE,CAAC;SACjF,OAAO,CAAC,OAAO,CAAC,CAAC;IAEpB,iBAAiB;IACjB,OAAO;SACJ,MAAM,CAAC,eAAe,EAAE,wBAAwB,CAAC,CAAC;IAErD,wBAAwB;IACxB,IAAA,0BAAmB,EAAC,OAAO,CAAC,CAAC;IAC7B,IAAA,wBAAkB,EAAC,OAAO,CAAC,CAAC;IAC5B,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,8BAAqB,EAAC,OAAO,CAAC,CAAC;IAC/B,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,4BAAoB,EAAC,OAAO,CAAC,CAAC;IAC9B,IAAA,iCAAsB,EAAC,OAAO,CAAC,CAAC;IAChC,IAAA,oCAAwB,EAAC,OAAO,CAAC,CAAC;IAClC,IAAA,4BAAoB,EAAC,OAAO,CAAC,CAAC;IAC9B,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,8BAAqB,EAAC,OAAO,CAAC,CAAC;IAC/B,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,yCAA0B,EAAC,OAAO,CAAC,CAAC;IACpC,IAAA,4BAAoB,EAAC,OAAO,CAAC,CAAC;IAC9B,IAAA,oCAAwB,EAAC,OAAO,CAAC,CAAC;IAClC,IAAA,oCAAwB,EAAC,OAAO,CAAC,CAAC;IAClC,IAAA,sCAAyB,EAAC,OAAO,CAAC,CAAC;IACnC,IAAA,qCAAwB,EAAC,OAAO,CAAC,CAAC;IAClC,IAAA,8BAAqB,EAAC,OAAO,CAAC,CAAC;IAE/B,MAAM,OAAO,CAAC,UAAU,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;AACzC,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACrB,OAAO,CAAC,KAAK,CAAC,cAAc,EAAE,KAAK,CAAC,CAAC;IACrC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/cli/index.ts"],"names":[],"mappings":";;AACA;;;GAGG;;AAEH,yCAAoC;AACpC,0CAAsD;AACtD,wCAAoD;AACpD,kDAA8D;AAC9D,kDAA8D;AAC9D,8CAA0D;AAC1D,kDAA8D;AAC9D,4CAAwD;AACxD,kDAA6D;AAC7D,oDAAgE;AAChE,4CAAwD;AACxD,8CAA0D;AAC1D,0CAAsD;AACtD,kDAA8D;AAC9D,8CAA0D;AAC1D,kDAA8D;AAC9D,0DAAqE;AACrE,4CAAwD;AACxD,oDAAgE;AAChE,oDAAgE;AAChE,sDAAkE;AAClE,sDAAiE;AAEjE,wFAAwF;AACxF,MAAM,EAAE,OAAO,EAAE,GAAG,OAAO,CAAC,oBAAoB,CAAwB,CAAC;AAEzE,KAAK,UAAU,IAAI;IACjB,MAAM,OAAO,GAAG,IAAI,mBAAO,EAAE,CAAC;IAE9B,OAAO;SACJ,IAAI,CAAC,QAAQ,CAAC;SACd,WAAW,CAAC,oEAAoE,CAAC;SACjF,OAAO,CAAC,OAAO,CAAC,CAAC;IAEpB,iBAAiB;IACjB,OAAO;SACJ,MAAM,CAAC,eAAe,EAAE,wBAAwB,CAAC,CAAC;IAErD,wBAAwB;IACxB,IAAA,0BAAmB,EAAC,OAAO,CAAC,CAAC;IAC7B,IAAA,wBAAkB,EAAC,OAAO,CAAC,CAAC;IAC5B,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,8BAAqB,EAAC,OAAO,CAAC,CAAC;IAC/B,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,4BAAoB,EAAC,OAAO,CAAC,CAAC;IAC9B,IAAA,iCAAsB,EAAC,OAAO,CAAC,CAAC;IAChC,IAAA,oCAAwB,EAAC,OAAO,CAAC,CAAC;IAClC,IAAA,4BAAoB,EAAC,OAAO,CAAC,CAAC;IAC9B,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,8BAAqB,EAAC,OAAO,CAAC,CAAC;IAC/B,IAAA,kCAAuB,EAAC,OAAO,CAAC,CAAC;IACjC,IAAA,yCAA0B,EAAC,OAAO,CAAC,CAAC;IACpC,IAAA,4BAAoB,EAAC,OAAO,CAAC,CAAC;IAC9B,IAAA,oCAAwB,EAAC,OAAO,CAAC,CAAC;IAClC,IAAA,oCAAwB,EAAC,OAAO,CAAC,CAAC;IAClC,IAAA,sCAAyB,EAAC,OAAO,CAAC,CAAC;IACnC,IAAA,qCAAwB,EAAC,OAAO,CAAC,CAAC;IAClC,IAAA,8BAAqB,EAAC,OAAO,CAAC,CAAC;IAC/B,IAAA,0BAAmB,EAAC,OAAO,CAAC,CAAC;IAE7B,MAAM,OAAO,CAAC,UAAU,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;AACzC,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACrB,OAAO,CAAC,KAAK,CAAC,cAAc,EAAE,KAAK,CAAC,CAAC;IACrC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC"}

