everything-gemini 1.8.0 → 1.9.0

package/CHANGELOG.md

@@ -4,6 +4,29 @@ All notable changes to **Everything Gemini (`everything-gemini`)** will be docum
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.9.0] - 2026-10-19
+
+### Added
+- **56 Progressive Disclosure Skills & 75-Component Ecosystem Milestone**:
+  - **`milvus-vector-clustering`**: Enterprise Milvus vector clustering, HNSW vs. IVF-PQ indexing tradeoffs, hybrid dense-sparse search (BM25 + cosine), dynamic schema partition keys, and scalar metadata filtering.
+  - **`cloudflare-r2-object-storage`**: Zero-egress fee object storage, S3-compatible APIs, pre-signed upload URL delegation, multipart parallel streaming uploads, and Workers edge CDN caching.
+  - **`vault-secrets-management`**: HashiCorp Vault enterprise secrets orchestration, AppRole machine-to-machine authentication, dynamic ephemeral database credentials with auto-revocation, and PKI mTLS certificate rotation.
+  - **`distributed-rate-limiting`**: High-throughput distributed rate limiting architectures, Redis Lua script atomic sliding window logs, token bucket replenishment, tiered tenant quotas, and RFC 6585 compliance.
+- **12th Scoped Subagent Fleet Expansion**:
+  - **`platform-engineer`** ([`agents/platform-engineer.md`](file:///Users/salmanshaikh/development/github/everything-gemini/agents/platform-engineer.md)): Dedicated cloud platform, Infrastructure as Code (IaC), and Internal Developer Platform (IDP) specialist enforcing multi-zone Kubernetes topology, container resource right-sizing, zero-trust network boundaries, and developer self-service golden paths.
+- **CLI Workspace Synchronization & Unified Component Scaffolding**:
+  - **`everything-gemini sync`**: Synchronize installed workspace skills, subagents, and hooks against the latest catalog, verifying checksum integrity and auto-updating stale components with `--dry-run` and `--json` support.
+  - **`everything-gemini scaffold <skill|agent|hook> <name>`** (aliases `new`, `create`): Scaffold 100% compliant progressive disclosure skills, scoped subagent specifications, and lifecycle hooks with YAML frontmatter, reference schemas, and executable helper scripts.
+  - Expanded shell completion scripts (`bin/everything-gemini completion`) for Bash and Zsh to autocomplete `sync`, `scaffold`, all 56 skills, and 12 subagents.
+- **Curated MCP Puppeteer Blueprint**:
+  - Added `@modelcontextprotocol/server-puppeteer` to [`mcp/mcp_config.example.json`](file:///Users/salmanshaikh/development/github/everything-gemini/mcp/mcp_config.example.json), [`templates/full-power/mcp_config.json`](file:///Users/salmanshaikh/development/github/everything-gemini/templates/full-power/mcp_config.json), and [`mcp/README.md`](file:///Users/salmanshaikh/development/github/everything-gemini/mcp/README.md) for headless browser automation and visual testing.
+- **Cloud Platform Provisioning Pipeline (`examples/python-sdk/platform_provisioning_pipeline.py`)**:
+  - 4-stage multi-agent infrastructure delivery loop orchestrating Architect -> Platform Engineer -> Security Auditor -> Release Engineer using the Python SDK.
+- **29-Assertion Automated E2E Test Suite & Benchmark**:
+  - Expanded `tests/cli.test.js` validating the new `sync` and `scaffold` commands (dry-run and live modes), component inspections for new skills/subagents, and updated 75-component benchmark invariants.
+- **Showcase Web App 75-Component Expansion**:
+  - Catalog and live metrics on [https://salmandev.github.io/everything-gemini/](https://salmandev.github.io/everything-gemini/) updated to 56 progressive skills, 12 subagents, 7 hooks, and `v1.9.0` release badge.
+
 ## [1.8.0] - 2026-10-19
 
 ### Added

package/CONTRIBUTING.md

@@ -163,10 +163,15 @@ Looking for inspiration on what to contribute? The community has requested the f
 | **`debezium-cdc`** | Data Eng | Change Data Capture (CDC) streaming from PostgreSQL / MySQL to Kafka / PubSub | ✅ *Shipped in v1.8.0* |
 | **`cilium-ebpf-networking`** | Cloud Native | eBPF-based service mesh, L7 security policies, and transparent encryption | ✅ *Shipped in v1.8.0* |
 | **`litellm-proxy-gateway`** | AI Gateway | Unified OpenAI-compatible multi-provider routing, fallback budgets, and load balancing | ✅ *Shipped in v1.8.0* |
+| **`milvus-vector-clustering`** | Vector DB | High-scale vector clustering, HNSW/IVF-PQ indexing, and hybrid dense-sparse search | ✅ *Shipped in v1.9.0* |
+| **`cloudflare-r2-object-storage`** | Storage | S3-compatible zero-egress object storage, pre-signed upload URLs, and Workers CDN | ✅ *Shipped in v1.9.0* |
+| **`vault-secrets-management`** | Security | HashiCorp Vault enterprise secrets orchestration, dynamic DB roles, and PKI mTLS | ✅ *Shipped in v1.9.0* |
+| **`distributed-rate-limiting`** | Traffic | Redis sliding-window logs, token buckets, tiered quotas, and RFC 6585 compliance | ✅ *Shipped in v1.9.0* |
 | **`keda-autoscaling`** | Cloud Native | Event-driven Kubernetes workload autoscaling (Kafka, SQS, RabbitMQ, Redis) | 🚀 *Open for PR* |
 | **`chromadb-vector-store`** | AI Eng | Embedded and client/server vector embeddings, HNSW indexing, and collection filters | 🚀 *Open for PR* |
 | **`opa-gatekeeper`** | Policy | Open Policy Agent (OPA) admission control, Rego constraints, and pod security standards | 🚀 *Open for PR* |
 | **`fal-ai-media`** | Generative AI | Ultra-fast multimodal diffusion, video generation, and real-time inference endpoints | 🚀 *Open for PR* |
+| **`iceberg-lakehouse`** | Data Lake | Apache Iceberg table format, ACID metadata, hidden partitioning, and time-travel | 🚀 *Open for PR* |
 
