oh-my-customcode 0.3.2 → 0.5.0

package/README.md

@@ -16,7 +16,7 @@ Like oh-my-zsh transformed shell customization, oh-my-customcode makes personali
 
 | Feature | Description |
 |---------|-------------|
-| **Batteries Included** | 34 agents, 42 skills, 13 guides - synced with baekgom-agents templates |
+| **Batteries Included** | 34 agents, 41 skills, 14 guides - ready to use out of the box |
 | **Sub-Agent Model** | Supports hierarchical agent orchestration with specialized roles |
 | **Dead Simple Customization** | Create a folder + markdown file = new agent or skill |
 | **Mix and Match** | Use built-in components, create your own, or combine both |
@@ -94,45 +94,19 @@ Claude Code selects the appropriate model and parallelizes independent tasks (up
 |---------|-------|-------------|
 | `/create-agent <name>` | mgr-creator | Create a new agent |
 | `/update-docs` | mgr-updater | Sync docs with project structure |
-| `/audit-dependencies` | mgr-supplier | Verify agent dependencies |
-| `/code-review` | lang-* experts | Review code with expert agents |
-| `/run-pipeline <name>` | pipeline skill | Execute a workflow pipeline |
-| `/sync-check` | mgr-sync-checker | Full synchronization check |
-
-### Custom Pipelines
-
-Define repeatable multi-agent workflows:
-
-```yaml
-# .claude/skills/pipelines/deploy-review.yaml
-name: deploy-review
-steps:
-  - id: security_scan
-    agent: qa-planner
-    action: security_review
-
-  - id: performance_check
-    agent: tool-optimizer
-    action: analyze_performance
-
-  - id: migration_review
-    agent: db-migration-expert
-    action: review_migrations
-```
-
-Run it: `/run-pipeline deploy-review`
+| `/audit-agents` | mgr-supplier | Verify agent dependencies |
+| `/dev-review` | lang-* experts | Review code with expert agents |
+| `/sauron-watch` | mgr-sauron | Full synchronization check |
 
 ---
 
 ## What's Included
 
-> **Templates synced from [baekgom-agents](https://github.com/baekenough/baekgom-agents)** - Battle-tested agent system with sub-agent orchestration support.
-
 ### Agents (34)
 
 | Category | Count | Agents |
 |----------|-------|--------|
-| **Managers** | 6 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sync-checker, mgr-sauron |
+| **Managers** | 7 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sync-checker, mgr-sauron, mgr-claude-code-bible |
 | **System** | 2 | sys-memory-keeper, sys-naggy |
 | **Languages** | 6 | lang-golang-expert, lang-python-expert, lang-rust-expert, lang-kotlin-expert, lang-typescript-expert, lang-java21-expert |
 | **Frontend** | 3 | fe-vercel-agent, fe-vuejs-agent, fe-svelte-agent |
@@ -142,10 +116,9 @@ Run it: `/run-pipeline deploy-review`
 | **Architecture** | 2 | arch-documenter, arch-speckit-agent |
 | **Infrastructure** | 2 | infra-docker-expert, infra-aws-expert |
 | **QA** | 3 | qa-planner, qa-writer, qa-engineer |
-| **Tutor** | 1 | tutor-go |
 | **Total** | **34** | |
 
-### Skills (42)
+### Skills (41)
 
 Includes slash commands and capabilities:
 
@@ -156,7 +129,7 @@ Includes slash commands and capabilities:
 - **Orchestration** (2): Pipeline execution, intent detection
 - **Slash Commands** (20+): /create-agent, /code-review, /audit-dependencies, /sync-check, /commit, /pr, and more
 
-### Guides (13)
+### Guides (14)
 
 Comprehensive reference documentation covering:
 - Agent creation and management
@@ -165,13 +138,13 @@ Comprehensive reference documentation covering:
 - Best practices and patterns
 - Sub-agent orchestration
 
-### Rules (18)
+### Rules (17)
 
 | Priority | Count | Purpose |
 |----------|-------|---------|
-| **MUST** | 10 | Safety, permissions, agent design (enforced) |
-| **SHOULD** | 6 | Interactions, error handling (recommended) |
-| **MAY** | 2 | Optimization guidelines (optional) |
+| **MUST** | 11 | Safety, permissions, agent design (enforced) |
+| **SHOULD** | 5 | Interactions, error handling (recommended) |
+| **MAY** | 1 | Optimization guidelines (optional) |
 
