@techwavedev/agi-agent-kit 1.3.5 → 1.4.2

package/README.md

@@ -13,6 +13,7 @@
 [![OpenCode](https://img.shields.io/badge/OpenCode-CLI-gray)](https://github.com/opencode-ai/opencode)
 [![Antigravity IDE](https://img.shields.io/badge/Antigravity-DeepMind-red)](https://github.com/techwavedev/agi-agent-kit)
 [![AdaL CLI](https://img.shields.io/badge/AdaL%20CLI-SylphAI-pink)](https://sylph.ai/)
+[![OpenClaw](https://img.shields.io/badge/OpenClaw-CLI-teal)](https://github.com/openclaw/openclaw)
 [![Buy me a coffee](https://img.shields.io/badge/Buy%20me%20a-coffee-d13610?logo=buymeacoffee&logoColor=white)](https://www.buymeacoffee.com/eltonmachado)
 
 **AGI Agent Kit** is the enterprise-grade scaffolding that turns any AI coding assistant into a **deterministic production machine**. While LLMs are probabilistic (90% accuracy per step = 59% over 5 steps), this framework forces them through a **3-Layer Architecture** — Intent → Orchestration → Execution — where business logic lives in tested scripts, not hallucinated code.
@@ -21,11 +22,11 @@
 
 Most AI coding setups give you a prompt and hope for the best. AGI Agent Kit gives you:
 