package/dist/harness/eval/skill-lint.d.ts

@@ -0,0 +1,16 @@
+export interface SkillLintFinding {
+    level: 'error' | 'warn';
+    file: string;
+    rule: string;
+    detail: string;
+}
+export interface SkillLintResult {
+    checked: number;
+    findings: SkillLintFinding[];
+    errors: number;
+}
+/** Lint the AI-instruction templates in `dir` (default: the sungen source templates). */
+export declare function lintSkills(dir: string): SkillLintResult;
+/** Default templates dir, resolved relative to this module (works from src via tsx and dist). */
+export declare function defaultSkillDir(): string;
+//# sourceMappingURL=skill-lint.d.ts.map

package/dist/harness/eval/skill-lint.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"skill-lint.d.ts","sourceRoot":"","sources":["../../../src/harness/eval/skill-lint.ts"],"names":[],"mappings":"AAiBA,MAAM,WAAW,gBAAgB;IAAG,KAAK,EAAE,OAAO,GAAG,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE;AACzG,MAAM,WAAW,eAAe;IAAG,OAAO,EAAE,MAAM,CAAC;IAAC,QAAQ,EAAE,gBAAgB,EAAE,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE;AAWlG,yFAAyF;AACzF,wBAAgB,UAAU,CAAC,GAAG,EAAE,MAAM,GAAG,eAAe,CAkDvD;AAED,iGAAiG;AACjG,wBAAgB,eAAe,IAAI,MAAM,CAGxC"}