 ---
 
@@ -197,7 +170,7 @@ After `omcustom init`:
 your-project/
 ├── CLAUDE.md              # Entry point for Claude
 └── .claude/
-    ├── rules/             # Behavior rules (18 total)
+    ├── rules/             # Behavior rules (17 total)
     ├── hooks/             # Event hooks
     ├── contexts/          # Context files
     ├── agents/            # All agents (flat structure, 34 total)
@@ -205,13 +178,13 @@ your-project/
     │   ├── be-fastapi-expert/
     │   ├── mgr-creator/
     │   └── ...
-    ├── skills/            # All skills (42 total, includes slash commands)
+    ├── skills/            # All skills (41 total, includes slash commands)
     │   ├── development/
     │   ├── backend/
     │   ├── infrastructure/
     │   ├── system/
     │   └── orchestration/
-    └── guides/            # Reference docs (13 total)
+    └── guides/            # Reference docs (14 total)
 ```
 
 ---
@@ -230,32 +203,6 @@ bun run build        # Build for production
 - Node.js >= 18.0.0
 - Claude Code CLI
 
-### Sync Verification
-
-oh-my-customcode templates are synced from [baekgom-agents](https://github.com/baekenough/baekgom-agents). To verify templates are in sync:
-
-```bash
-# Local verification (requires baekgom-agents checkout)
-./scripts/verify-sync.sh /path/to/baekgom-agents
-
-# Or using environment variable
-BAEKGOM_AGENTS_PATH=/path/to/baekgom-agents ./scripts/verify-sync.sh
-```
-
-The verification checks 7 content directories:
-- `.claude/agents/` (34 agents)
-- `.claude/skills/` (42 skills)
-- `.claude/rules/` (18 rules)
-- `.claude/hooks/`
-- `.claude/contexts/`
-- `guides/`
-- `pipelines/`
-
-CI automatically runs sync verification on:
-- Push to main (when templates change)
-- Weekly schedule (Monday 00:00 UTC)
-- Manual workflow dispatch
-
 ---
 
 ## Contributing

package/dist/cli/index.js

@@ -12314,24 +12314,6 @@ async function checkHooks(targetDir) {
     fixable: false
   };
 }
-async function checkPipelines(targetDir) {
-  const pipelinesDir = path.join(targetDir, "pipelines");
-  const exists2 = await isDirectory(pipelinesDir);
-  if (!exists2) {
-    return {
-      name: "Pipelines",
-      status: "fail",
-      message: "pipelines/ directory not found",
-      fixable: true
-    };
-  }
-  return {
-    name: "Pipelines",
-    status: "pass",
-    message: "Pipelines OK",
-    fixable: false
-  };
-}
 async function checkContexts(targetDir) {
   const contextsDir = path.join(targetDir, ".claude", "contexts");
   const exists2 = await isDirectory(contextsDir);
@@ -12384,7 +12366,6 @@ async function fixSingleIssue(check, targetDir) {
     Skills: () => createMissingDirectory(path.join(targetDir, ".claude", "skills")),
     Guides: () => createMissingDirectory(path.join(targetDir, "guides")),
     Hooks: () => createMissingDirectory(path.join(targetDir, ".claude", "hooks")),
-    Pipelines: () => createMissingDirectory(path.join(targetDir, "pipelines")),
     Contexts: () => createMissingDirectory(path.join(targetDir, ".claude", "contexts")),
     Symlinks: async () => {
       if (!check.details || check.details.length === 0)
@@ -12441,7 +12422,6 @@ async function doctorCommand(options = {}) {
     checkIndexFiles(targetDir),
     checkGuides(targetDir),
     checkHooks(targetDir),
-    checkPipelines(targetDir),
     checkContexts(targetDir)
   ]);
   if (options.fix) {
@@ -12828,7 +12808,7 @@ function getDefaultConfig() {
     componentVersions: {},
     agents: {},
     preferences: getDefaultPreferences(),
-    sourceRepo: "https://github.com/baekenough/baekgom-agents",
+    sourceRepo: "https://github.com/baekenough/oh-my-customcode",
     autoUpdate: {
       enabled: false,
       checkIntervalHours: 24,
@@ -12907,25 +12887,12 @@ function migrateConfig(config) {
 }
 
 // src/core/installer.ts
-var DIRECTORY_STRUCTURE = [
-  ".claude",
-  ".claude/rules",
-  ".claude/hooks",
-  ".claude/contexts",
-  ".claude/agents",
-  ".claude/skills",
-  "guides",
-  "pipelines",
-  "pipelines/templates",
-  "pipelines/examples"
-];
 var COMPONENT_PATHS = {
   "claude-md": "",
   rules: ".claude/rules",
   agents: ".claude/agents",