-- 🧠 **Semantic Memory** — Qdrant-powered caching that eliminates redundant LLM calls (90-100% token savings)
+- 🧠 **Hybrid Memory** — Qdrant vectors + BM25 keywords: semantic similarity for concepts, exact matching for error codes and IDs (90-100% token savings)
 - 🎯 **19 Specialist Agents** — Domain-bounded experts (Frontend, Backend, Security, Mobile, Game Dev...) with enforced file ownership
-- ⚡ **861 Curated Skills** — 4 core + 75 professional + 782 community skills across 16 domain categories
+- ⚡ **878 Curated Skills** — 4 core + 89 professional + 785 community skills across 16 domain categories
 - 🔒 **Verification Gates** — No task completes without evidence. TDD enforcement. Two-stage code review.
-- 🌐 **8 Platforms, One Config** — Write once, run on Claude Code, Gemini CLI, Codex CLI, Cursor, Copilot, OpenCode, AdaL CLI, Antigravity IDE
+- 🌐 **9 Platforms, One Config** — Write once, run on Claude Code, Gemini CLI, Codex CLI, Cursor, Copilot, OpenCode, AdaL CLI, Antigravity IDE, OpenClaw
 
 ```bash
 npx @techwavedev/agi-agent-kit init
@@ -46,8 +47,8 @@ npx @techwavedev/agi-agent-kit init
 You'll be prompted to choose a pack:
 
 - **core** — 4 essential skills (webcrawler, pdf-reader, qdrant-memory, documentation)
-- **medium** — Core + 75 specialized skills in 16 categories + `.agent/` structure (API, Security, Design, Architecture)
-- **full** — Complete suite: Medium + 782 community skills from [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills) (861 total)
+- **medium** — Core + 89 specialized skills in 16 categories + `.agent/` structure (API, Security, Design, Architecture)
+- **full** — Complete suite: Medium + 785 community skills from [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills) (878 total)
 
 After installation, run the **one-shot setup wizard** to auto-configure your environment:
 
@@ -72,13 +73,13 @@ This checks Qdrant, Ollama, embedding models, and collections — auto-fixing an
 | Feature                       | Description                                                                                   |
 | ----------------------------- | --------------------------------------------------------------------------------------------- |
 | **Deterministic Execution**   | Separates business logic (Python scripts) from AI reasoning (Directives)                      |
-| **Modular Skill System**      | 861 plug-and-play skills across 3 tiers, organized in 16 domain categories                    |
+| **Modular Skill System**      | 878 plug-and-play skills across 3 tiers, organized in 16 domain categories                    |
 | **Structured Plan Execution** | Batch or subagent-driven execution with two-stage review (spec + quality)                     |
 | **TDD Enforcement**           | Iron-law RED-GREEN-REFACTOR cycle — no production code without failing test                   |
 | **Verification Gates**        | Evidence before claims — no completion without fresh verification output                      |
 | **Platform-Adaptive**         | Auto-detects Claude Code, Gemini CLI, Codex CLI, Cursor, Copilot, OpenCode, AdaL, Antigravity |
 | **Multi-Agent Orchestration** | Agent Teams, subagents, Powers, or sequential personas — adapts to platform                   |
-| **Semantic Memory**           | Built-in Qdrant-powered memory with 95% token savings via caching                             |
+| **Hybrid Memory**             | Qdrant vectors + BM25 keywords with weighted score merge (95% token savings)                  |
 | **Self-Healing Workflows**    | Agents read error logs, patch scripts, and update directives automatically                    |
 | **One-Shot Setup**            | Platform detection + project stack scan + auto-configuration in one command                   |
 
@@ -95,15 +96,15 @@ The agi framework adopts all best patterns from [obra/superpowers](https://githu
 | Systematic Debugging         |        ✅        | ✅ Adapted + `debugger` agent  |
 | Verification Gates           |        ✅        | ✅ Adapted + 12 audit scripts  |
 | Two-Stage Code Review        |        ✅        |  ✅ Adapted into orchestrator  |
-| Multi-Platform Orchestration |  ❌ Claude only  |         ✅ 4 platforms         |
+| Multi-Platform Orchestration |  ❌ Claude only  |         ✅ 9 platforms         |
 | Semantic Memory (Qdrant)     |        ❌        |    ✅ 90-100% token savings    |
 | 19 Specialist Agents         |        ❌        |      ✅ Domain boundaries      |
 | Agent Boundary Enforcement   |        ❌        |     ✅ File-type ownership     |
 | Dynamic Question Generation  |        ❌        |   ✅ Trade-offs + priorities   |
 | Memory-First Protocol        |        ❌        |       ✅ Auto cache-hit        |
-| Skill Creator + Catalog      |        ❌        |    ✅ 861 composable skills    |
+| Skill Creator + Catalog      |        ❌        |    ✅ 878 composable skills    |
 | Platform Setup Wizard        |        ❌        |       ✅ One-shot config       |
-| Multi-Platform Symlinks      |  ❌ Claude only  |         ✅ 8 platforms         |
+| Multi-Platform Symlinks      |  ❌ Claude only  |         ✅ 9 platforms         |
 
 ---
 
@@ -219,10 +220,10 @@ your-project/
 ├── CLAUDE.md → AGENTS.md
 ├── OPENCODE.md → AGENTS.md
 ├── COPILOT.md → AGENTS.md
-├── skills/                # Up to 861 skills (depends on pack)
+├── skills/                # Up to 878 skills (depends on pack)
 │   ├── webcrawler/        # Documentation harvesting
 │   ├── qdrant-memory/     # Semantic caching & memory
-│   └── ...                # 860 more skills in full pack
+│   └── ...                # 877 more skills in full pack
 ├── .claude/skills → skills/   # Platform-specific symlinks
 ├── .gemini/skills → skills/
 ├── .codex/skills → skills/
@@ -261,15 +262,16 @@ The system operates on three layers:
 
 ---
 
-## 🧠 Semantic Memory
+## 🧠 Hybrid Memory (BM25 + Vector)
 
-Built-in Qdrant-powered memory with automatic token savings:
+Dual-engine retrieval: Qdrant vector similarity for semantic concepts + SQLite FTS5 BM25 for exact keyword matching. Automatically merges results with configurable weights.
 
 | Scenario              | Without Memory | With Memory | Savings  |
 | --------------------- | -------------- | ----------- | -------- |
 | Repeated question     | ~2000 tokens   | 0 tokens    | **100%** |
 | Similar architecture  | ~5000 tokens   | ~500 tokens | **90%**  |
 | Past error resolution | ~3000 tokens   | ~300 tokens | **90%**  |
+| Exact ID/code lookup  | ~3000 tokens   | ~200 tokens | **93%**  |
 
 **Setup** (requires [Qdrant](https://qdrant.tech/) + [Ollama](https://ollama.com/)):
 
@@ -291,11 +293,27 @@ Agents automatically run `session_boot.py` at session start (first instruction i
 # Auto-query (check cache + retrieve context)
 python3 execution/memory_manager.py auto --query "your task summary"
 
-# Store a decision
+# Store a decision (auto-indexes into BM25)
 python3 execution/memory_manager.py store --content "what was decided" --type decision
 
-# Health check
+# Health check (includes BM25 index status)
 python3 execution/memory_manager.py health
+
+# Rebuild BM25 index from existing Qdrant data
+python3 execution/memory_manager.py bm25-sync
+```
+
+**Hybrid search modes** (via `hybrid_search.py`):
+
+```bash
+# True hybrid (default): vector + BM25 merged
+python3 scripts/hybrid_search.py --query "ImagePullBackOff error" --mode hybrid
+
+# Vector only (pure semantic)
+python3 scripts/hybrid_search.py --query "database architecture" --mode vector
+
+# Keyword only (exact BM25 match)
+python3 scripts/hybrid_search.py --query "sg-018f20ea63e82eeb5" --mode keyword
 ```
 