package/dist/harness/eval/skill-lint.js

@@ -0,0 +1,129 @@
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.lintSkills = lintSkills;
+exports.defaultSkillDir = defaultSkillDir;
+/**
+ * Static skill-lint (Eval Harness L1) — deterministic quality checks on Sungen's OWN
+ * AI-instruction templates, so a broken / unregistered / oversized skill fails before it
+ * ships. Learned (generically) from the "static validations" tier of an agent-kit evals
+ * layer. No project data — this lints the sungen package's own templates.
+ *
+ * Design note: the checks are MAPPING-DRIVEN. `AI_RULES_FILE_MAPPING` is the source of
+ * truth for what each template installs as, so the lint uses the install target (does it
+ * end in `/SKILL.md`?) to tell a top-level skill from a sub-content fragment — instead of
+ * guessing from filenames. We deliberately do NOT enforce claude↔github body parity: the
+ * two variants are hand-tuned per platform and intentionally diverge in wording and even
+ * structure, so byte/heading equality would be pure false positives.
+ */
+const fs = __importStar(require("fs"));
+const path = __importStar(require("path"));
+const ai_rules_updater_1 = require("../../orchestrator/ai-rules-updater");
+const LINE_BUDGET = 700; // a skill much larger than this is a context-cost smell (warn)
+const SKILL_RE = /^(claude|github)-skill-/;
+function stripFrontmatter(text) {
+    const m = text.match(/^---\n([\s\S]*?)\n---\n?/);
+    if (!m)
+        return { fm: null, body: text };
+    return { fm: m[1], body: text.slice(m[0].length) };
+}
+/** Lint the AI-instruction templates in `dir` (default: the sungen source templates). */
+function lintSkills(dir) {
+    const findings = [];
+    const files = fs.existsSync(dir) ? fs.readdirSync(dir).filter((f) => f.endsWith('.md')) : [];
+    const skillFiles = files.filter((f) => SKILL_RE.test(f));
+    // mapping: template file -> install target (source of truth for "is this a top-level skill")
+    const target = new Map(ai_rules_updater_1.AI_RULES_FILE_MAPPING.map(([tpl, dst]) => [tpl, dst]));
+    const isTopLevelSkill = (f) => (target.get(f) || '').endsWith('/SKILL.md');
+    // 1) registration integrity (bidirectional) — the highest-value check:
+    //    a skill file missing from the mapping never installs; a mapping to a missing file
+    //    ships a broken/empty skill.
+    for (const f of skillFiles) {
+        if (!target.has(f))
+            findings.push({ level: 'error', file: f, rule: 'unregistered', detail: 'skill template not in AI_RULES_FILE_MAPPING (it would never be installed)' });
+    }
+    for (const [tpl] of ai_rules_updater_1.AI_RULES_FILE_MAPPING) {
+        if (!fs.existsSync(path.join(dir, tpl)))
+            findings.push({ level: 'error', file: tpl, rule: 'mapped-missing', detail: 'AI_RULES_FILE_MAPPING points to a template that does not exist' });
+    }
+    // 2) frontmatter (name + description) — ONLY for top-level skills (SKILL.md targets).
+    //    Sub-content fragments (mode-*.md, group-*.md) are loaded by their parent router
+    //    and legitimately carry no frontmatter.
+    for (const f of skillFiles) {
+        if (!isTopLevelSkill(f))
+            continue;
+        const text = fs.readFileSync(path.join(dir, f), 'utf8');
+        const { fm } = stripFrontmatter(text);
+        if (!fm) {
+            findings.push({ level: 'error', file: f, rule: 'frontmatter', detail: 'top-level skill (SKILL.md) is missing --- frontmatter --- (Claude/Copilot will not load it)' });
+            continue;
+        }
+        if (!/\bname\s*:/.test(fm))
+            findings.push({ level: 'error', file: f, rule: 'frontmatter-name', detail: 'no `name:` in frontmatter' });
+        if (!/\bdescription\s*:/.test(fm))
+            findings.push({ level: 'error', file: f, rule: 'frontmatter-description', detail: 'no `description:` in frontmatter' });
+    }
+    // 3) line budget — context-cost smell (advisory).
+    for (const f of skillFiles) {
+        const lines = fs.readFileSync(path.join(dir, f), 'utf8').split('\n').length;
+        if (lines > LINE_BUDGET)
+            findings.push({ level: 'warn', file: f, rule: 'line-budget', detail: `${lines} lines > ${LINE_BUDGET} (context-cost smell)` });
+    }
+    // 4) variant PRESENCE (not body equality) — every top-level skill should ship for both
+    //    platforms. Catches "added a Claude skill but forgot the Copilot variant". Advisory.
+    const skillName = (dst) => { const m = dst.match(/\/(sungen-[^/]+)\/SKILL\.md$/); return m ? m[1] : null; };
+    const claudeSkills = new Set(), githubSkills = new Set();
+    for (const f of skillFiles) {
+        if (!isTopLevelSkill(f))
+            continue;
+        const name = skillName(target.get(f));
+        if (!name)
+            continue;
+        (f.startsWith('claude-') ? claudeSkills : githubSkills).add(name);
+    }
+    for (const n of claudeSkills)
+        if (!githubSkills.has(n))
+            findings.push({ level: 'warn', file: `claude .../${n}/SKILL.md`, rule: 'variant-missing', detail: `Claude skill "${n}" has no GitHub (Copilot) variant` });
+    for (const n of githubSkills)
+        if (!claudeSkills.has(n))
+            findings.push({ level: 'warn', file: `github .../${n}/SKILL.md`, rule: 'variant-missing', detail: `GitHub skill "${n}" has no Claude variant` });
+    return { checked: skillFiles.length, findings, errors: findings.filter((f) => f.level === 'error').length };
+}
+/** Default templates dir, resolved relative to this module (works from src via tsx and dist). */
+function defaultSkillDir() {
+    // src/harness/eval → src/orchestrator/...  |  dist/harness/eval → dist/orchestrator/...
+    return path.resolve(__dirname, '..', '..', 'orchestrator', 'templates', 'ai-instructions');
+}
+//# sourceMappingURL=skill-lint.js.map

