everything-gemini 1.1.1 → 1.8.0

package/docs/COMMUNITY_SUBMISSIONS.md

@@ -0,0 +1,88 @@
+# 🌟 Community Directory Submissions & Backlink Guide
+
+Submitting **Everything Gemini (`everything-gemini`)** to curated GitHub awesome-lists and developer directories is one of the highest-leverage ways to generate organic inbound stars, community backlinks, and developer adoption.
+
+---
+
+## 📋 1. `e2b-dev/awesome-ai-agents`
+
+* **Repository**: [https://github.com/e2b-dev/awesome-ai-agents](https://github.com/e2b-dev/awesome-ai-agents)
+* **Direct Edit URL**: [https://github.com/e2b-dev/awesome-ai-agents/edit/main/README.md](https://github.com/e2b-dev/awesome-ai-agents/edit/main/README.md)
+* **Exact Insertion Position**: Between `## [evo.ninja]` and `## [FastAgency]`
+* **Verified Entry (matches their exact `<details>` schema)**:
+  ```markdown
+  ## [Everything Gemini](https://github.com/salmandev/everything-gemini)
+  Open-source multi-agent harness & progressive disclosure skills for Google Antigravity & Gemini
+
+  <details>
+
+  ![Image](https://raw.githubusercontent.com/salmandev/everything-gemini/main/assets/banner.jpg)
+
+  ### Category
+  Coding, Developer Tools, Multi-agent, Autonomous agents
+
+  ### Description
+  - Open-source multi-agent harness, progressive disclosure skills ecosystem, and lifecycle safety suite designed for Google Antigravity and Gemini 3.8.
+  - Features 30 lazy-loaded progressive disclosure skills saving up to 85% token overhead.
+  - Harnesses Gemini's 2M token context window with static prefix caching.
+  - Dedicated 6-subagent fleet (Planner, Code Reviewer, Build Repair, Browser QA, Security Auditor, Architect).
+  - Deterministic lifecycle security gates (GeminiShield) intercepting destructive operations before execution.
+  - Zero-dependency distribution: instant install via `npx everything-gemini install`.
+
+  ### Links
+  - [GitHub](https://github.com/salmandev/everything-gemini)
+  - [Web](https://salmandev.github.io/everything-gemini/)
+  - [NPM](https://www.npmjs.com/package/everything-gemini)
+
+  </details>
+  ```
+* **Pull Request Title**: `docs: add Everything Gemini to AI agents directory`
+* **Pull Request Body**:
+  ```markdown
+  ### Summary
+  Adds **Everything Gemini (`everything-gemini`)** to the list of autonomous coding and multi-agent frameworks.
+
+  - **Repository**: https://github.com/salmandev/everything-gemini
+  - **Category**: Coding, Developer Tools, Multi-agent
+  - **Description**: Open-source agent harness and 30-skill progressive disclosure suite for Google Antigravity and Gemini 3.8.
+  ```
+
+---
+
+## 📋 2. `GoogleCloudPlatform/generative-ai`
+
+* **Repository**: [https://github.com/GoogleCloudPlatform/generative-ai](https://github.com/GoogleCloudPlatform/generative-ai)
+* **Direct Edit URL**: [https://github.com/GoogleCloudPlatform/generative-ai/edit/main/README.md](https://github.com/GoogleCloudPlatform/generative-ai/edit/main/README.md)
+* **Exact Insertion Position**: Under `## Related Repositories` -> `Other`
+* **Verified Entry**:
+  ```markdown
+  - [Everything Gemini](https://github.com/salmandev/everything-gemini) - Open-source multi-agent harness & progressive disclosure skills ecosystem for Google Antigravity and Gemini 3.8.
+  ```
+* **Pull Request Title**: `docs: add Everything Gemini to related repositories`
+* **Pull Request Body**:
+  ```markdown
+  Adds Everything Gemini to the Related Repositories section. Everything Gemini is an open-source multi-agent harness and progressive disclosure skills ecosystem designed specifically for Gemini and Google Antigravity.
+  ```
+
+---
+
+## 📋 3. `punkpeye/awesome-mcp-servers`
+
+* **Repository**: [https://github.com/punkpeye/awesome-mcp-servers](https://github.com/punkpeye/awesome-mcp-servers)
+* **Direct Edit URL**: [https://github.com/punkpeye/awesome-mcp-servers/edit/main/README.md](https://github.com/punkpeye/awesome-mcp-servers/edit/main/README.md)
+* **Exact Insertion Position**: Under `### 🤖 Coding Agents` (around line 770)
+* **Verified Entry**:
+  ```markdown
+  - [salmandev/everything-gemini](https://github.com/salmandev/everything-gemini) 🪐 🏠 🍎 🪟 🐧 - Open-source multi-agent harness & performance ecosystem for Google Antigravity and Gemini with pre-configured MCP blueprints (GitHub, Postgres, SQLite, Scraping), 30 progressive skills, and lifecycle safety gates.
+  ```
+* **Pull Request Title**: `docs: add Everything Gemini to coding agents`
+
+---
+
+## 📋 4. `f/awesome-chatgpt-prompts` / AI Systems Lists
+
+* **Section**: `Developer Tools & Coding Assistants`
+* **Suggested Entry**:
+  ```markdown
+  - [Everything Gemini](https://github.com/salmandev/everything-gemini) - Progressive disclosure skills ecosystem and multi-agent orchestrator designed specifically for Google Gemini.
+  ```