   skills: ".claude/skills",
   guides: "guides",
-  pipelines: "pipelines",
   hooks: ".claude/hooks",
   contexts: ".claude/contexts"
 };
@@ -13017,8 +12984,6 @@ async function install(options) {
     await handleBackup(options.targetDir, !!options.backup, result);
     await checkAndWarnExisting(options.targetDir, !!options.force, !!options.backup, result);
     await verifyTemplateDirectory();
-    await createDirectoryStructure(options.targetDir);
-    debug("install.directories_created");
     await installAllComponents(options.targetDir, options, result);
     await installClaudeMdWithTracking(options.targetDir, options, result);
     await updateInstallConfig(options.targetDir, options, result.installedComponents);
@@ -13031,14 +12996,8 @@ async function install(options) {
   }
   return result;
 }
-async function createDirectoryStructure(targetDir) {
-  for (const dir2 of DIRECTORY_STRUCTURE) {
-    const fullPath = join3(targetDir, dir2);
-    await ensureDirectory(fullPath);
-  }
-}
 function getAllComponents() {
-  return ["rules", "agents", "skills", "guides", "pipelines", "hooks", "contexts"];
+  return ["rules", "agents", "skills", "guides", "hooks", "contexts"];
 }
 async function installComponent(targetDir, component, options) {
   const templatePath = COMPONENT_PATHS[component];
@@ -13088,7 +13047,7 @@ async function backupExisting(sourcePath, backupDir) {
   return backupPath;
 }
 async function checkExistingPaths(targetDir) {
-  const pathsToCheck = ["CLAUDE.md", ".claude", "guides", "pipelines"];
+  const pathsToCheck = ["CLAUDE.md", ".claude", "guides"];
   const existingPaths = [];
   for (const relativePath of pathsToCheck) {
     const fullPath = join3(targetDir, relativePath);
@@ -13126,7 +13085,7 @@ async function checkExistingInstallation(targetDir) {
   const claudeDir = join4(targetDir, ".claude");
   return fileExists(claudeDir);
 }
-var CLAUDE_SUBDIR_COMPONENTS = new Set(["rules", "hooks", "contexts"]);
+var CLAUDE_SUBDIR_COMPONENTS = new Set(["rules", "hooks", "contexts", "agents", "skills"]);
 function componentToPath(targetDir, component) {
   if (component === "claude-md") {
     return join4(targetDir, "CLAUDE.md");
@@ -13541,30 +13500,13 @@ async function getContexts(targetDir) {
     return [];
   }
 }
-async function getPipelines(targetDir) {
-  const pipelinesDir = join5(targetDir, "pipelines");
-  if (!await fileExists(pipelinesDir))
-    return [];
-  try {
-    const pipelineFiles = await listFiles(pipelinesDir, { recursive: true, pattern: "*.yaml" });
-    return pipelineFiles.map((pipePath) => ({
-      name: basename2(pipePath, ".yaml"),
-      type: "pipeline",
-      category: relative(join5(targetDir, "pipelines"), dirname2(pipePath)) || "root",
-      path: relative(targetDir, pipePath)
-    })).sort((a, b) => a.name.localeCompare(b.name));
-  } catch {
-    return [];
-  }
-}
 var COMPONENT_GETTERS = {
   agents: getAgents,
   skills: getSkills,
   guides: getGuides,
   rules: getRules,
   hooks: getHooks,
-  contexts: getContexts,
-  pipelines: getPipelines
+  contexts: getContexts
 };
 function displayComponents(components, type, format) {
   if (format === "json") {
@@ -13576,14 +13518,13 @@ function displayComponents(components, type, format) {
   }
 }
 async function handleListAll(targetDir, format) {
-  const [agents, skills, guides, rules, hooks, contexts, pipelines] = await Promise.all([
+  const [agents, skills, guides, rules, hooks, contexts] = await Promise.all([
     getAgents(targetDir),
     getSkills(targetDir),
     getGuides(targetDir),
     getRules(targetDir),
     getHooks(targetDir),
-    getContexts(targetDir),
-    getPipelines(targetDir)
+    getContexts(targetDir)
   ]);
   if (format !== "json") {
     displayComponents(agents, "agents", format);
@@ -13592,9 +13533,8 @@ async function handleListAll(targetDir, format) {
     displayComponents(rules, "rules", format);
     displayComponents(hooks, "hooks", format);
     displayComponents(contexts, "contexts", format);
-    displayComponents(pipelines, "pipelines", format);
   }
-  return [...agents, ...skills, ...guides, ...rules, ...hooks, ...contexts, ...pipelines];