package/dist/harness/eval/skill-lint.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"skill-lint.js","sourceRoot":"","sources":["../../../src/harness/eval/skill-lint.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AA8BA,gCAkDC;AAGD,0CAGC;AAtFD;;;;;;;;;;;;GAYG;AACH,uCAAyB;AACzB,2CAA6B;AAC7B,0EAA4E;AAK5E,MAAM,WAAW,GAAG,GAAG,CAAC,CAAC,+DAA+D;AACxF,MAAM,QAAQ,GAAG,yBAAyB,CAAC;AAE3C,SAAS,gBAAgB,CAAC,IAAY;IACpC,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,0BAA0B,CAAC,CAAC;IACjD,IAAI,CAAC,CAAC;QAAE,OAAO,EAAE,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC;IACxC,OAAO,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,CAAC;AACrD,CAAC;AAED,yFAAyF;AACzF,SAAgB,UAAU,CAAC,GAAW;IACpC,MAAM,QAAQ,GAAuB,EAAE,CAAC;IACxC,MAAM,KAAK,GAAG,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;IAC7F,MAAM,UAAU,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC;IAEzD,6FAA6F;IAC7F,MAAM,MAAM,GAAG,IAAI,GAAG,CAAiB,wCAAqB,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG,EAAE,GAAG,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC;IAC9F,MAAM,eAAe,GAAG,CAAC,CAAS,EAAE,EAAE,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,QAAQ,CAAC,WAAW,CAAC,CAAC;IAEnF,uEAAuE;IACvE,uFAAuF;IACvF,iCAAiC;IACjC,KAAK,MAAM,CAAC,IAAI,UAAU,EAAE,CAAC;QAC3B,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC;YAAE,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,EAAE,cAAc,EAAE,MAAM,EAAE,2EAA2E,EAAE,CAAC,CAAC;IAC5K,CAAC;IACD,KAAK,MAAM,CAAC,GAAG,CAAC,IAAI,wCAAqB,EAAE,CAAC;QAC1C,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC;YAAE,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,EAAE,gBAAgB,EAAE,MAAM,EAAE,gEAAgE,EAAE,CAAC,CAAC;IAC1L,CAAC;IAED,sFAAsF;IACtF,qFAAqF;IACrF,4CAA4C;IAC5C,KAAK,MAAM,CAAC,IAAI,UAAU,EAAE,CAAC;QAC3B,IAAI,CAAC,eAAe,CAAC,CAAC,CAAC;YAAE,SAAS;QAClC,MAAM,IAAI,GAAG,EAAE,CAAC,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC;QACxD,MAAM,EAAE,EAAE,EAAE,GAAG,gBAAgB,CAAC,IAAI,CAAC,CAAC;QACtC,IAAI,CAAC,EAAE,EAAE,CAAC;YAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,EAAE,aAAa,EAAE,MAAM,EAAE,6FAA6F,EAAE,CAAC,CAAC;YAAC,SAAS;QAAC,CAAC;QAC9L,IAAI,CAAC,YAAY,CAAC,IAAI,CAAC,EAAE,CAAC;YAAE,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,EAAE,kBAAkB,EAAE,MAAM,EAAE,2BAA2B,EAAE,CAAC,CAAC;QACtI,IAAI,CAAC,mBAAmB,CAAC,IAAI,CAAC,EAAE,CAAC;YAAE,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,EAAE,yBAAyB,EAAE,MAAM,EAAE,kCAAkC,EAAE,CAAC,CAAC;IAC7J,CAAC;IAED,kDAAkD;IAClD,KAAK,MAAM,CAAC,IAAI,UAAU,EAAE,CAAC;QAC3B,MAAM,KAAK,GAAG,EAAE,CAAC,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,CAAC;QAC5E,IAAI,KAAK,GAAG,WAAW;YAAE,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,EAAE,aAAa,EAAE,MAAM,EAAE,GAAG,KAAK,YAAY,WAAW,uBAAuB,EAAE,CAAC,CAAC;IAC1J,CAAC;IAED,uFAAuF;IACvF,yFAAyF;IACzF,MAAM,SAAS,GAAG,CAAC,GAAW,EAAE,EAAE,GAAG,MAAM,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,8BAA8B,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;IACpH,MAAM,YAAY,