package/docs/LAUNCH_KIT.md

@@ -8,11 +8,11 @@ This launch kit contains ready-to-post announcements, social copy, and submissio
 
 ### Option A: The High-Impact Single Tweet (251 chars)
 ```text
-🪐 Everything Gemini v1.1.0 is live!
+🪐 Everything Gemini v1.2.0 is live!
 
 The open-source multi-agent harness for Google Antigravity & Gemini 3.8.
 
-⚡ 27 lazy-loaded skills (Multimodal, RAG, 2M context caching)
+⚡ 30 lazy-loaded skills (Multimodal, RAG, Evals, 2M context caching)
 🤖 6 scoped subagents
 🛡️ GeminiShield safety gates
 
@@ -33,9 +33,10 @@ Introducing Everything Gemini 🪐 — the open-source agent harness & multi-age
 **Tweet 2 (Core Innovations)**:
 ```text
 Unlike traditional prompt dumps, Everything Gemini uses strict Progressive Disclosure:
-- 🧠 27 lazy-loaded skills load runbooks on demand (saving up to 85% token overhead).
+- 🧠 30 lazy-loaded skills load runbooks on demand (saving up to 85% token overhead).
 - ⚡ Exploits Gemini's 2M token context with static prefix caching.
 - 👁️ Multimodal visual QA with automated WebP recordings.
+- 🧪 Agent Evals with LLM-as-a-judge scoring rubrics.
 ```
 
 **Tweet 3 (Fleet & Safety)**:
@@ -63,7 +64,7 @@ Give it a ⭐ and let me know what skills to add next!
 
 **Title**:
 ```text
-Everything Gemini: Open-source multi-agent harness, 27 progressive skills & subagent fleet for Google Antigravity
+Everything Gemini: Open-source multi-agent harness, 30 progressive skills & subagent fleet for Google Antigravity
 ```
 
 **Body**:
@@ -74,10 +75,10 @@ With Google Antigravity rolling out across Desktop 2.0, IDE, and CLI surfaces, I
 
 ### 🌟 Key Highlights
 
-1. **27 Lazy-Loaded Progressive Disclosure Skills**:
-   - **Frontier**: Native multimodal UI testing, 2M token prefix context caching, real-time Google Search grounding, RAG with re-ranking (`rag-architect`), and typed function calling schemas.
-   - **Cloud & Backend**: Supabase RLS policies, Cloudflare Workers & D1 SQL, Kubernetes manifests with HPA, Stripe webhook verification, and Next.js App Router.
-   - **Engineering**: Test-Driven Development (Red-Green-Refactor), automated git bisect debugging, GitHub Ops, and performance profiling.
+1. **30 Lazy-Loaded Progressive Disclosure Skills**:
+   - **Frontier**: Native multimodal UI testing, 2M token prefix context caching, real-time Google Search grounding, RAG with re-ranking (`rag-architect`), agent evaluations (`agent-evals`), and typed function calling schemas.
+   - **Cloud & Backend**: Supabase RLS policies, Cloudflare Workers & D1 SQL, Kubernetes manifests with HPA, GraphQL APIs with DataLoader, Stripe webhook verification, and Next.js App Router.
+   - **Engineering & DevOps**: Docker Compose orchestrator, Test-Driven Development (Red-Green-Refactor), automated git bisect debugging, GitHub Ops, and performance profiling.
 
 2. **6 Scoped Subagents (`agents/`)**:
    - Specialized specifications for **Planner**, **Code Reviewer**, **Build Repair**, **Browser QA**, **Security Auditor**, and **Architect** with formal task delegation and boundary protocols.
@@ -120,7 +121,7 @@ As coding agents move beyond simple single-turn prompts into multi-step autonomo
 
 Inspired by Affan Mustafa's Everything Claude Code (ECC), I built Everything Gemini (everything-gemini) specifically optimized for Google Antigravity and Gemini's architecture:
 
-- Progressive Disclosure: The agent only sees metadata in its system prompt; complete procedural playbooks (27 skills) are lazy-loaded only when triggered by user intent.
+- Progressive Disclosure: The agent only sees metadata in its system prompt; complete procedural playbooks (30 skills) are lazy-loaded only when triggered by user intent.
 - Massive Context Economics: Harnesses Gemini's 1M-2M token window with static prefix caching (~75% cost reduction).
 - Scoped Subagent Fleet: Discrete roles for Planner, Reviewer, Browser QA, Build Repair, Security, and Architect.
 - GeminiShield: Deterministic PreToolUse lifecycle gates intercepting catastrophic commands.
@@ -133,24 +134,149 @@ Would love to hear your thoughts and feedback!
 
 ---
 
-## 💼 4. LinkedIn Post
+---
+