+  return [...agents, ...skills, ...guides, ...rules, ...hooks, ...contexts];
 }
 async function listCommand(type = "all", options = {}) {
   const targetDir = process.cwd();

package/dist/index.js

@@ -1,4 +1,20 @@
 import { createRequire } from "node:module";
+var __create = Object.create;
+var __getProtoOf = Object.getPrototypeOf;
+var __defProp = Object.defineProperty;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __toESM = (mod, isNodeMode, target) => {
+  target = mod != null ? __create(__getProtoOf(mod)) : {};
+  const to = isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target;
+  for (let key of __getOwnPropNames(mod))
+    if (!__hasOwnProp.call(to, key))
+      __defProp(to, key, {
+        get: () => mod[key],
+        enumerable: true
+      });
+  return to;
+};
 var __require = /* @__PURE__ */ createRequire(import.meta.url);
 
 // src/core/config.ts
@@ -321,7 +337,7 @@ function getDefaultConfig() {
     componentVersions: {},
     agents: {},
     preferences: getDefaultPreferences(),
-    sourceRepo: "https://github.com/baekenough/baekgom-agents",
+    sourceRepo: "https://github.com/baekenough/oh-my-customcode",
     autoUpdate: {
       enabled: false,
       checkIntervalHours: 24,
@@ -408,10 +424,7 @@ var DIRECTORY_STRUCTURE = [
   ".claude/contexts",
   ".claude/agents",
   ".claude/skills",
-  "guides",
-  "pipelines",
-  "pipelines/templates",
-  "pipelines/examples"
+  "guides"
 ];
 var COMPONENT_PATHS = {
   "claude-md": "",
@@ -419,7 +432,6 @@ var COMPONENT_PATHS = {
   agents: ".claude/agents",
   skills: ".claude/skills",
   guides: "guides",
-  pipelines: "pipelines",
   hooks: ".claude/hooks",
   contexts: ".claude/contexts"
 };
@@ -511,8 +523,6 @@ async function install(options) {
     await handleBackup(options.targetDir, !!options.backup, result);
     await checkAndWarnExisting(options.targetDir, !!options.force, !!options.backup, result);
     await verifyTemplateDirectory();
-    await createDirectoryStructure(options.targetDir);
-    debug("install.directories_created");
     await installAllComponents(options.targetDir, options, result);
     await installClaudeMdWithTracking(options.targetDir, options, result);
     await updateInstallConfig(options.targetDir, options, result.installedComponents);
@@ -555,11 +565,11 @@ async function getTemplateManifest() {
       description: `${name} component`,
       files: 0
     })),
-    source: "https://github.com/baekenough/baekgom-agents"
+    source: "https://github.com/baekenough/oh-my-customcode"
   };
 }
 function getAllComponents() {
-  return ["rules", "agents", "skills", "guides", "pipelines", "hooks", "contexts"];
+  return ["rules", "agents", "skills", "guides", "hooks", "contexts"];
 }
 async function installComponent(targetDir, component, options) {
   const templatePath = COMPONENT_PATHS[component];
@@ -609,7 +619,7 @@ async function backupExisting(sourcePath, backupDir) {
   return backupPath;
 }
 async function checkExistingPaths(targetDir) {
-  const pathsToCheck = ["CLAUDE.md", ".claude", "guides", "pipelines"];
+  const pathsToCheck = ["CLAUDE.md", ".claude", "guides"];
   const existingPaths = [];
   for (const relativePath of pathsToCheck) {
     const fullPath = join3(targetDir, relativePath);
@@ -764,7 +774,7 @@ async function preserveCustomizations(targetDir, customizations) {
   return preserved;
 }
 function getAllUpdateComponents() {
-  return ["rules", "agents", "skills", "guides", "pipelines", "hooks", "contexts"];
+  return ["rules", "agents", "skills", "guides", "hooks", "contexts"];
 }
 async function getLatestVersion() {
   const manifestPath = resolveTemplatePath("manifest.json");
@@ -812,7 +822,6 @@ function getComponentPath(component) {
     agents: ".claude/agents",
     skills: ".claude/skills",
     guides: "guides",
-    pipelines: "pipelines",
     hooks: ".claude/hooks",
     contexts: ".claude/contexts"
   };
@@ -823,7 +832,7 @@ async function backupInstallation(targetDir) {
   const backupDir = join4(targetDir, `.omcustom-backup-${timestamp}`);
   const fs = await import("node:fs/promises");