GAAG,IAAI,GAAG,EAAU,EAAE,YAAY,GAAG,IAAI,GAAG,EAAU,CAAC;IACzE,KAAK,MAAM,CAAC,IAAI,UAAU,EAAE,CAAC;QAC3B,IAAI,CAAC,eAAe,CAAC,CAAC,CAAC;YAAE,SAAS;QAClC,MAAM,IAAI,GAAG,SAAS,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAE,CAAC,CAAC;QAAC,IAAI,CAAC,IAAI;YAAE,SAAS;QAC5D,CAAC,CAAC,CAAC,UAAU,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;IACpE,CAAC;IACD,KAAK,MAAM,CAAC,IAAI,YAAY;QAAE,IAAI,CAAC,YAAY,CAAC,GAAG,CAAC,CAAC,CAAC;YAAE,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,MAAM,EAAE,IAAI,EAAE,cAAc,CAAC,WAAW,EAAE,IAAI,EAAE,iBAAiB,EAAE,MAAM,EAAE,iBAAiB,CAAC,mCAAmC,EAAE,CAAC,CAAC;IACnN,KAAK,MAAM,CAAC,IAAI,YAAY;QAAE,IAAI,CAAC,YAAY,CAAC,GAAG,CAAC,CAAC,CAAC;YAAE,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,MAAM,EAAE,IAAI,EAAE,cAAc,CAAC,WAAW,EAAE,IAAI,EAAE,iBAAiB,EAAE,MAAM,EAAE,iBAAiB,CAAC,yBAAyB,EAAE,CAAC,CAAC;IAEzM,OAAO,EAAE,OAAO,EAAE,UAAU,CAAC,MAAM,EAAE,QAAQ,EAAE,MAAM,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,KAAK,OAAO,CAAC,CAAC,MAAM,EAAE,CAAC;AAC9G,CAAC;AAED,iGAAiG;AACjG,SAAgB,eAAe;IAC7B,wFAAwF;IACxF,OAAO,IAAI,CAAC,OAAO,CAAC,SAAS,EAAE,IAAI,EAAE,IAAI,EAAE,cAAc,EAAE,WAAW,EAAE,iBAAiB,CAAC,CAAC;AAC7F,CAAC"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sun-asterisk/sungen",
-  "version": "3.0.0-beta.81",
+  "version": "3.0.0-beta.82",
   "description": "Deterministic E2E Test Compiler - Gherkin + Selectors → Playwright tests",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -12,7 +12,7 @@
     "copy-templates": "mkdir -p dist/generators/test-generator/adapters/playwright/templates/steps && mkdir -p dist/generators/test-generator/templates && mkdir -p dist/orchestrator/templates && mkdir -p dist/dashboard/templates && cp -r src/generators/test-generator/adapters/playwright/templates/*.hbs dist/generators/test-generator/adapters/playwright/templates/ 2>/dev/null || true && cp -r src/generators/test-generator/adapters/playwright/templates/steps dist/generators/test-generator/adapters/playwright/templates/ && cp src/generators/test-generator/templates/*.hbs dist/generators/test-generator/templates/ 2>/dev/null || true && cp -r src/orchestrator/templates/* dist/orchestrator/templates/ && cp src/dashboard/templates/index.html dist/dashboard/templates/index.html && mkdir -p dist/harness/catalog && cp src/harness/catalog/*.yaml dist/harness/catalog/",
     "build:dashboard": "cd dashboard && npm install --silent && npm run build && cd .. && cp dashboard/dist/index.html src/dashboard/templates/index.html",
     "dev": "tsx src/cli/index.ts",
-    "test": "tsx tests/golden/run.ts && tsx tests/audit/run.ts && tsx tests/ingest/run.ts",
+    "test": "tsx tests/golden/run.ts && tsx tests/audit/run.ts && tsx tests/ingest/run.ts && tsx tests/eval/run.ts",
     "test:update": "tsx tests/golden/run.ts --update && tsx tests/audit/run.ts --update && tsx tests/ingest/run.ts --update",
     "prepublishOnly": "npm run build:dashboard && npm run build"
   },