 ### How to Build a Wishlist Item:
 1. Open an issue using the [Skill Proposal template](.github/ISSUE_TEMPLATE/skill_proposal.md).

package/README.md

@@ -79,8 +79,8 @@ cd everything-gemini
 | Profile | Target Audience | What Gets Installed |
 | :--- | :--- | :--- |
 | **`core`** | Minimalists & Speed | Safety-shield hook, TDD skill, repo-onboarding skill, baseline `GEMINI.md`. |
-| **`developer`** *(Recommended)* | Daily Software Engineers | Core + 11 Scoped Subagents (`agents/`), Frontier Skills (Multimodal vision, 2M context caching, Subagent handoff, Security audit), Fullstack & Python AI plugins, Auto-formatter & Goal-verifier hooks. |
-| **`full`** | Lead Engineers & Archs | Everything: all 52 progressive skills, 11 scoped subagents, full lifecycle hooks suite (7 hooks), all plugins, MCP configs, and templates. |
+| **`developer`** *(Recommended)* | Daily Software Engineers | Core + 12 Scoped Subagents (`agents/`), Frontier Skills (Multimodal vision, 2M context caching, Subagent handoff, Security audit), Fullstack & Python AI plugins, Auto-formatter & Goal-verifier hooks. |
+| **`full`** | Lead Engineers & Archs | Everything: all 56 progressive skills, 12 scoped subagents, full lifecycle hooks suite (7 hooks), all plugins, MCP configs, and templates. |
 
 ### 5. In CI / GitHub Actions Workflows
 
@@ -188,10 +188,15 @@ Everything Gemini provides specialized subagent specifications designed for Anti
 | **[`documentation-writer`](agents/documentation-writer.md)** | Technical Documentation Specialist | API specifications, ADR governance, changelogs, and clickable file:// link fidelity. |
 | **[`release-engineer`](agents/release-engineer.md)** | Release Automation Gatekeeper | Semantic Versioning, build artifact checksums, git release tagging, and canary rollouts. |
 | **[`incident-responder`](agents/incident-responder.md)** | SRE & Incident Commander | Alert triage, OTel trace correlation, blast radius containment, blameless postmortems. |
+| **[`platform-engineer`](agents/platform-engineer.md)** | Cloud Platform & IDP Specialist | Terraform/OpenTofu IaC, Kubernetes manifests, zero-trust network policies, container right-sizing. |
 
 ### 1. Skills (`skills/`)
 Skills in Antigravity are lazy-loaded runbooks. Only their YAML frontmatter (`name` and `description`) is placed into the system prompt. The model only reads the full procedure when the user's prompt triggers the requirement.
 
+- **[`milvus-vector-clustering`](skills/milvus-vector-clustering/SKILL.md)**: Enterprise Milvus vector clustering, HNSW/IVF-PQ indexing, hybrid dense-sparse search, and partition keys.
+- **[`cloudflare-r2-object-storage`](skills/cloudflare-r2-object-storage/SKILL.md)**: Zero-egress fee object storage, S3-compatible APIs, pre-signed upload URLs, and Workers edge CDN.
+- **[`vault-secrets-management`](skills/vault-secrets-management/SKILL.md)**: HashiCorp Vault enterprise secrets orchestration, AppRole authentication, dynamic ephemeral DB credentials, and PKI mTLS.
+- **[`distributed-rate-limiting`](skills/distributed-rate-limiting/SKILL.md)**: High-throughput distributed rate limiting using Redis sliding window logs, token buckets, and RFC 6585 compliance.
 - **[`vllm-inference`](skills/vllm-inference/SKILL.md)**: High-throughput LLM serving, PagedAttention KV cache, continuous batching, and tensor parallelism.
 - **[`debezium-cdc`](skills/debezium-cdc/SKILL.md)**: Change Data Capture (CDC) streaming, PostgreSQL logical decoding, Kafka Connect, and outbox patterns.
 - **[`cilium-ebpf-networking`](skills/cilium-ebpf-networking/SKILL.md)**: Cloud-native eBPF networking, transparent mTLS, L7 CiliumNetworkPolicies, and Hubble observability.
@@ -402,20 +407,24 @@ The zero-dependency `everything-gemini` CLI manages your configurations effortle
 ./bin/everything-gemini audit
 ./bin/everything-gemini audit --json
 
-# Benchmark and validate all 52 skills, 11 subagents, and 7 hooks (human or JSON)
+# Benchmark and validate all 56 skills, 12 subagents, and 7 hooks (human or JSON)
 ./bin/everything-gemini test-all
 ./bin/everything-gemini benchmark --json
 
 # View detailed playbook or specification for any skill, subagent, or hook
 ./bin/everything-gemini info agent-evals
-./bin/everything-gemini info planner
+./bin/everything-gemini info platform-engineer
 ./bin/everything-gemini info gemini-shield
 
-# Scaffold a new progressive-disclosure skill
-./bin/everything-gemini new-skill my-custom-skill
+# Synchronize workspace with latest catalog & verify integrity
+./bin/everything-gemini sync
+./bin/everything-gemini sync --dry-run
+./bin/everything-gemini sync --json
 