 ---
@@ -390,43 +408,54 @@ Use these keywords, commands, and phrases to trigger specific capabilities:
 
 ### Agent Mentions (`@agent`)
 
-| Mention                | Specialist              | When To Use                               |
-| ---------------------- | ----------------------- | ----------------------------------------- |
-| `@orchestrator`        | Multi-agent coordinator | Complex multi-domain tasks                |
-| `@project-planner`     | Planning specialist     | Roadmaps, task breakdowns, phase planning |
-| `@frontend-specialist` | UI/UX architect         | Web interfaces, React, Next.js            |
-| `@mobile-developer`    | Mobile specialist       | iOS, Android, React Native, Flutter       |
-| `@backend-specialist`  | API/DB engineer         | Server-side, databases, APIs              |
-| `@security-auditor`    | Security expert         | Vulnerability scanning, audits, hardening |
-| `@debugger`            | Debug specialist        | Complex bug investigation                 |
-| `@game-developer`      | Game dev specialist     | 2D/3D games, multiplayer, VR/AR           |
+| Mention                   | Specialist              | When To Use                                |
+| ------------------------- | ----------------------- | ------------------------------------------ |
+| `@orchestrator`           | Multi-agent coordinator | Complex multi-domain tasks                 |
+| `@project-planner`        | Planning specialist     | Roadmaps, task breakdowns, phase planning  |
+| `@frontend-specialist`    | UI/UX architect         | Web interfaces, React, Next.js             |
+| `@backend-specialist`     | API/DB engineer         | Server-side, databases, APIs               |
+| `@mobile-developer`       | Mobile specialist       | iOS, Android, React Native, Flutter        |
+| `@security-auditor`       | Security expert         | Vulnerability scanning, audits, hardening  |
+| `@debugger`               | Debug specialist        | Complex bug investigation                  |
+| `@game-developer`         | Game dev specialist     | 2D/3D games, multiplayer, VR/AR            |
+| `@devops-engineer`        | DevOps specialist       | CI/CD, containers, cloud infrastructure    |
+| `@database-architect`     | Database specialist     | Schema design, migrations, optimization    |
+| `@documentation-writer`   | Docs specialist         | Technical writing, API docs, READMEs       |
+| `@test-engineer`          | Testing specialist      | Test strategy, automation, coverage        |
+| `@qa-automation-engineer` | QA specialist           | E2E testing, regression, quality gates     |
+| `@performance-optimizer`  | Performance specialist  | Profiling, bottlenecks, optimization       |
+| `@seo-specialist`         | SEO specialist          | Search optimization, meta tags, rankings   |
+| `@penetration-tester`     | Pen testing specialist  | Red team exercises, exploit verification   |
+| `@product-manager`        | Product specialist      | Requirements, user stories, prioritization |
+| `@code-archaeologist`     | Legacy code specialist  | Understanding old codebases, migrations    |
+| `@explorer-agent`         | Discovery specialist    | Codebase exploration, dependency mapping   |
 
