@b0tts/template-dev-installer 1.0.0

package/files/.agents/skills/write-a-skill/SKILL.md

@@ -0,0 +1,117 @@
+---
+name: write-a-skill
+description: Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
+---
+
+# Writing Skills
+
+## Process
+
+1. **Gather requirements** - ask user about:
+   - What task/domain does the skill cover?
+   - What specific use cases should it handle?
+   - Does it need executable scripts or just instructions?
+   - Any reference materials to include?
+
+2. **Draft the skill** - create:
+   - SKILL.md with concise instructions
+   - Additional reference files if content exceeds 500 lines
+   - Utility scripts if deterministic operations needed
+
+3. **Review with user** - present draft and ask:
+   - Does this cover your use cases?
+   - Anything missing or unclear?
+   - Should any section be more/less detailed?
+
+## Skill Structure
+
+```
+skill-name/
+├── SKILL.md           # Main instructions (required)
+├── REFERENCE.md       # Detailed docs (if needed)
+├── EXAMPLES.md        # Usage examples (if needed)
+└── scripts/           # Utility scripts (if needed)
+    └── helper.js
+```
+
+## SKILL.md Template
+
+```md
+---
+name: skill-name
+description: Brief description of capability. Use when [specific triggers].
+---
+
+# Skill Name
+
+## Quick start
+
+[Minimal working example]
+
+## Workflows
+
+[Step-by-step processes with checklists for complex tasks]
+
+## Advanced features
+
+[Link to separate files: See [REFERENCE.md](REFERENCE.md)]
+```
+
+## Description Requirements
+
+The description is **the only thing your agent sees** when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.
+
+**Goal**: Give your agent just enough info to know:
+
+1. What capability this skill provides
+2. When/why to trigger it (specific keywords, contexts, file types)
+
+**Format**:
+
+- Max 1024 chars
+- Write in third person
+- First sentence: what it does
+- Second sentence: "Use when [specific triggers]"
+
+**Good example**:
+
+```
+Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.
+```
+
+**Bad example**:
+
+```
+Helps with documents.
+```
+
+The bad example gives your agent no way to distinguish this from other document skills.
+
+## When to Add Scripts
+
+Add utility scripts when:
+
+- Operation is deterministic (validation, formatting)
+- Same code would be generated repeatedly
+- Errors need explicit handling
+
+Scripts save tokens and improve reliability vs generated code.
+
+## When to Split Files
+
+Split into separate files when:
+
+- SKILL.md exceeds 100 lines
+- Content has distinct domains (finance vs sales schemas)
+- Advanced features are rarely needed
+
+## Review Checklist
+
+After drafting, verify:
+
+- [ ] Description includes triggers ("Use when...")
+- [ ] SKILL.md under 100 lines
+- [ ] No time-sensitive info
+- [ ] Consistent terminology
+- [ ] Concrete examples included
+- [ ] References one level deep

package/files/.agents/skills/zoom-out/SKILL.md

@@ -0,0 +1,7 @@
+---
+name: zoom-out
+description: Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
+disable-model-invocation: true
+---
+
+I don't know this area of code well. Go up a layer of abstraction. Give me a map of all the relevant modules and callers, using the project's domain glossary vocabulary.