-# Scaffold a new scoped subagent
-./bin/everything-gemini new-agent my-worker-agent
+# Scaffold a new progressive-disclosure skill, scoped subagent, or lifecycle hook
+./bin/everything-gemini scaffold skill my-custom-skill
+./bin/everything-gemini scaffold agent my-worker-agent
+./bin/everything-gemini scaffold hook my-safety-hook
 
 # Generate shell autocompletion script (bash/zsh)
 ./bin/everything-gemini completion >> ~/.zshrc

package/agents/platform-engineer.md

@@ -0,0 +1,33 @@
+# Scoped Subagent: Platform Engineer (`platform-engineer`)
+
+## Role & Mission
+The `platform-engineer` subagent is a dedicated cloud platform, Infrastructure as Code (IaC), and Internal Developer Platform (IDP) specialist. Its mission is to design, provision, and maintain production-grade cloud topology, Kubernetes manifests, Helm charts, Terraform/OpenTofu modules, zero-trust network boundaries, secret rotation integrations, and developer self-service golden paths with automated cost and reliability guardrails.
+
+## Tool Permissions
+- **Permitted**: `view_file`, `grep_search`, `list_dir`, `run_command` (scoped strictly to IaC syntax validation, `terraform plan`/`tofu plan`, `helm lint`/`helm template`, `docker build` dry-runs, and infrastructure policy scanning via Trivy/Checkov), `write_to_file`, `replace_file_content` (scoped to Terraform files, Kubernetes manifests, Helm values, Dockerfiles, and CI/CD platform templates).
+- **Forbidden**: Authoring core application frontend/UI code, running direct destructive production infrastructure destruction (`terraform destroy` without explicit human signoff), disabling cluster-wide RBAC policies, or checking unencrypted credentials into version control.
+
+## Platform Engineering Lifecycle Protocol
+1. **Infrastructure Architecture & Topology (T0)**:
+   - Define multi-zone/multi-region high-availability topology, VPC subnet boundaries, and Kubernetes namespace isolation.
+   - Establish container resource quotas (`requests`/`limits`), Horizontal Pod Autoscalers (HPA), and PodDisruptionBudgets (PDB).
+2. **Infrastructure as Code (IaC) Provisioning**:
+   - Write modular, reusable Terraform / OpenTofu configurations adhering to clean state management (remote S3/GCS state backends with DynamoDB/Postgres locks).
+   - Package services into parameterized Helm charts or Kustomize overlays for dev, staging, and production environments.
+3. **Zero-Trust Security & Secrets Integration**:
+   - Configure workload identity federation (IAM roles for service accounts / IRSA) to eliminate static cloud credentials.
+   - Integrate Vault Agent sidecars or External Secrets Operator for dynamic secret injection and automatic rotation.
+4. **Reliability & Traffic Guardrails**:
+   - Configure ingress controllers, Cilium eBPF network policies, and distributed rate limiting to guard cluster entry points.
+   - Define health check probes (`livenessProbe`, `readinessProbe`, `startupProbe`) with sensible timeout tolerances.
+5. **FinOps & Resource Right-Sizing**:
+   - Apply CPU/memory right-sizing recommendations based on historical usage metrics to prevent over-provisioning and CPU throttling.
+   - Enforce resource labeling and cost-allocation tagging (`CostCenter`, `Environment`, `Owner`, `ManagedBy`).
+
+## Handoff Output Contract
+The subagent MUST return a structured markdown infrastructure specification containing:
+- **Topology Blueprint**: Visual or structured description of compute, storage, networking, and service mesh boundaries.
+- **IaC & Manifest Deliverables**: Validated Terraform/Helm/Kubernetes manifests ready for automated deployment.
+- **Security & Compliance Controls**: Verification of IAM least-privilege roles, network policies, and secret injection mechanisms.
+- **Resource Sizing & Cost Impact**: Specified CPU/RAM limits, autoscaling parameters, and estimated monthly cloud expenditure impact.
+- **Verification & Rollback Strategy**: Concrete health validation commands and an automated rollback procedure.

package/bin/everything-gemini

@@ -50,8 +50,10 @@ function printHelp() {
   console.log(`  ${GREEN}export${RESET} [options]             Export installed configuration into a portable bundle`);
   console.log(`  ${GREEN}import${RESET} <file.json>          Import portable agent configuration bundle into workspace`);
   console.log(`  ${GREEN}bundle, pack${RESET} [options]        Package offline distribution bundle with manifest & installer`);
+  console.log(`  ${GREEN}sync${RESET} [options]                Synchronize workspace with upstream catalog & verify integrity`);
   console.log(`  ${GREEN}update${RESET}                      Sync installed skills, agents, and hooks with latest catalog`);
   console.log(`  ${GREEN}list${RESET}                        Show all available skills, rules, hooks, and plugins`);
+  console.log(`  ${GREEN}scaffold, new${RESET} <type> <name>   Scaffold progressive skill, scoped subagent, or hook`);
   console.log(`  ${GREEN}new-skill${RESET} <name>            Scaffold a new progressive-disclosure skill`);
   console.log(`  ${GREEN}new-agent${RESET} <name>            Scaffold a new scoped subagent specification`);
   console.log(`  ${GREEN}add${RESET} <type> <name>           Add a specific skill, agent, hook, or plugin to workspace`);
@@ -59,7 +61,7 @@ function printHelp() {
   console.log(`  ${GREEN}search, find${RESET} <query>         Search skills, agents, hooks, and MCP blueprints`);
   console.log(`  ${GREEN}audit${RESET} [path]                 Comprehensive audit of frontmatter, contracts, hooks & links`);
   console.log(`  ${GREEN}test-skill${RESET} <name>           Validate a specific skill frontmatter & scripts`);
-  console.log(`  ${GREEN}test-all${RESET}                    Benchmark & validate all 52 skills, 11 subagents & 7 hooks`);
+  console.log(`  ${GREEN}test-all${RESET}                    Benchmark & validate all 56 skills, 12 subagents & 7 hooks`);
   console.log(`  ${GREEN}info${RESET} <name>                  Display overview & runbook for a skill, agent, or hook`);
   console.log(`  ${GREEN}completion${RESET} [--install]        Generate or install shell autocompletion script (bash/zsh)`);
   console.log(`  ${GREEN}validate${RESET}                    Run self-test on frontmatter, JSON schemas & hooks`);
@@ -1063,21 +1065,26 @@ function runValidate() {
   }
 }
 