 ### Skill Trigger Keywords (Natural Language)
 
-| Category           | Trigger Words / Phrases                                                | Skill Activated                     |
-| ------------------ | ---------------------------------------------------------------------- | ----------------------------------- |
-| **Memory**         | "don't use cache", "no cache", "skip memory", "fresh"                  | Memory opt-out                      |
-| **Research**       | "research my docs", "check my notebooks", "deep search", "@notebooklm" | `notebooklm-rag`                    |
-| **Documentation**  | "update docs", "regenerate catalog", "sync documentation"              | `documentation`                     |
-| **Quality**        | "lint", "format", "check", "validate", "static analysis"               | `lint-and-validate`                 |
-| **Testing**        | "write tests", "run tests", "TDD", "test coverage"                     | `testing-patterns` / `tdd-workflow` |
-| **TDD**            | "test first", "red green refactor", "failing test"                     | `test-driven-development`           |
-| **Plan Execution** | "execute plan", "run the plan", "batch execution"                      | `executing-plans`                   |
-| **Verification**   | "verify", "prove it works", "evidence", "show me the output"           | `verification-before-completion`    |
-| **Debugging**      | "debug", "root cause", "investigate", "why is this failing"            | `systematic-debugging`              |
-| **Architecture**   | "design system", "architecture decision", "ADR", "trade-off"           | `architecture`                      |
-| **Security**       | "security scan", "vulnerability", "audit", "OWASP"                     | `red-team-tactics`                  |
-| **Performance**    | "lighthouse", "bundle size", "core web vitals", "profiling"            | `performance-profiling`             |
-| **Design**         | "design UI", "color scheme", "typography", "layout"                    | `frontend-design`                   |
-| **Deployment**     | "deploy", "rollback", "release", "CI/CD"                               | `deployment-procedures`             |
-| **API**            | "REST API", "GraphQL", "tRPC", "API design"                            | `api-patterns`                      |
-| **Database**       | "schema design", "migration", "query optimization"                     | `database-design`                   |
-| **Planning**       | "plan this", "break down", "task list", "requirements"                 | `plan-writing`                      |
-| **Brainstorming**  | "explore options", "what are the approaches", "pros and cons"          | `brainstorming`                     |
-| **Code Review**    | "review this", "code quality", "best practices"                        | `code-review-checklist`             |
-| **i18n**           | "translate", "localization", "RTL", "locale"                           | `i18n-localization`                 |
-| **AWS**            | "terraform", "EKS", "Lambda", "S3", "CloudFront"                       | `aws` / `aws-terraform`             |
-| **Infrastructure** | "Consul", "service mesh", "OpenSearch"                                 | `consul` / `opensearch`             |
+| Category           | Trigger Words / Phrases                                                | Skill Activated                       |
+| ------------------ | ---------------------------------------------------------------------- | ------------------------------------- |
+| **Memory**         | "don't use cache", "no cache", "skip memory", "fresh"                  | Memory opt-out                        |
+| **Research**       | "research my docs", "check my notebooks", "deep search", "@notebooklm" | `notebooklm-rag`                      |
+| **Documentation**  | "update docs", "regenerate catalog", "sync documentation"              | `documentation`                       |
+| **Quality**        | "lint", "format", "check", "validate", "static analysis"               | `lint-and-validate`                   |
+| **Testing**        | "write tests", "run tests", "TDD", "test coverage"                     | `testing-patterns` / `tdd-workflow`   |
+| **TDD**            | "test first", "red green refactor", "failing test"                     | `test-driven-development`             |
+| **Plan Execution** | "execute plan", "run the plan", "batch execution"                      | `executing-plans`                     |
+| **Verification**   | "verify", "prove it works", "evidence", "show me the output"           | `verification-before-completion`      |
+| **Debugging**      | "debug", "root cause", "investigate", "why is this failing"            | `systematic-debugging`                |
+| **Architecture**   | "design system", "architecture decision", "ADR", "trade-off"           | `architecture`                        |
+| **Security**       | "security scan", "vulnerability", "audit", "OWASP"                     | `red-team-tactics`                    |
+| **Performance**    | "lighthouse", "bundle size", "core web vitals", "profiling"            | `performance-profiling`               |
+| **Design**         | "design UI", "color scheme", "typography", "layout"                    | `frontend-design`                     |
+| **Deployment**     | "deploy", "rollback", "release", "CI/CD"                               | `deployment-procedures`               |
+| **API**            | "REST API", "GraphQL", "tRPC", "API design"                            | `api-patterns`                        |
+| **Database**       | "schema design", "migration", "query optimization"                     | `database-design`                     |
+| **Planning**       | "plan this", "break down", "task list", "requirements"                 | `plan-writing`                        |
+| **Brainstorming**  | "explore options", "what are the approaches", "pros and cons"          | `brainstorming`                       |
+| **Code Review**    | "review this", "code quality", "best practices"                        | `code-review-checklist`               |
+| **i18n**           | "translate", "localization", "RTL", "locale"                           | `i18n-localization`                   |
+| **AWS**            | "terraform", "EKS", "Lambda", "S3", "CloudFront"                       | `aws-skills` / `terraform-skill`      |
+| **Infrastructure** | "service mesh", "Kubernetes", "Helm"                                   | `docker-expert` / `server-management` |
 
 ### Memory System Commands
 
@@ -444,7 +473,7 @@ Use these keywords, commands, and phrases to trigger specific capabilities:
 ## 📚 Documentation
 
 - **[AGENTS.md](./AGENTS.md)** — Complete architecture and operating principles
-- **[skills/SKILLS_CATALOG.md](./skills/SKILLS_CATALOG.md)** — Skill catalog
+- **[skills/SKILLS_CATALOG.md](./templates/skills/SKILLS_CATALOG.md)** — Skill catalog
 - **[CHANGELOG.md](./CHANGELOG.md)** — Version history
 - **[THIRD-PARTY-LICENSES.md](./THIRD-PARTY-LICENSES.md)** — Third-party attributions
 
@@ -452,7 +481,7 @@ Use these keywords, commands, and phrases to trigger specific capabilities:
 
 ## 🤝 Community Skills & Credits
 
-The **Full** tier includes 782 community skills adapted from the [Antigravity Awesome Skills](https://github.com/sickn33/antigravity-awesome-skills) project (v5.4.0) by [@sickn33](https://github.com/sickn33), distributed under the MIT License.
+The **Full** tier includes 774 community skills adapted from the [Antigravity Awesome Skills](https://github.com/sickn33/antigravity-awesome-skills) project (v5.4.0) by [@sickn33](https://github.com/sickn33), distributed under the MIT License.
 