package/src/cli/commands/eval.ts

@@ -0,0 +1,28 @@
+import { Command } from 'commander';
+import { lintSkills, defaultSkillDir } from '../../harness/eval/skill-lint';
+
+export function registerEvalCommand(program: Command): void {
+  program
+    .command('eval')
+    .description('Eval harness: quality checks on Sungen\'s own skills/instructions (dev/CI)')
+    .option('--skills', 'Static skill-lint: frontmatter, line budget, claude↔github sync, registration')
+    .option('--dir <path>', 'Templates dir to lint (default: bundled ai-instructions)')
+    .option('--json', 'Output the raw findings JSON')
+    .action((options) => {
+      try {
+        if (!options.skills) throw new Error('Provide --skills (the only eval mode today)');
+        const dir = options.dir || defaultSkillDir();
+        const r = lintSkills(dir);
+        if (options.json) { console.log(JSON.stringify(r, null, 2)); process.exit(r.errors > 0 ? 2 : 0); }
+        console.log('');
+        console.log(`━━━ Skill-lint: ${r.checked} skill template(s) ━━━`);
+        if (!r.findings.length) console.log('  ✓ all skills pass (frontmatter · line-budget · variant-sync · registration)');
+        for (const f of r.findings) console.log(`  ${f.level === 'error' ? '✗' : '⚠'} [${f.rule}] ${f.file} — ${f.detail}`);
+        console.log('');
+        process.exit(r.errors > 0 ? 2 : 0);
+      } catch (error) {
+        console.error('Error:', error instanceof Error ? error.message : error);
+        process.exit(1);
+      }
+    });
+}

package/src/cli/index.ts

@@ -16,6 +16,7 @@ import { registerAddFlowCommand } from './commands/add-flow';
 import { registerDashboardCommand } from './commands/dashboard';
 import { registerAuditCommand } from './commands/audit';
 import { registerIngestCommand } from './commands/ingest';
+import { registerEvalCommand } from './commands/eval';
 import { registerManifestCommand } from './commands/manifest';
 import { registerLedgerCommand } from './commands/ledger';
 import { registerFeedbackCommand } from './commands/feedback';
@@ -62,6 +63,7 @@ async function main() {
   registerCapabilityCommand(program);
   registerFlowCheckCommand(program);
   registerIngestCommand(program);
+  registerEvalCommand(program);
 