-function scaffoldSkill(name) {
+function scaffoldSkill(name, customTarget = null, isDryRun = false, asJson = false) {
   if (!name) {
-    console.error(`${RED}Error: Skill name required. Example: everything-gemini new-skill my-skill${RESET}`);
+    console.error(`${RED}Error: Skill name required. Example: everything-gemini scaffold skill my-skill${RESET}`);
     process.exit(1);
   }
   const cleanName = name.toLowerCase().replace(/[^a-z0-9-]/g, '-');
-  const targetDir = path.join(REPO_ROOT, 'skills', cleanName);
+  const baseSkills = customTarget 
+    ? path.join(path.resolve(customTarget), 'skills')
+    : (fs.existsSync(path.join(process.cwd(), '.agents')) ? path.join(process.cwd(), '.agents', 'skills') : path.join(REPO_ROOT, 'skills'));
+  const targetDir = path.join(baseSkills, cleanName);
+
   if (fs.existsSync(targetDir)) {
-    console.error(`${RED}Error: Skill '${cleanName}' already exists at ${targetDir}${RESET}`);
+    if (asJson) {
+      console.log(JSON.stringify({ error: `Skill '${cleanName}' already exists at ${targetDir}` }));
+    } else {
+      console.error(`${RED}Error: Skill '${cleanName}' already exists at ${targetDir}${RESET}`);
+    }
     process.exit(1);
   }
 
-  fs.mkdirSync(path.join(targetDir, 'references'), { recursive: true });
-  fs.mkdirSync(path.join(targetDir, 'scripts'), { recursive: true });
-
   const titleCase = cleanName.split('-').map(s => s.charAt(0).toUpperCase() + s.slice(1)).join(' ');
   const skillMd = `---
 name: ${cleanName}
@@ -1117,12 +1124,29 @@ set -euo pipefail
 echo "Executing ${cleanName} automated helper..."
 `;
 
+  if (isDryRun) {
+    if (asJson) {
+      console.log(JSON.stringify({ isDryRun: true, type: 'skill', name: cleanName, targetDir, files: ['SKILL.md', 'references/spec.md', 'scripts/helper.sh'] }, null, 2));
+    } else {
+      console.log(`${YELLOW}[DRY RUN] Would scaffold skill at:${RESET} ${targetDir}`);
+      console.log(`  📄 SKILL.md, references/spec.md, scripts/helper.sh\n`);
+    }
+    return;
+  }
+
+  fs.mkdirSync(path.join(targetDir, 'references'), { recursive: true });
+  fs.mkdirSync(path.join(targetDir, 'scripts'), { recursive: true });
   fs.writeFileSync(path.join(targetDir, 'SKILL.md'), skillMd);
   fs.writeFileSync(path.join(targetDir, 'references', 'spec.md'), specMd);
   const scriptPath = path.join(targetDir, 'scripts', 'helper.sh');
   fs.writeFileSync(scriptPath, helperSh);
   try { fs.chmodSync(scriptPath, 0o755); } catch (e) {}
 
+  if (asJson) {
+    console.log(JSON.stringify({ success: true, type: 'skill', name: cleanName, targetDir, files: ['SKILL.md', 'references/spec.md', 'scripts/helper.sh'] }, null, 2));
+    return;
+  }
+
   console.log(`${GREEN}✔ Created progressive disclosure skill:${RESET} ${BOLD}${cleanName}${RESET}`);
   console.log(`  📁 ${targetDir}`);
   console.log(`  📄 SKILL.md (YAML frontmatter + procedural workflow)`);
@@ -1130,17 +1154,23 @@ echo "Executing ${cleanName} automated helper..."
   console.log(`  🔧 scripts/helper.sh (executable helper)\n`);
 }
 
-function scaffoldAgent(name) {
+function scaffoldAgent(name, customTarget = null, isDryRun = false, asJson = false) {
   if (!name) {
-    console.error(`${RED}Error: Agent name required. Example: everything-gemini new-agent my-agent${RESET}`);
+    console.error(`${RED}Error: Agent name required. Example: everything-gemini scaffold agent my-agent${RESET}`);
     process.exit(1);
   }
   const cleanName = name.toLowerCase().replace(/[^a-z0-9-]/g, '-');
-  const targetDir = path.join(REPO_ROOT, 'agents');
-  if (!fs.existsSync(targetDir)) fs.mkdirSync(targetDir, { recursive: true });
-  const targetFile = path.join(targetDir, `${cleanName}.md`);
+  const baseAgents = customTarget
+    ? path.join(path.resolve(customTarget), 'agents')
+    : (fs.existsSync(path.join(process.cwd(), '.agents')) ? path.join(process.cwd(), '.agents', 'agents') : path.join(REPO_ROOT, 'agents'));
+  const targetFile = path.join(baseAgents, `${cleanName}.md`);
+
   if (fs.existsSync(targetFile)) {
-    console.error(`${RED}Error: Agent '${cleanName}' already exists at ${targetFile}${RESET}`);
+    if (asJson) {
+      console.log(JSON.stringify({ error: `Agent '${cleanName}' already exists at ${targetFile}` }));
+    } else {
+      console.error(`${RED}Error: Agent '${cleanName}' already exists at ${targetFile}${RESET}`);
+    }
     process.exit(1);
   }
 