   await ensureDirectory(backupDir);
-  const dirsToBackup = [".claude", "guides", "pipelines"];
+  const dirsToBackup = [".claude", "guides"];
   for (const dir of dirsToBackup) {
     const srcPath = join4(targetDir, dir);
     if (await fileExists(srcPath)) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-customcode",
-  "version": "0.3.2",
+  "version": "0.5.0",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {
@@ -46,8 +46,13 @@
     "yaml": "^2.8.2"
   },
   "devDependencies": {
+    "@anthropic-ai/sdk": "^0.39.0",
     "@biomejs/biome": "^2.3.12",
     "@types/bun": "^1.3.6",
+    "@types/js-yaml": "^4.0.9",
+    "@types/nodemailer": "^6.4.17",
+    "js-yaml": "^4.1.0",
+    "nodemailer": "^6.10.1",
     "typescript": "^5.7.3",
     "vitepress": "^1.6.3"
   },

package/templates/.claude/agents/arch-documenter.md

@@ -2,6 +2,9 @@
 name: arch-documenter
 description: Use for generating architecture documentation, API specifications (OpenAPI), Architecture Decision Records (ADRs), technical diagrams (Mermaid/PlantUML), and README maintenance
 model: sonnet
+memory: project
+effort: high
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/arch-speckit-agent.md

@@ -2,6 +2,9 @@
 name: arch-speckit-agent
 description: Use for spec-driven development, transforming requirements into executable specifications, defining project constitution, creating technical plans, and generating TDD task lists
 model: sonnet
+memory: project
+effort: high
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/be-express-expert.md

@@ -2,6 +2,9 @@
 name: be-express-expert
 description: Expert Express.js developer for production-ready Node.js APIs following security best practices and 12-factor app principles. Use for Express.js APIs, REST API architectures, middleware chains, authentication/authorization, security hardening, and Node.js performance optimization.
 model: sonnet
+memory: project
+effort: high
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/be-fastapi-expert.md

@@ -2,6 +2,10 @@
 name: be-fastapi-expert
 description: Expert FastAPI developer for building high-performance async Python APIs. Use for FastAPI projects, Python async/await patterns, Pydantic models, API architecture design, and performance optimization.
 model: sonnet
+memory: project
+effort: high
+skills:
+  - fastapi-best-practices
 tools:
   - Read
   - Write

package/templates/.claude/agents/be-go-backend-expert.md

@@ -2,6 +2,10 @@
 name: be-go-backend-expert
 description: Expert Go backend developer for production-ready services following Uber style guide and standard layout. Use for Go backend services, HTTP/gRPC servers, microservices in Go, concurrent systems, and Go performance optimization.
 model: sonnet
+memory: project
+effort: high
+skills:
+  - go-backend-best-practices
 tools:
   - Read
   - Write

package/templates/.claude/agents/be-nestjs-expert.md

@@ -2,6 +2,9 @@
 name: be-nestjs-expert
 description: Expert NestJS developer for opinionated, scalable Node.js applications with TypeScript. Use for NestJS projects, decorator-based patterns (@Injectable, @Module, @Controller), enterprise API architectures, authentication/authorization guards, DTO validation, and modular architecture.
 model: sonnet
+memory: project
+effort: high
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/be-springboot-expert.md

@@ -2,6 +2,10 @@
 name: be-springboot-expert
 description: Expert Spring Boot 3.5.x developer for enterprise-grade Java 21 applications. Use for Spring Boot projects, Java/Kotlin enterprise apps, RESTful APIs, microservices architecture, Spring Data, security patterns, virtual threads, and GraalVM native images.
 model: sonnet
+memory: project
+effort: high
+skills:
+  - springboot-best-practices
 tools:
   - Read
   - Write

package/templates/.claude/agents/db-supabase-expert.md

@@ -2,6 +2,8 @@
 name: db-supabase-expert
 description: Supabase and PostgreSQL expert. Use when working with Supabase projects, writing SQL queries, designing database schemas, configuring Row-Level Security (RLS), optimizing Postgres performance, or managing connection pooling. Handles .sql files and Supabase configuration.