   await program.parseAsync(process.argv);
 }

package/src/harness/eval/skill-lint.ts

@@ -0,0 +1,87 @@
+/**
+ * Static skill-lint (Eval Harness L1) — deterministic quality checks on Sungen's OWN
+ * AI-instruction templates, so a broken / unregistered / oversized skill fails before it
+ * ships. Learned (generically) from the "static validations" tier of an agent-kit evals
+ * layer. No project data — this lints the sungen package's own templates.
+ *
+ * Design note: the checks are MAPPING-DRIVEN. `AI_RULES_FILE_MAPPING` is the source of
+ * truth for what each template installs as, so the lint uses the install target (does it
+ * end in `/SKILL.md`?) to tell a top-level skill from a sub-content fragment — instead of
+ * guessing from filenames. We deliberately do NOT enforce claude↔github body parity: the
+ * two variants are hand-tuned per platform and intentionally diverge in wording and even
+ * structure, so byte/heading equality would be pure false positives.
+ */
+import * as fs from 'fs';
+import * as path from 'path';
+import { AI_RULES_FILE_MAPPING } from '../../orchestrator/ai-rules-updater';
+
+export interface SkillLintFinding { level: 'error' | 'warn'; file: string; rule: string; detail: string }
+export interface SkillLintResult { checked: number; findings: SkillLintFinding[]; errors: number }
+
+const LINE_BUDGET = 700; // a skill much larger than this is a context-cost smell (warn)
+const SKILL_RE = /^(claude|github)-skill-/;
+
+function stripFrontmatter(text: string): { fm: string | null; body: string } {
+  const m = text.match(/^---\n([\s\S]*?)\n---\n?/);
+  if (!m) return { fm: null, body: text };
+  return { fm: m[1], body: text.slice(m[0].length) };
+}
+
+/** Lint the AI-instruction templates in `dir` (default: the sungen source templates). */
+export function lintSkills(dir: string): SkillLintResult {
+  const findings: SkillLintFinding[] = [];
+  const files = fs.existsSync(dir) ? fs.readdirSync(dir).filter((f) => f.endsWith('.md')) : [];
+  const skillFiles = files.filter((f) => SKILL_RE.test(f));
+
+  // mapping: template file -> install target (source of truth for "is this a top-level skill")
+  const target = new Map<string, string>(AI_RULES_FILE_MAPPING.map(([tpl, dst]) => [tpl, dst]));
+  const isTopLevelSkill = (f: string) => (target.get(f) || '').endsWith('/SKILL.md');
+
+  // 1) registration integrity (bidirectional) — the highest-value check:
+  //    a skill file missing from the mapping never installs; a mapping to a missing file
+  //    ships a broken/empty skill.
+  for (const f of skillFiles) {
+    if (!target.has(f)) findings.push({ level: 'error', file: f, rule: 'unregistered', detail: 'skill template not in AI_RULES_FILE_MAPPING (it would never be installed)' });
+  }
+  for (const [tpl] of AI_RULES_FILE_MAPPING) {
+    if (!fs.existsSync(path.join(dir, tpl))) findings.push({ level: 'error', file: tpl, rule: 'mapped-missing', detail: 'AI_RULES_FILE_MAPPING points to a template that does not exist' });
+  }
+
+  // 2) frontmatter (name + description) — ONLY for top-level skills (SKILL.md targets).
+  //    Sub-content fragments (mode-*.md, group-*.md) are loaded by their parent router
+  //    and legitimately carry no frontmatter.
+  for (const f of skillFiles) {
+    if (!isTopLevelSkill(f)) continue;
+    const text = fs.readFileSync(path.join(dir, f), 'utf8');
+    const { fm } = stripFrontmatter(text);
+    if (!fm) { findings.push({ level: 'error', file: f, rule: 'frontmatter', detail: 'top-level skill (SKILL.md) is missing --- frontmatter --- (Claude/Copilot will not load it)' }); continue; }
+    if (!/\bname\s*:/.test(fm)) findings.push({ level: 'error', file: f, rule: 'frontmatter-name', detail: 'no `name:` in frontmatter' });
+    if (!/\bdescription\s*:/.test(fm)) findings.push({ level: 'error', file: f, rule: 'frontmatter-description', detail: 'no `description:` in frontmatter' });
+  }
+
+  // 3) line budget — context-cost smell (advisory).
+  for (const f of skillFiles) {
+    const lines = fs.readFileSync(path.join(dir, f), 'utf8').split('\n').length;
+    if (lines > LINE_BUDGET) findings.push({ level: 'warn', file: f, rule: 'line-budget', detail: `${lines} lines > ${LINE_BUDGET} (context-cost smell)` });
+  }
+
+  // 4) variant PRESENCE (not body equality) — every top-level skill should ship for both
+  //    platforms. Catches "added a Claude skill but forgot the Copilot variant". Advisory.
+  const skillName = (dst: string) => { const m = dst.match(/\/(sungen-[^/]+)\/SKILL\.md$/); return m ? m[1] : null; };
+  const claudeSkills = new Set<string>(), githubSkills = new Set<string>();
+  for (const f of skillFiles) {
+    if (!isTopLevelSkill(f)) continue;
+    const name = skillName(target.get(f)!); if (!name) continue;
+    (f.startsWith('claude-') ? claudeSkills : githubSkills).add(name);
+  }
+  for (const n of claudeSkills) if (!githubSkills.has(n)) findings.push({ level: 'warn', file: `claude .../${n}/SKILL.md`, rule: 'variant-missing', detail: `Claude skill "${n}" has no GitHub (Copilot) variant` });
+  for (const n of githubSkills) if (!claudeSkills.has(n)) findings.push({ level: 'warn', file: `github .../${n}/SKILL.md`, rule: 'variant-missing', detail: `GitHub skill "${n}" has no Claude variant` });
+
+  return { checked: skillFiles.length, findings, errors: findings.filter((f) => f.level === 'error').length };
+}
+
+/** Default templates dir, resolved relative to this module (works from src via tsx and dist). */
+export function defaultSkillDir(): string {
+  // src/harness/eval → src/orchestrator/...  |  dist/harness/eval → dist/orchestrator/...
+  return path.resolve(__dirname, '..', '..', 'orchestrator', 'templates', 'ai-instructions');
+}