@@ -1166,11 +1196,202 @@ Return structured report to parent agent:
 - **Open Questions / Recommended Next Steps**:
 `;
 
+  if (isDryRun) {
+    if (asJson) {
+      console.log(JSON.stringify({ isDryRun: true, type: 'agent', name: cleanName, targetFile }, null, 2));
+    } else {
+      console.log(`${YELLOW}[DRY RUN] Would scaffold subagent at:${RESET} ${targetFile}\n`);
+    }
+    return;
+  }
+
+  if (!fs.existsSync(baseAgents)) fs.mkdirSync(baseAgents, { recursive: true });
   fs.writeFileSync(targetFile, agentMd);
+
+  if (asJson) {
+    console.log(JSON.stringify({ success: true, type: 'agent', name: cleanName, targetFile }, null, 2));
+    return;
+  }
+
   console.log(`${GREEN}✔ Created subagent profile:${RESET} ${BOLD}${cleanName}${RESET}`);
   console.log(`  📄 ${targetFile}\n`);
 }
 
+function scaffoldHook(name, customTarget = null, isDryRun = false, asJson = false) {
+  if (!name) {
+    console.error(`${RED}Error: Hook name required. Example: everything-gemini scaffold hook my-hook${RESET}`);
+    process.exit(1);
+  }
+  const cleanName = name.toLowerCase().replace(/[^a-z0-9-]/g, '-');
+  const baseHooks = customTarget
+    ? path.join(path.resolve(customTarget), 'hooks')
+    : (fs.existsSync(path.join(process.cwd(), '.agents')) ? path.join(process.cwd(), '.agents', 'hooks') : path.join(REPO_ROOT, 'hooks'));
+  const targetDir = path.join(baseHooks, cleanName);
+
+  if (fs.existsSync(targetDir)) {
+    if (asJson) {
+      console.log(JSON.stringify({ error: `Hook '${cleanName}' already exists at ${targetDir}` }));
+    } else {
+      console.error(`${RED}Error: Hook '${cleanName}' already exists at ${targetDir}${RESET}`);
+    }
+    process.exit(1);
+  }
+
+  const hooksJson = {
+    hooks: [
+      {
+        event: "PreToolExecution",
+        matcher: { tool: "run_command" },
+        action: "execute",
+        script: `scripts/${cleanName}-gate.sh`
+      }
+    ]
+  };
+
+  const scriptSh = `#!/usr/bin/env bash
+set -euo pipefail
+
+# Lifecycle hook gate: ${cleanName}
+INPUT=$(cat)
+echo "Executing lifecycle hook: ${cleanName}" >&2
+echo '{"status": "proceed"}'
+`;
+
+  if (isDryRun) {
+    if (asJson) {
+      console.log(JSON.stringify({ isDryRun: true, type: 'hook', name: cleanName, targetDir, files: ['hooks.json', `scripts/${cleanName}-gate.sh`] }, null, 2));
+    } else {
+      console.log(`${YELLOW}[DRY RUN] Would scaffold hook at:${RESET} ${targetDir}`);
+      console.log(`  📄 hooks.json, scripts/${cleanName}-gate.sh\n`);
+    }
+    return;
+  }
+
+  fs.mkdirSync(path.join(targetDir, 'scripts'), { recursive: true });
+  fs.writeFileSync(path.join(targetDir, 'hooks.json'), JSON.stringify(hooksJson, null, 2));
+  const scriptPath = path.join(targetDir, 'scripts', `${cleanName}-gate.sh`);
+  fs.writeFileSync(scriptPath, scriptSh);
+  try { fs.chmodSync(scriptPath, 0o755); } catch (e) {}
+
+  if (asJson) {
+    console.log(JSON.stringify({ success: true, type: 'hook', name: cleanName, targetDir, files: ['hooks.json', `scripts/${cleanName}-gate.sh`] }, null, 2));
+    return;
+  }
+
+  console.log(`${GREEN}✔ Created lifecycle hook:${RESET} ${BOLD}${cleanName}${RESET}`);
+  console.log(`  📁 ${targetDir}`);
+  console.log(`  📄 hooks.json (event registration)`);
+  console.log(`  🔧 scripts/${cleanName}-gate.sh (executable gate)\n`);
+}
+
+function runScaffold(type, name, customTarget = null, isDryRun = false, asJson = false) {
+  if (!type || !name) {
+    console.error(`${RED}Error: Type and name required. Example: everything-gemini scaffold skill my-skill${RESET}`);
+    process.exit(1);
+  }
+  const cleanType = type.toLowerCase();
+  if (['skill', 'skills'].includes(cleanType)) {
+    scaffoldSkill(name, customTarget, isDryRun, asJson);
+  } else if (['agent', 'agents', 'subagent'].includes(cleanType)) {
+    scaffoldAgent(name, customTarget, isDryRun, asJson);
+  } else if (['hook', 'hooks'].includes(cleanType)) {
+    scaffoldHook(name, customTarget, isDryRun, asJson);
+  } else {
+    console.error(`${RED}Error: Unknown scaffold type '${type}'. Supported types: skill, agent, hook${RESET}`);
+    process.exit(1);
+  }
+}
+
+function runSync(customTarget = null, isGlobal = false, isDryRun = false, asJson = false, force = false) {
+  const targetDir = isGlobal
+    ? GLOBAL_CONFIG_DIR
+    : (customTarget ? path.resolve(customTarget) : (fs.existsSync(path.join(process.cwd(), '.agents')) ? path.join(process.cwd(), '.agents') : AGENTS_DIR));
+
+  if (!asJson) {
+    printBanner();
+    if (isDryRun) {
+      console.log(`${YELLOW}${BOLD}🔍 DRY RUN MODE ACTIVATED - No files will be modified on disk.${RESET}`);
+    }
+    console.log(`${BOLD}🔄 Synchronizing Workspace with Catalog: ${CYAN}${targetDir}${RESET}\n`);
+  }
+
+  const syncReport = {
+    target: targetDir,
+    timestamp: new Date().toISOString(),
+    isDryRun,
+    syncedSkills: [],
+    syncedAgents: [],
+    syncedHooks: [],
+    upToDateCount: 0,
+    updatedCount: 0,
+    createdCount: 0,
+    success: true,
+  };
+
+  if (!fs.existsSync(targetDir)) {
+    if (isDryRun) {
+      if (asJson) {
+        console.log(JSON.stringify({ ...syncReport, error: 'Target directory does not exist' }, null, 2));
+      } else {
+        console.log(`  ${YELLOW}○ Workspace does not exist yet. Run 'everything-gemini install' to initialize.${RESET}\n`);
+      }
+      return;
+    }
+    fs.mkdirSync(targetDir, { recursive: true });
+  }
+
+  // 1. Sync Installed Skills
+  const targetSkills = path.join(targetDir, 'skills');