package/files/AGENTS.md

@@ -0,0 +1,40 @@
+# AGENTS.md
+
+This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, Antigravity, etc.) when working with code in this repository.
+
+### Core Rules
+
+- If a task matches a skill, you MUST invoke it
+- Skills are located in `skills/<skill-name>/SKILL.md`
+- Never implement directly if a skill applies
+- Always follow the skill instructions exactly (do not partially apply them)
+- **NEVER attempt to SSH into the VPS.** The VPS is strictly off-limits for direct access. All VPS information is documented in the navigation guides — read those instead.
+
+### Execution Model
+
+For every request:
+
+1. Determine if any skill applies (even 1% chance)
+2. Invoke the appropriate skill using the `skill` tool
+3. Follow the skill workflow strictly
+4. Only proceed to implementation after required steps (spec, plan, etc.) are complete
+
+### Navigation Guides
+
+Reference documents for configured services and systems (VPS, Docker, Minecraft, Prism, etc.) are stored in `b0ttsagent/NavGuides/`. Each guide has YAML front matter with `name`, `topics` (keywords), and `description` fields. Scan the front matter to find relevant guides when the user asks about anything that might have stored reference material.
+
+### Handoffs
+
+Handoff documents are saved to `b0ttsagent/handoffs/<MM-DD-YYYY>/` (date-based folders).
+
+### Anti-Rationalization
+
+The following thoughts are incorrect and must be ignored:
+
+- "This is too small for a skill"
+- "I can just quickly implement this"
+- "I’ll gather context first"
+
+Correct behavior:
+
+- Always check for and use skills first