 This collection aggregates skills from 50+ open-source contributors and organizations including Anthropic, Microsoft, Vercel Labs, Supabase, Trail of Bits, Expo, Sentry, Neon, fal.ai, and many more. For the complete attribution ledger, see [SOURCES.md](https://github.com/sickn33/antigravity-awesome-skills/blob/main/docs/SOURCES.md).
 
@@ -466,7 +495,18 @@ If these community skills help you, consider [starring the original repo](https:
 
 ---
 
-## 🛡️ Security
+## �️ Roadmap
+
+| Feature                             | Status     | Description                                                                                                                                                                                                                                                           |
+| ----------------------------------- | ---------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Federated Agent Memory**          | 🔬 Design  | Cross-agent knowledge sharing via project-scoped Qdrant collections. Agents working on the same project read each other's decisions, errors, and patterns — building collective intelligence across sessions and platforms.                                           |
+| **Blockchain-Authenticated Memory** | 🔬 Design  | Cryptographic trust layer for shared memory using enterprise blockchains (Hyperledger Fabric, MultiChain, or Quorum) — self-hosted, no fees, no cryptocurrency. Agent writes are signed, content hashes are anchored on-chain, and access is token-gated per project. |
+| **Event-Driven Agent Streaming**    | 🔬 Design  | Real-time agent communication via Kafka/Flink. Agents publish decisions and observations to topics, enabling reactive workflows — e.g., a security agent triggers remediation when a vulnerability scan agent publishes findings.                                     |
+| **Workflow Engine**                 | 📋 Planned | Execute `data/workflows.json` playbooks as guided multi-skill sequences with progress tracking and branching logic.                                                                                                                                                   |
+
+---
+
+## �🛡️ Security
 
 This package includes a pre-flight security scanner that checks for private terms before publishing. All templates are sanitized for public use.
 

package/bin/init.js

@@ -9,8 +9,8 @@
  *
  * Packs:
  *   core   - Base framework + common skills (webcrawler, pdf-reader, qdrant-memory)
- *   medium - Core + 76 specialized skills + .agent structure
- *   full   - Medium + 782 community skills (complete suite)
+ *   medium - Core + 89 specialized skills + .agent structure
+ *   full   - Medium + 785 community skills (complete suite)
  *
  * Options:
  *   --path=<dir>    Target directory (default: current)
@@ -54,14 +54,14 @@ const PACKS = {
   medium: {
     name: "Medium",
     description:
-      "Core + 76 specialized skills + .agent structure (API, Security, Design, AI, Architecture)",
+      "Core + 89 specialized skills + .agent structure (API, Security, Design, AI, Architecture)",
     skills: ["core", "knowledge"],
     includeAgent: true,
   },
   full: {
     name: "Full Suite",
     description:
-      "Complete suite (Medium + 782 community skills from antigravity-awesome-skills)",
+      "Complete suite (Medium + 785 community skills from antigravity-awesome-skills v5.4.0)",
     skills: ["core", "knowledge", "extended"],
     includeAgent: true,
   },
@@ -113,10 +113,10 @@ ${colors.bright}Packs:${colors.reset}
   ${colors.green}core${colors.reset}      Base framework + common skills
            (webcrawler, pdf-reader, qdrant-memory, documentation)
 
-  ${colors.blue}medium${colors.reset}    Core + 76 specialized skills + .agent/ structure
+  ${colors.blue}medium${colors.reset}    Core + 89 specialized skills + .agent/ structure
            (API, Security, Design, AI, Architecture, Testing...)
   