+## 💼 4. LinkedIn Master Announcement
+
+### Option A: The Executive & Technical Leader Post
+```text
+🚀 Today, I'm thrilled to open-source Everything Gemini (everything-gemini) — the comprehensive agent harness, multi-agent orchestrator, and performance ecosystem native to Google Antigravity and Gemini 3.8.
+
+If you've been working with AI coding agents, you've likely hit these critical bottlenecks:
+1️⃣ Context Bloat: Dumping entire prompt books into every turn erodes reasoning capacity.
+2️⃣ Execution Risk: Agents accidentally running destructive commands (`rm -rf`, raw DB drops).
+3️⃣ Cognitive Fatigue: Agents stopping prematurely before automated test suites pass.
+
+Claude Code developers have ECC (Everything Claude Code).
+Now, the Google Antigravity & Gemini ecosystem has Everything Gemini. 🪐
+
+Here is what we engineered:
+
+🧠 30 Progressive Disclosure Skills:
+Instead of loading 48,000 tokens on every turn, skills load their runbooks on-demand ONLY when user intent matches. Result: >85% token reduction and 3x faster first-token latency.
+Covering: Native Multimodal Vision, 2M Prefix Context Caching, Agent Evals (LLM-as-a-judge), RAG with Re-ranking, Supabase, Cloudflare Workers, Docker Compose, and Kubernetes.
+
+🤖 6 Scoped Subagents with Rigid Handoffs:
+Dedicated roles for Planner, Code Reviewer, Browser QA, Build Repair, Security Auditor, and Architect. No more hallucinated roles or prompt contamination.
+
+🛡️ GeminiShield Lifecycle Safety:
+Deterministic PreToolUse shell interception that blocks catastrophic commands before execution, coupled with PostToolUse auto-formatters and Stop-guard test verifiers.
+
+📦 Zero-Dependency Distribution:
+Install directly in 1 second without cloning:
+$ npx everything-gemini install
+
+Or drop it straight into your CI/CD pipelines:
+uses: salmandev/everything-gemini@v1
+
+🌐 Interactive Web Showcase: https://salmandev.github.io/everything-gemini/
+💻 GitHub (Apache 2.0): https://github.com/salmandev/everything-gemini
+📦 NPM: https://www.npmjs.com/package/everything-gemini
+
+Give it a ⭐ on GitHub and let me know in the comments: what custom skill or lifecycle gate should we add next?
+
+#GoogleGemini #GoogleAntigravity #ArtificialIntelligence #SoftwareEngineering #OpenSource #DevTools #MachineLearning #AIAgents
+```
+
+---
+
+## 🧵 5. Threads (Meta) Viral 5-Post Thread
+
+**Post 1 (Hook)**:
+```text
+AI coding agents are powerful, but without guardrails, they suffer from context window bloat and catastrophic terminal commands.
+
+Claude Code has ECC.
+Now Google Antigravity has Everything Gemini. 🪐
+
+Introducing everything-gemini — the open-source agent harness & multi-agent orchestrator. 🧵👇
+```
+
+**Post 2 (Progressive Disclosure & Economics)**:
+```text
+The secret sauce is Progressive Disclosure:
+Instead of dumping 48,000 prompt tokens into every turn, skills are lazy-loaded only when triggered.
+
+⚡ 30 skills (Multimodal QA, 2M prefix caching, Agent Evals, RAG)
+⚡ >85% token savings per prompt turn
+⚡ Exploits Gemini 3.8's 2M token context window
+```
+
+**Post 3 (The Subagent Fleet)**:
+```text
+It features 6 scoped subagents with formal delegation boundaries:
+• Planner 📐
+• Code Reviewer 🔍
+• Browser QA 🌐 (automated WebP recording)
+• Build Repair 🛠️
+• Security Auditor 🔐
+• Architect 🏛️
+
+Each handles one job with zero token contamination.
+```
+
+**Post 4 (GeminiShield Safety Gate)**:
+```text
+Tired of agents running destructive bash commands?
+
+GeminiShield is a deterministic PreToolUse gate that intercepts `rm -rf`, `DROP TABLE`, or force pushes before they hit your terminal.
+
+Plus Stop hooks that prevent the agent from quitting until tests pass!
+```
 
+**Post 5 (Call to Action)**:
 ```text
-🚀 Excited to launch Everything Gemini (everything-gemini) — an open-source multi-agent harness and performance suite for Google Antigravity and Gemini 3.8!
+Install in 1 second anywhere:
+$ npx everything-gemini install
+
+Or use in GitHub Actions:
+uses: salmandev/everything-gemini@v1
+
+🌐 Live Showcase: https://salmandev.github.io/everything-gemini/
+💻 GitHub: https://github.com/salmandev/everything-gemini
 