package/files/README.md

@@ -0,0 +1,245 @@
+# Setup
+
+### Docker
+
+**1. Create and start the Docker workspace:**
+
+   ```bash
+docker run -it \
+  --name project_name \
+  -v "C:\_Project_Directory:/workspace" \
+  -w /workspace \
+  -p 58741:58741 \
+  -p 2222:22 \
+  ghcr.io/anomalyco/opencode
+   ```
+
+(Flatten that to a single line using an AI chat or Docker Gordon, then run it.)
+
+**2. Enter the container:**
+
+```bash
+docker exec -it project_name sh
+```
+
+**2.1 Find your container** (if you forgot the name):
+
+```bash
+docker ps
+```
+
+### Install Dependencies
+
+**1. Node.js:**
+
+```bash
+apk add nodejs npm
+```
+
+**2. Git:**
+
+```bash
+apk add git
+```
+
+### OpenSSH (Remote Access)
+
+**1. Install OpenSSH server:**
+
+```bash
+apk add openssh-server
+```
+
+**2. Generate host keys:**
+
+```bash
+ssh-keygen -A
+```
+
+**3. Enable root login with password — append to `/etc/ssh/sshd_config`:**
+
+```bash
+echo -e "PermitRootLogin yes\nPasswordAuthentication yes" >> /etc/ssh/sshd_config
+```
+
+**4. Set root password:**
+
+```bash
+passwd root
+```
+
+**5. Start SSH server:**
+
+```bash
+/usr/sbin/sshd
+```
+
+### Auto-Start SSH on Container Restart
+
+After completing all setup above (dependencies, OpenSSH, tmux), save the container as an image so SSH auto-starts on future `docker start`:
+
+**1. Exit the container:**
+
+```bash
+exit
+```
+
+**2. Save the container as an image:**
+
+```bash
+docker commit project_name project_name-image
+```
+
+**3. Remove the old container:**
+
+```bash
+docker stop project_name && docker rm project_name
+```
+
+**4. Run a new container from the saved image:**
+
+```bash
+docker run -it \
+  --name project_name \
+  -v "C:\_Project_Directory:/workspace" \
+  -w /workspace \
+  -p 58741:58741 \
+  -p 2222:22 \
+  --entrypoint sh \
+  project_name-image \
+  -c "/usr/sbin/sshd && exec sh"
+```
+
+(Flatten that to a single line using an AI chat or Docker Gordon, then run it.)
+
+**Note:** If you install new packages later, re-run step 2 to update the image:
+
+```bash
+docker commit project_name project_name-image
+```
+
+### tmux + Termius (Persistent Sessions)
+
+**1. Install tmux:**
+
+```bash
+apk add tmux
+```
+
+**2. Create a named session:**
+
+```bash
+tmux new-session -d -s main
+```
+
+**3. Auto-attach on login — append to `~/.profile`:**
+
+```bash
+if command -v tmux &>/dev/null && [ -z "$TMUX" ]; then
+  tmux attach -t main 2>/dev/null || tmux new -s main
+fi
+```
+
+(Flatten that to a single line using an AI chat or Docker Gordon, then run it.)
+
+**4. Connect from Termius (phone):**
+
+| Field    | Value                    |
+| -------- | ------------------------ |
+| Host     | Your Windows PC local IP |
+| Port     | 2222                     |
+| User     | root                     |
+| Password | *(the one you set)*      |
+
+Run `ipconfig` on Windows to find your local IP.
+
+**5. Using tmux from phone:**
+
+- `tmux ls` — list sessions
+- `tmux attach -t main` — attach to session
+- `Ctrl+B, D` — detach (keeps session running)
+
+### GSD
+
+**1. Install GSD:**
+
+```
+npx @opengsd/gsd-core@latest
+```
+
+**2. Install GSD SDK globally**
+
+```
+npm install -g @gsd-build/sdk
+```
+
+**Note:** you can also just ask the model to do it, so you don't have to reinstall every session.
+
+**3. Configure model overrides** — paste into `.opencode/opencode.json` under `"agent"`.
+For other override strategies, see `C:\Users\Jonah\.config\opencode\Model Overrides\model-override-strategies.md`.
+
+### opencode MCPs
+
+**1. Roblox Studio MCP** (read-only inspector) — browse the live place file from AI. Add to `.opencode/opencode.json`:
+
+```json
+"mcp": {
+  "robloxstudio": {
+    "type": "local",
+    "command": ["npx", "-y", "robloxstudio-mcp-inspector@latest"],
+    "enabled": true,
+    "timeout": 30000
+  }
+}
+```
+
+**1.1 - Requirements:** Enable `HTTP Requests` in Roblox Studio (`File > Game Settings > Security`).
+
+**2. Context7 MCP** — Roblox/Luau documentation lookups. Add to `.opencode/opencode.json`:
+
+```json
+"mcp": {
+    "context7": {
+      "type": "remote",
+      "url": "https://mcp.context7.com/mcp",
+      "headers": {
+        "CONTEXT7_API_KEY": "{env:CONTEXT7_API_KEY}"
+      },
+      "enabled": true
+    }
+}
+```
+
+Then set the env var: `export CONTEXT7_API_KEY=ctx7sk-...`
+
+### Notifications
+
+Push notifications via [ntfy.sh](https://ntfy.sh) when the AI finishes, needs permission, or errors.
+
+**1.** Create a `plugins` folder inside `.opencode/` in your project.
+
+**2.** Copy `Notifications.js` from `C:\Users\Jonah\.config\opencode\Plugins\Notifications.js` into `.opencode/plugins/`.
+
+**3.** Update placeholders in `.opencode/plugins/Notifications.js`:
+
+- Replace the ntfy topic URL with your own (get one at [ntfy.sh](https://ntfy.sh)).
+- Replace `project_name` in the title strings.
+
+**4.** Subscribe — install the ntfy app ([Android](https://play.google.com/store/apps/details?id=io.heckel.ntfy) / [iOS](https://apps.apple.com/app/ntfy/id1625396347)) and subscribe to your topic.
+
+### Cleanup
+
+**Remove a specific project:**
+
+```bash
+docker stop project_name && docker rm project_name
+docker rmi project_name-image
+```
+
+**Remove all unused images and containers:**
+
+```bash
+docker system prune
+```
+
+</instructions>