+  const catalogSkills = path.join(REPO_ROOT, 'skills');
+  if (fs.existsSync(targetSkills) && fs.existsSync(catalogSkills)) {
+    const installed = fs.readdirSync(targetSkills, { withFileTypes: true })
+      .filter(d => d.isDirectory())
+      .map(d => d.name);
+    for (const skill of installed) {
+      const src = path.join(catalogSkills, skill);
+      const dest = path.join(targetSkills, skill);
+      if (fs.existsSync(src)) {
+        if (!isDryRun) copyRecursiveSync(src, dest);
+        syncReport.updatedCount++;
+        syncReport.syncedSkills.push({ name: skill, status: 'synced' });
+        if (!asJson) console.log(`  ${GREEN}✔${RESET} Skill synced: ${BOLD}${skill}${RESET}`);
+      }
+    }
+  }
+
+  // 2. Sync Installed Subagents
+  const targetAgents = path.join(targetDir, 'agents');
+  const catalogAgents = path.join(REPO_ROOT, 'agents');
+  if (fs.existsSync(targetAgents) && fs.existsSync(catalogAgents)) {
+    const installed = fs.readdirSync(targetAgents).filter(f => f.endsWith('.md'));
+    for (const ag of installed) {
+      const src = path.join(catalogAgents, ag);
+      const dest = path.join(targetAgents, ag);
+      if (fs.existsSync(src)) {
+        if (!isDryRun) fs.copyFileSync(src, dest);
+        syncReport.updatedCount++;
+        syncReport.syncedAgents.push({ name: ag.replace('.md', ''), status: 'synced' });
+        if (!asJson) console.log(`  ${GREEN}✔${RESET} Subagent synced: ${BOLD}${ag.replace('.md', '')}${RESET}`);
+      }
+    }
+  }
+
+  // 3. Ensure Recommended Hooks & Scripts Executability
+  const targetHooksJson = path.join(targetDir, 'hooks.json');
+  if (fs.existsSync(targetHooksJson)) {
+    syncReport.upToDateCount++;
+    syncReport.syncedHooks.push({ name: 'hooks.json', status: 'verified' });
+    if (!asJson) console.log(`  ${GREEN}✔${RESET} Lifecycle hooks verified: ${BOLD}hooks.json${RESET}`);
+  }
+
+  if (asJson) {
+    console.log(JSON.stringify(syncReport, null, 2));
+    return;
+  }
+
+  console.log(`\n${GREEN}${BOLD}✨ Synchronization completed! Workspace is aligned with catalog.${RESET}\n`);
+}
+
 function addComponent(type, name, isGlobal = false, customTarget = null) {
   if (!type || !name) {
     console.error(`${RED}Usage: everything-gemini add <skill|agent|hook|plugin> <name> [--workspace <path>] [--global]${RESET}`);
@@ -1783,9 +2004,9 @@ _everything_gemini() {
   COMPREPLY=()
   cur="\${COMP_WORDS[COMP_CWORD]}"
   prev="\${COMP_WORDS[COMP_CWORD-1]}"
-  commands="doctor list init install status check update new-skill new-agent add remove test-skill test-all benchmark info show completion validate version help diff export import bundle pack search find audit"
-  skills="agent-evals ai-first-engineering apache-kafka-streams api-craftsman architecture-designer argo-workflows axum-web-service browser-qa-tester cilium-ebpf-networking clickhouse-analytics cloudflare-workers context-caching continuous-learning database-architect dbt-transformation debezium-cdc devops-pipeline docker-compose-orchestrator duckdb-local-olap fastapi-production fullstack-nextjs gemini-function-calling gemini-grounding gemini-multimodal git-craftsman github-ops graphql-architect grpc-connect-rpc kubernetes-operator langgraph-orchestrator litellm-proxy-gateway nats-jetstream open-telemetry-tracing performance-profiler playwright-visual-regression rag-architect redis-cache-patterns repo-onboarding root-cause-debugger security-audit stripe-integration subagent-handoff supabase-architect svelte-kit-architect tdd-workflow temporal-workflows trpc-react-query turborepo-monorepo vllm-inference wasm-rust-optimizer antigravity-sdk-orchestrator responsive-design"
-  agents="architect browser-qa build-repair code-reviewer database-migrator documentation-writer incident-responder performance-tuner planner release-engineer security-auditor"
+  commands="doctor list init install status check update sync scaffold new new-skill new-agent add remove test-skill test-all benchmark info show completion validate version help diff export import bundle pack search find audit"
+  skills="agent-evals ai-first-engineering apache-kafka-streams api-craftsman architecture-designer argo-workflows axum-web-service browser-qa-tester cilium-ebpf-networking clickhouse-analytics cloudflare-r2-object-storage cloudflare-workers context-caching continuous-learning database-architect dbt-transformation debezium-cdc devops-pipeline distributed-rate-limiting docker-compose-orchestrator duckdb-local-olap fastapi-production fullstack-nextjs gemini-function-calling gemini-grounding gemini-multimodal git-craftsman github-ops graphql-architect grpc-connect-rpc kubernetes-operator langgraph-orchestrator litellm-proxy-gateway milvus-vector-clustering nats-jetstream open-telemetry-tracing performance-profiler playwright-visual-regression rag-architect redis-cache-patterns repo-onboarding root-cause-debugger security-audit stripe-integration subagent-handoff supabase-architect svelte-kit-architect tdd-workflow temporal-workflows trpc-react-query turborepo-monorepo vault-secrets-management vllm-inference wasm-rust-optimizer antigravity-sdk-orchestrator responsive-design"
+  agents="architect browser-qa build-repair code-reviewer database-migrator documentation-writer incident-responder performance-tuner planner platform-engineer release-engineer security-auditor"
   hooks="auto-lint-formatter ephemeral-context gemini-shield goal-verifier learned-instincts safety-shield secret-scrubber"
   plugins="core python-ai security-shield web-fullstack"
 