-As AI coding platforms evolve, developers need structured engineering workflows, deterministic safety rails, and context-efficient architectures.
+Drop a 🪐 if you're building with Gemini!
+```
+
+---
+
+## 🏆 6. Product Hunt Launch Kit
+
+**Product Name**: Everything Gemini
+**Tagline**: Multi-agent harness, 30 skills & safety gates for Google Antigravity
+**Topics**: Developer Tools, Artificial Intelligence, Open Source, GitHub Actions
+
+**Short Description**:
+The open-source multi-agent harness for Google Antigravity & Gemini. Features 30 lazy-loaded progressive disclosure skills, 6 scoped subagents, GeminiShield safety gates, and 1-second `npx` install.
+
+**Maker First Comment**:
+```text
+Hey Product Hunt! 👋
 
-🪐 Everything Gemini delivers:
-✅ 27 Progressive Disclosure Skills (Multimodal vision, 2M context caching, RAG with re-ranking, Supabase, Cloudflare Workers, GitHub Ops)
-✅ 6 Scoped Subagents with formal delegation boundaries (Planner, Reviewer, QA, Repair, Security, Architect)
-✅ GeminiShield deterministic lifecycle safety hooks
-✅ 1-second setup: `npx everything-gemini install`
+I'm excited to share Everything Gemini (everything-gemini).
 
-Check out our interactive showcase catalog:
-👉 https://salmandev.github.io/everything-gemini/
+As AI coding assistants transition from simple autocomplete into autonomous agentic pair programmers (like Google Antigravity), they face critical challenges:
+1. System prompt bloat consuming massive context.
+2. Accidental destructive shell executions.
+3. Premature completion before tests pass.
 
-GitHub repository:
-👉 https://github.com/salmandev/everything-gemini
+Everything Gemini provides a hardened harness architecture:
+• 30 Progressive Disclosure Skills (lazy-loaded on-demand, saving >85% token overhead).
+• 6 Scoped Subagents with deterministic delegation (Planner, Reviewer, QA, Repair, Security, Architect).
+• GeminiShield: PreToolUse lifecycle gates stopping catastrophic commands.
+• GitHub Composite Action (`uses: salmandev/everything-gemini@v1`).
+• Zero-dependency CLI: `npx everything-gemini install`.
 
-#AI #GoogleGemini #GoogleAntigravity #SoftwareEngineering #OpenSource #DevTools #MachineLearning
+Everything is open source under Apache 2.0. We'd love your feedback!
 ```
+
+---
+
+## ✍️ 7. Technical Blog Draft (Dev.to / Hashnode / Medium)
+
+**Title**: *Supercharging Google Antigravity: How We Built an Open-Source Multi-Agent Harness with 85% Token Savings*
+
+**Summary**:
+A deep technical dive into agent harnesses, progressive disclosure architectures, lifecycle safety hooks, and multi-agent delegation patterns tailored for Google Antigravity and Gemini 3.8.
+*(Available for cross-posting from the repository documentation)*.
+

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 (e.g. naive)    | ~48,000 tokens / turn    |
-| Everything Gemini Progressive Disc. | ~3,200 tokens / turn     |
+| Monolithic Prompts (52+ skills)    | ~48,000+ tokens / turn   |
+| Everything Gemini Progressive Disc.| ~3,800 tokens / turn     |
 +------------------------------------+--------------------------+
-| Net Token Savings                  | 85% - 93%                |
+| Net Token Savings                  | 85% - 92% (>40,000 saved)|
 +------------------------------------+--------------------------+
 ```