-  ${colors.yellow}full${colors.reset}      Complete suite (Medium + 782 community skills)
+  ${colors.yellow}full${colors.reset}      Complete suite (Medium + 785 community skills)
            (All antigravity-awesome-skills, AGI-adapted)
 
 ${colors.bright}Examples:${colors.reset}
@@ -143,10 +143,10 @@ async function promptPackSelection() {
       `  1. ${colors.green}core${colors.reset}      Essential skills (webcrawler, pdf-reader, qdrant-memory, documentation)`,
     );
     console.log(
-      `  2. ${colors.blue}medium${colors.reset}    Core + 76 specialized skills + .agent/ structure`,
+      `  2. ${colors.blue}medium${colors.reset}    Core + 89 specialized skills + .agent/ structure`,
     );
     console.log(
-      `  3. ${colors.yellow}full${colors.reset}      Complete suite (Medium + 782 community skills)\n`,
+      `  3. ${colors.yellow}full${colors.reset}      Complete suite (Medium + 785 community skills from antigravity-awesome-skills)\n`,
     );
 
     rl.question(
@@ -254,7 +254,10 @@ function copySkills(targetPath, pack, templatesPath) {
           // Category directory (e.g., knowledge/frontend/) — recurse one level
           const categorySkills = fs
             .readdirSync(entryPath, { withFileTypes: true })
-            .filter((d) => d.isDirectory() && isSkillDir(path.join(entryPath, d.name)));
+            .filter(
+              (d) =>
+                d.isDirectory() && isSkillDir(path.join(entryPath, d.name)),
+            );
 
           for (const skill of categorySkills) {
             const src = path.join(entryPath, skill.name);
@@ -317,6 +320,15 @@ function copyBaseFiles(targetPath, templatesPath, options) {
     copyDirSync(srcSkillCreator, destSkillCreator);
     log.success("Installed skill-creator/");
   }
+
+  // Copy data (workflows metadata)
+  const srcData = path.join(templatesPath, "base", "data");
+  const destData = path.join(targetPath, "data");
+
+  if (fs.existsSync(srcData)) {
+    copyDirSync(srcData, destData);
+    log.success("Installed data/ (workflows metadata)");
+  }
 }
 
 // Create symlinks for multi-platform support
@@ -336,6 +348,7 @@ function createSymlinks(targetPath) {
     { name: "CLAUDE.md", target: "AGENTS.md" },
     { name: "OPENCODE.md", target: "AGENTS.md" },
     { name: "COPILOT.md", target: "AGENTS.md" },
+    { name: "OPENCLAW.md", target: "AGENTS.md" },
   ];
 
   for (const link of instructionSymlinks) {
@@ -365,6 +378,7 @@ function createSymlinks(targetPath) {
     { platform: ".codex/skills", platformName: "Codex CLI" },
     { platform: ".cursor/skills", platformName: "Cursor" },
     { platform: ".adal/skills", platformName: "AdaL CLI" },
+    { platform: ".openclaw/skills", platformName: "OpenClaw" },
   ];
 
   for (const { platform, platformName } of platformDirs) {
@@ -389,9 +403,13 @@ function createSymlinks(targetPath) {
       // Create relative symlink: .claude/skills → ../skills
       const relativeTarget = path.relative(parentDir, skillsDir);
       fs.symlinkSync(relativeTarget, linkPath);
-      log.success(`Created skill symlink: ${platform} → skills/ (${platformName})`);
+      log.success(
+        `Created skill symlink: ${platform} → skills/ (${platformName})`,
+      );
     } catch (err) {
-      log.warn(`Failed to create skill symlink for ${platformName}: ${err.message}`);
+      log.warn(
+        `Failed to create skill symlink for ${platformName}: ${err.message}`,
+      );
     }
   }
 }

package/package.json

@@ -1,10 +1,13 @@
 {
   "name": "@techwavedev/agi-agent-kit",
-  "version": "1.3.5",
+  "version": "1.4.2",
   "description": "Enterprise-Grade Agentic Framework - Modular skill-based AI assistant toolkit with deterministic execution, semantic memory, and platform-adaptive orchestration.",
   "bin": {
     "agi-agent-kit": "./bin/init.js"
   },
+  "scripts": {
+    "prepublishOnly": "python3 .agent/scripts/release_gate.py"
+  },
   "files": [
     "bin/",
     "templates/",

package/templates/base/AGENTS.md

@@ -1,6 +1,6 @@
 # Agent Instructions
 
-> `CLAUDE.md`, `GEMINI.md`, and `OPENCODE.md` are symlinks to this file, so the same instructions load in any AI environment.
+> `CLAUDE.md`, `GEMINI.md`, `OPENCODE.md`, `COPILOT.md`, and `OPENCLAW.md` are symlinks to this file, so the same instructions load in any AI environment.
 
 ---
 
@@ -163,7 +163,7 @@ python execution/scrape_single_site.py \
 
 ### 1. Memory-First (Automatic)
 
-**All operations use the Qdrant-powered memory system by default.**
+**All operations use the Hybrid Memory System (Qdrant + BM25) by default.**
 
 #### Session Start (MANDATORY — run once per session)
 
@@ -270,6 +270,33 @@ Before marking a task complete:
 - Spot-check data quality where possible
 - Confirm deliverables are in the expected location (cloud service, output file, etc.)
 