package/files/opencode/opencode.json

@@ -0,0 +1,178 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "permission": {
+    "read": {
+      ".opencode/get-shit-done/*": "allow"
+    },
+    "external_directory": {
+      ".opencode/get-shit-done/*": "allow"
+    }
+  },
+  "provider": {
+    "ollama": {
+      "models": {
+        "qwen2.5:14b-instruct-q5_K_M": {
+          "_launch": true,
+          "name": "qwen2.5:14b-instruct-q5_K_M"
+        }
+      },
+      "name": "Ollama",
+      "npm": "@ai-sdk/openai-compatible",
+      "options": {
+        "baseURL": "http://127.0.0.1:11434/v1"
+      }
+    }
+  },
+  "mcp": {
+    "context7": {
+      "type": "remote",
+      "url": "https://mcp.context7.com/mcp",
+      "headers": {
+        "CONTEXT7_API_KEY": "{env:CONTEXT7_API_KEY}"
+      },
+      "enabled": true
+    }
+  },
+    "agent": {
+        "gsd-roadmapper": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-planner": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-plan-checker": {
+            "model": "opencode-go/deepseek-v4-pro",
+            "reasoning": "max"
+        },
+        "gsd-code-reviewer": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-verifier": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-debugger": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-eval-planner": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-executor": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-phase-researcher": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-project-researcher": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-code-fixer": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-nyquist-auditor": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-eval-auditor": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-integration-checker": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-security-auditor": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-pattern-mapper": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-doc-synthesizer": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-research-synthesizer": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-codebase-mapper": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-ui-researcher": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-ui-auditor": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        },
+        "gsd-doc-classifier": {
+            "model": "deepseek/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-doc-verifier": {
+            "model": "deepseek/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-assumptions-analyzer": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-advisor-researcher": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-framework-selector": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-user-profiler": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-ai-researcher": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-domain-researcher": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-doc-writer": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-ui-checker": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-debug-session-manager": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "gsd-intel-updater": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "explore": {
+            "model": "opencode-go/deepseek-v4-flash",
+            "reasoning": "high"
+        },
+        "general": {
+            "model": "xiaomi-token-plan-sgp/mimo-v2.5-pro",
+            "reasoning": "high"
+        }
+    }
+}

package/files/opencode/plugins/Notifications.js

@@ -0,0 +1,66 @@
+// ── Notifications Plugin for OpenCode ───────────────────────────────
+// Sends push notifications via ntfy.sh when the AI finishes, needs
+// permission, or encounters errors.
+//
+// SETUP:
+//   1. Get a topic at https://ntfy.sh (or self-host)
+//   2. Update NTFY_CONFIG below with your URL, topic, and auth
+//   3. Subscribe to the topic in the ntfy app (Android / iOS)
+//
+//   Replace "project_name" in the event titles with your project name.
+// ────────────────────────────────────────────────────────────────────
+
+const USE_SELF_HOSTED = false // set to true if you self-host ntfy
+
+const NTFY_CONFIG = {
+  self: {
+    baseUrl: "https://{YOUR_TAILSCALE_URL}:3000",
+    topic: "{YOUR_NTFY_TOPIC}",
+    headers: {
+      "Authorization": "Basic " + btoa("{YOUR_USER}:{YOUR_PASSWORD}"),
+    },
+  },
+  cloud: {
+    baseUrl: "https://ntfy.sh",
+    topic: "{YOUR_NTFY_TOPIC}",
+    headers: {},
+  },
+}
+
+export const NotifyPlugin = async () => {
+  const config = USE_SELF_HOSTED ? NTFY_CONFIG.self : NTFY_CONFIG.cloud
+
+  const send = async (title, body, priority = "default", tags = "robot") => {
+    try {
+      await fetch(`${config.baseUrl}/${config.topic}`, {
+        method: "POST",
+        body,
+        headers: {
+          "Title": title,
+          "Priority": priority,
+          "Tags": tags,
+          ...config.headers,
+        },
+      })
+    } catch {}
+  }
+
+  return {
+    event: async ({ event }) => {
+      switch (event.type) {
+        case "session.idle":
+          await send("OpenCode - project_name", "Response ready")
+          break
+        case "session.error":
+          await send("OpenCode - project_name", "Session errored", "high", "warning")
+          break
+        case "permission.asked":
+          await send("OpenCode - project_name", "Needs permission", "high", "lock")
+          break
+        case "question.asked":
+          await send("OpenCode - project_name", "Has a question", "high", "question")
+          break
+      }
+    },
+  }
+}

package/files/opencode/settings.json

@@ -0,0 +1 @@
+{}