 model: sonnet
+memory: user
+effort: high
 tools:
   - Read
   - Write

package/templates/.claude/agents/fe-svelte-agent.md

@@ -2,6 +2,9 @@
 name: fe-svelte-agent
 description: Use for Svelte compiler-based reactivity, reactive statements ($:), Svelte stores, and SvelteKit full-stack development with SSR
 model: sonnet
+memory: project
+effort: medium
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/fe-vercel-agent.md

@@ -2,6 +2,12 @@
 name: fe-vercel-agent
 description: Use for React/Next.js optimization, web design review (accessibility, UX), Vercel deployment automation, and bundle size optimization
 model: sonnet
+memory: project
+effort: medium
+skills:
+  - react-best-practices
+  - web-design-guidelines
+  - vercel-deploy
 tools:
   - Read
   - Write

package/templates/.claude/agents/fe-vuejs-agent.md

@@ -2,6 +2,9 @@
 name: fe-vuejs-agent
 description: Use for Vue 3 Composition API development, single-file components, Pinia state management, and Vue Router navigation
 model: sonnet
+memory: project
+effort: medium
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/infra-aws-expert.md

@@ -2,6 +2,10 @@
 name: infra-aws-expert
 description: Use for AWS architecture design with Well-Architected Framework, infrastructure as code (CloudFormation/CDK/Terraform), VPC networking, IAM security, and cost optimization
 model: sonnet
+memory: user
+effort: high
+skills:
+  - aws-best-practices
 tools:
   - Read
   - Write

package/templates/.claude/agents/infra-docker-expert.md

@@ -2,6 +2,10 @@
 name: infra-docker-expert
 description: Use for creating optimized Dockerfiles, multi-stage builds, container security hardening, Docker Compose configurations, and image size optimization
 model: sonnet
+memory: user
+effort: medium
+skills:
+  - docker-best-practices
 tools:
   - Read
   - Write

package/templates/.claude/agents/lang-golang-expert.md

@@ -2,6 +2,10 @@
 name: lang-golang-expert
 description: Expert Go developer for writing idiomatic, performant Go code. Use for Go files (*.go, go.mod, go.sum), Go-related keywords, implementing concurrent systems, reviewing Go code, and optimizing Go applications.
 model: sonnet
+memory: project
+effort: high
+skills:
+  - go-best-practices
 tools:
   - Read
   - Write

package/templates/.claude/agents/lang-java21-expert.md

@@ -2,6 +2,9 @@
 name: lang-java21-expert
 description: Expert Java 21 developer for modern Java with Virtual Threads, Pattern Matching, Record Patterns, and Sequenced Collections. Use for Java files (*.java, pom.xml, build.gradle), Java-related keywords, high-concurrency systems, data-centric APIs with Records, and migrating from older Java versions.
 model: sonnet
+memory: project
+effort: high
+skills: []
 tools:
   - Read
   - Write

package/templates/.claude/agents/lang-kotlin-expert.md

@@ -2,6 +2,10 @@
 name: lang-kotlin-expert
 description: Expert Kotlin developer for writing idiomatic, concise, null-safe Kotlin code. Use for Kotlin files (*.kt, *.kts), Kotlin-related keywords, Android development, Kotlin multiplatform projects, and migrating Java to Kotlin.
 model: sonnet
+memory: project
+effort: high
+skills:
+  - kotlin-best-practices
 tools:
   - Read
   - Write

package/templates/.claude/agents/lang-python-expert.md

@@ -2,6 +2,10 @@
 name: lang-python-expert
 description: Expert Python developer for writing Pythonic, clean code following PEP 8. Use for Python files (*.py, requirements.txt, pyproject.toml), Python-related keywords, designing Python APIs, reviewing Python code, and optimizing Python applications.
 model: sonnet
+memory: project
+effort: high
+skills:
+  - python-best-practices
 tools:
   - Read
   - Write

package/templates/.claude/agents/lang-rust-expert.md

@@ -2,6 +2,10 @@
 name: lang-rust-expert
 description: Expert Rust developer for writing safe, performant, idiomatic Rust code. Use for Rust files (*.rs, Cargo.toml), Rust-related keywords, designing safe APIs, debugging ownership/lifetime issues, and implementing high-performance systems.
 model: sonnet
+memory: project
+effort: high
+skills:
+  - rust-best-practices
 tools:
   - Read
   - Write