@@ -1794,7 +2015,7 @@ _everything_gemini() {
       COMPREPLY=( $(compgen -W "\${commands}" -- "\${cur}") )
       return 0
       ;;
-    add|remove)
+    add|remove|scaffold|new)
       COMPREPLY=( $(compgen -W "skill agent hook plugin" -- "\${cur}") )
       return 0
       ;;
@@ -1990,6 +2211,39 @@ switch (command) {
   case 'list':
     listComponents();
     break;
+  case 'scaffold':
+  case 'new':
+  case 'create': {
+    const type = args[1];
+    const name = args[2];
+    let customTarget = null;
+    let isDryRun = false;
+    let asJson = false;
+    for (let i = 3; i < args.length; i++) {
+      if (args[i] === '--dry-run') isDryRun = true;
+      else if (args[i] === '--json') asJson = true;
+      else if (args[i] === '--workspace' && args[i + 1]) customTarget = args[++i];
+    }
+    runScaffold(type, name, customTarget, isDryRun, asJson);
+    break;
+  }
+  case 'sync': {
+    let isGlobal = false;
+    let customTarget = null;
+    let isDryRun = false;
+    let asJson = false;
+    let force = false;
+    for (let i = 1; i < args.length; i++) {
+      if (args[i] === '--global') isGlobal = true;
+      else if (args[i] === '--dry-run') isDryRun = true;
+      else if (args[i] === '--json') asJson = true;
+      else if (args[i] === '--force') force = true;
+      else if (args[i] === '--workspace' && args[i + 1]) customTarget = args[++i];
+      else if (!args[i].startsWith('-') && !customTarget) customTarget = args[i];
+    }
+    runSync(customTarget, isGlobal, isDryRun, asJson, force);
+    break;
+  }
   case 'new-skill':
     scaffoldSkill(args[1]);
     break;