+### 6. Release Governance Protocol (MANDATORY)
+
+**Before merging to `public` branch or publishing to NPM, YOU MUST:**
+
+1.  **Execute the Release Gate**:
+
+    ```bash
+    python3 .agent/scripts/release_gate.py
+    ```
+
+    This validates:
+    - Documentation (README/CHANGELOG) presence & updates
+    - Security (Secret scanning)
+    - Code Syntax (Python/JS)
+    - Version Consistency (package.json vs CHANGELOG)
+    - Git Status (Clean working tree)
+
+2.  **Verify Workflow**:
+    - Review `.agent/workflows/release-protocol.md` for manual steps.
+    - Ensure `AGENTS.md` and `memory_integration.md` are up-to-date with code.
+
+3.  **Publish via Script**:
+    - Do NOT run `npm publish` manually.
+    - Run `npm run prepublishOnly` (or relying on the lifecycle hook) to enforce the gate.
+
+**ZERO TOLERANCE:** Never bypass the Release Gate. If it fails, FIX the issue. Do not force push.
+
 ---
 
 ## File Organization
@@ -384,6 +411,65 @@ For frequently-used processes, create workflows in `.agent/workflows/`:
 
 ---
 
+## Playbook Engine (Multi-Skill Sequences)
+
+For complex, multi-step tasks, use **playbooks** — pre-defined sequences of skills that guide you through a complete workflow with progress tracking.
+
+### How It Works
+
+Playbooks are defined in `data/workflows.json`. Each playbook is a sequence of steps, and each step recommends specific skills to use. The Workflow Engine (`execution/workflow_engine.py`) manages state, tracks progress, and tells you which skills to activate at each step.
+
+### Quick Start
+
+```bash
+# 1. See available playbooks
+python3 execution/workflow_engine.py list
+
+# 2. Start a playbook
+python3 execution/workflow_engine.py start ship-saas-mvp
+
+# 3. The engine shows Step 1 with recommended skills — execute them
+
+# 4. When step is done, mark it complete and get next step
+python3 execution/workflow_engine.py complete --notes "Planned scope with brainstorming skill"
+
+# 5. Check overall progress at any time
+python3 execution/workflow_engine.py status
+```
+
+### Agent Protocol for Playbooks
+
+When a user says `/playbook`, "run a playbook", or asks for a multi-step workflow:
+
+1. **List playbooks**: `python3 execution/workflow_engine.py list`
+2. **Ask the user** which playbook to run (or auto-select if the intent is clear)
+3. **Start it**: `python3 execution/workflow_engine.py start <id>`
+4. **For each step**:
+   a. Read the step's `goal` and `recommendedSkills` from the engine output
+   b. Read the relevant `SKILL.md` files for the recommended skills
+   c. Execute the step using those skills' instructions
+   d. Mark complete: `python3 execution/workflow_engine.py complete --notes "what was done"`
+5. **If a step is not applicable**, skip it: `python3 execution/workflow_engine.py skip --reason "why"`
+6. **If the user wants to stop**, abort: `python3 execution/workflow_engine.py abort`
+
+### Commands Reference
+
+| Command    | Description                             | When to Use                  |
+| ---------- | --------------------------------------- | ---------------------------- |
+| `list`     | Show all available playbooks            | User asks "what playbooks?"  |
+| `start`    | Begin a playbook, get Step 1            | User selects a playbook      |
+| `next`     | Show current step details               | Need to re-read current step |
+| `status`   | Show progress bar and step statuses     | User asks "where are we?"    |
+| `complete` | Mark current step done, advance to next | Step work is finished        |
+| `skip`     | Skip current step with reason           | Step not applicable          |
+| `abort`    | Cancel the active playbook              | User wants to stop           |
+
+> **State persistence:** Progress is saved in `.tmp/playbook_state.json`. If a session ends mid-playbook, the next session can resume with `python3 execution/workflow_engine.py next`.
+
+> **Skill availability:** The engine checks which recommended skills are actually installed and flags missing ones with ⚠️ so you can adapt.
+
+---
+
 ## Best Practices for Execution Scripts
 
 ### Script Template

package/templates/base/README.md

@@ -23,7 +23,7 @@ Most AI coding setups give you a prompt and hope for the best. AGI Agent Kit giv
 