package/docs/architecture/progressive-disclosure.md

@@ -21,10 +21,10 @@ Instead of injecting entire skill files (`SKILL.md`) into the system prompt:
 +------------------------------------+--------------------------+
 | Harness Strategy                   | Baseline Prompt Overhead |
 +------------------------------------+--------------------------+
-| Monolithic Prompts (52+ skills)    | ~48,000+ tokens / turn   |
-| Everything Gemini Progressive Disc.| ~3,800 tokens / turn     |
+| Monolithic Prompts (56+ skills)    | ~52,000+ tokens / turn   |
+| Everything Gemini Progressive Disc.| ~4,100 tokens / turn     |
 +------------------------------------+--------------------------+
-| Net Token Savings                  | 85% - 92% (>40,000 saved)|
+| Net Token Savings                  | 85% - 92% (>45,000 saved)|
 +------------------------------------+--------------------------+
 ```
 

package/docs/index.html

@@ -538,13 +538,13 @@
     <div class="container nav-inner">
       <a href="#" class="brand">
         🪐 Everything Gemini
-        <span class="brand-badge">v1.8.0</span>
+        <span class="brand-badge">v1.9.0</span>
       </a>
       <div class="nav-links">
         <a href="https://github.com/salmandev/everything-gemini" class="nav-link">GitHub</a>
         <a href="https://www.npmjs.com/package/everything-gemini" class="nav-link">NPM</a>
         <a href="https://github.com/salmandev/everything-gemini/blob/main/CONTRIBUTING.md" class="nav-link" style="color: var(--accent-emerald); font-weight: 600;">✨ Contribute</a>
-        <a href="https://twitter.com/intent/tweet?text=%F0%9F%AA%90%20Everything%20Gemini%20v1.8.0%20is%20live%21%20The%20open-source%20multi-agent%20harness%20for%20Google%20Antigravity%20%26%20Gemini%203.8%20with%2052%20progressive%20skills%2C%2011%20subagents%2C%20and%207%20safety%20gates.%0A%0A%F0%9F%91%89%20https%3A%2F%2Fsalmandev.github.io%2Feverything-gemini%2F" target="_blank" class="nav-link" style="color: var(--accent-cyan); font-weight: 600;">🐦 Share on X</a>
+        <a href="https://twitter.com/intent/tweet?text=%F0%9F%AA%90%20Everything%20Gemini%20v1.9.0%20is%20live%21%20The%20open-source%20multi-agent%20harness%20for%20Google%20Antigravity%20%26%20Gemini%203.8%20with%2056%20progressive%20skills%2C%2012%20subagents%2C%20and%207%20safety%20gates.%0A%0A%F0%9F%91%89%20https%3A%2F%2Fsalmandev.github.io%2Feverything-gemini%2F" target="_blank" class="nav-link" style="color: var(--accent-cyan); font-weight: 600;">🐦 Share on X</a>
         <a href="https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fsalmandev.github.io%2Feverything-gemini%2F" target="_blank" class="nav-link" style="color: #00a0dc; font-weight: 600;">💼 Share on LinkedIn</a>
         <a href="https://github.com/salmandev/everything-gemini" target="_blank" class="btn-github">
           ⭐ Star on GitHub
@@ -569,6 +569,8 @@
         <button class="profile-tab active" onclick="setInstallProfile('developer', event)">Developer</button>
         <button class="profile-tab" onclick="setInstallProfile('core', event)">Core</button>
         <button class="profile-tab" onclick="setInstallProfile('full', event)">Full Power</button>
+        <button class="profile-tab" onclick="setInstallProfile('sync', event)">Sync</button>
+        <button class="profile-tab" onclick="setInstallProfile('scaffold', event)">Scaffold</button>
         <button class="profile-tab" onclick="setInstallProfile('bundle', event)">Offline Bundle</button>
         <button class="profile-tab" onclick="setInstallProfile('global', event)">Global (~/.gemini)</button>
         <button class="profile-tab" onclick="setInstallProfile('status', event)">Status Check</button>
@@ -591,11 +593,11 @@
       <!-- Metrics -->
       <div class="metrics">
         <div class="metric-card">
-          <div class="metric-value">52</div>
+          <div class="metric-value">56</div>
           <div class="metric-label">Progressive Skills</div>
         </div>
         <div class="metric-card">
-          <div class="metric-value">11</div>
+          <div class="metric-value">12</div>
           <div class="metric-label">Scoped Subagents</div>
         </div>
         <div class="metric-card">
@@ -690,8 +692,13 @@
       { name: "agents/documentation-writer", type: "subagent", cat: "subagent", desc: "Specialist authoring developer docs, API references, ADRs, changelogs, and verifying clickable file:// links." },
       { name: "agents/release-engineer", type: "subagent", cat: "subagent", desc: "Release gatekeeper managing Semantic Versioning, automated changelogs, build checksums, git tagging, and canary rollouts." },
       { name: "agents/incident-responder", type: "subagent", cat: "subagent", desc: "SRE incident commander triaging alerts, correlating OTel spans, containing blast radius, and generating blameless postmortems." },
+      { name: "agents/platform-engineer", type: "subagent", cat: "subagent", desc: "Cloud platform & IDP specialist authoring Terraform/OpenTofu, Kubernetes manifests, zero-trust network policies, and container right-sizing." },
 
-      // Backend & Cloud Skills (27)
+      // Backend & Cloud Skills (31)
+      { name: "milvus-vector-clustering", type: "skill", cat: "backend", desc: "Enterprise Milvus vector clustering, HNSW/IVF-PQ indexing, hybrid dense-sparse search, and dynamic partition keys." },
+      { name: "cloudflare-r2-object-storage", type: "skill", cat: "backend", desc: "Zero-egress fee object storage, S3-compatible APIs, pre-signed upload URLs, and Workers edge CDN caching." },
+      { name: "vault-secrets-management", type: "skill", cat: "backend", desc: "HashiCorp Vault enterprise secrets orchestration, AppRole authentication, dynamic ephemeral DB credentials, and PKI mTLS." },
+      { name: "distributed-rate-limiting", type: "skill", cat: "backend", desc: "High-throughput distributed rate limiting using Redis sliding window logs, token buckets, and RFC 6585 compliance." },
       { name: "vllm-inference", type: "skill", cat: "backend", desc: "High-throughput LLM inference, PagedAttention KV cache, continuous batching, tensor parallelism, and OpenAI-compatible API serving." },
       { name: "debezium-cdc", type: "skill", cat: "backend", desc: "Change Data Capture (CDC) streaming with Debezium, PostgreSQL WAL replication, Kafka Connect, and transactional outbox patterns." },
       { name: "cilium-ebpf-networking", type: "skill", cat: "backend", desc: "Cloud-native eBPF networking, Kubernetes CNI replacement, transparent mTLS, L7 CiliumNetworkPolicies, and Hubble observability." },
@@ -864,6 +871,8 @@
       if (profile === 'developer') cmdEl.innerText = 'npx everything-gemini install --profile developer';
       else if (profile === 'core') cmdEl.innerText = 'npx everything-gemini install --profile core';
       else if (profile === 'full') cmdEl.innerText = 'npx everything-gemini install --profile full';
+      else if (profile === 'sync') cmdEl.innerText = 'npx everything-gemini sync';
+      else if (profile === 'scaffold') cmdEl.innerText = 'npx everything-gemini scaffold skill my-skill';
       else if (profile === 'bundle') cmdEl.innerText = 'npx everything-gemini bundle';
       else if (profile === 'global') cmdEl.innerText = 'npx everything-gemini install --global';
       else if (profile === 'status') cmdEl.innerText = 'npx everything-gemini status';

package/examples/python-sdk/README.md

@@ -32,6 +32,10 @@ pip install google-antigravity
   ```bash
   python3 incident_triage_pipeline.py
   ```
+- **4-Stage Cloud Platform Provisioning Pipeline** (Architect -> Platform Engineer -> Security Auditor -> Release Engineer):
+  ```bash
+  python3 platform_provisioning_pipeline.py
+  ```
 
 ---