 - 🧠 **Semantic Memory** — Qdrant-powered caching that eliminates redundant LLM calls (90-100% token savings)
 - 🎯 **19 Specialist Agents** — Domain-bounded experts (Frontend, Backend, Security, Mobile, Game Dev...) with enforced file ownership
-- ⚡ **861 Curated Skills** — 4 core + 75 professional + 782 community skills across 16 domain categories
+- ⚡ **853 Curated Skills** — 4 core + 75 professional + 774 community skills across 16 domain categories
 - 🔒 **Verification Gates** — No task completes without evidence. TDD enforcement. Two-stage code review.
 - 🌐 **8 Platforms, One Config** — Write once, run on Claude Code, Gemini CLI, Codex CLI, Cursor, Copilot, OpenCode, AdaL CLI, Antigravity IDE
 
@@ -47,7 +47,7 @@ You'll be prompted to choose a pack:
 
 - **core** — 4 essential skills (webcrawler, pdf-reader, qdrant-memory, documentation)
 - **medium** — Core + 75 specialized skills in 16 categories + `.agent/` structure (API, Security, Design, Architecture)
-- **full** — Complete suite: Medium + 782 community skills from [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills) (861 total)
+- **full** — Complete suite: Medium + 774 community skills from [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills) (853 total)
 
 After installation, run the **one-shot setup wizard** to auto-configure your environment:
 
@@ -72,7 +72,7 @@ This checks Qdrant, Ollama, embedding models, and collections — auto-fixing an
 | Feature                       | Description                                                                                   |
 | ----------------------------- | --------------------------------------------------------------------------------------------- |
 | **Deterministic Execution**   | Separates business logic (Python scripts) from AI reasoning (Directives)                      |
-| **Modular Skill System**      | 861 plug-and-play skills across 3 tiers, organized in 16 domain categories                    |
+| **Modular Skill System**      | 853 plug-and-play skills across 3 tiers, organized in 16 domain categories                    |
 | **Structured Plan Execution** | Batch or subagent-driven execution with two-stage review (spec + quality)                     |
 | **TDD Enforcement**           | Iron-law RED-GREEN-REFACTOR cycle — no production code without failing test                   |
 | **Verification Gates**        | Evidence before claims — no completion without fresh verification output                      |
@@ -101,7 +101,7 @@ The agi framework adopts all best patterns from [obra/superpowers](https://githu
 | Agent Boundary Enforcement   |        ❌        |     ✅ File-type ownership     |
 | Dynamic Question Generation  |        ❌        |   ✅ Trade-offs + priorities   |
 | Memory-First Protocol        |        ❌        |       ✅ Auto cache-hit        |
-| Skill Creator + Catalog      |        ❌        |    ✅ 861 composable skills    |
+| Skill Creator + Catalog      |        ❌        |    ✅ 853 composable skills    |
 | Platform Setup Wizard        |        ❌        |       ✅ One-shot config       |
 | Multi-Platform Symlinks      |  ❌ Claude only  |         ✅ 8 platforms         |
 
@@ -219,10 +219,10 @@ your-project/
 ├── CLAUDE.md → AGENTS.md
 ├── OPENCODE.md → AGENTS.md
 ├── COPILOT.md → AGENTS.md
-├── skills/                # Up to 861 skills (depends on pack)
+├── skills/                # Up to 853 skills (depends on pack)
 │   ├── webcrawler/        # Documentation harvesting
 │   ├── qdrant-memory/     # Semantic caching & memory
-│   └── ...                # 860 more skills in full pack
+│   └── ...                # 852 more skills in full pack
 ├── .claude/skills → skills/   # Platform-specific symlinks
 ├── .gemini/skills → skills/
 ├── .codex/skills → skills/
@@ -452,7 +452,7 @@ Use these keywords, commands, and phrases to trigger specific capabilities:
 
 ## 🤝 Community Skills & Credits
 
-The **Full** tier includes 782 community skills adapted from the [Antigravity Awesome Skills](https://github.com/sickn33/antigravity-awesome-skills) project (v5.4.0) by [@sickn33](https://github.com/sickn33), distributed under the MIT License.
+The **Full** tier includes 774 community skills adapted from the [Antigravity Awesome Skills](https://github.com/sickn33/antigravity-awesome-skills) project (v5.4.0) by [@sickn33](https://github.com/sickn33), distributed under the MIT License.
 
 This collection aggregates skills from 50+ open-source contributors and organizations including Anthropic, Microsoft, Vercel Labs, Supabase, Trail of Bits, Expo, Sentry, Neon, fal.ai, and many more. For the complete attribution ledger, see [SOURCES.md](https://github.com/sickn33/antigravity-awesome-skills/blob/main/docs/SOURCES.md).