octocode-install
Interactive step-by-step installer for Octocode tools on macOS and Windows. Use when the user asks to "install octocode", "set up octocode", "configure octocode mcp", "get started with octocode", "install octocode-cli", "octocode setup", or needs help with GitHub auth, IDE MCP config, or skills installation.
What this skill does
# Octocode Install — Interactive Setup
`DETECT` → `CHECK INSTALLED` → `NODE` → `AUTH` → `INSTALL MCP` → `SKILLS` → `VERIFY`
**Agent rule**: Detect what you can from context. Ask only what you can't determine. One step at a time — wait for the user's answer before proceeding.
---
## Step 0 — Detect Platform & IDE
Check the conversation and environment context first:
- **Platform**: Is the OS already known? (macOS/Linux vs Windows)
- **IDE**: Is the user in Cursor, Claude Code, Claude Desktop, Windsurf, VS Code, Zed, Opencode, Trae, Kiro, Codex, Gemini CLI, Goose, Antigravity?
If either is **unknown**, ask:
> "What platform are you on, and which IDE/client are you setting up?"
> - macOS / Linux
> - Windows
>
> IDE: Cursor · Claude Code · Claude Desktop · Windsurf · Trae · Kiro · Antigravity · VS Code (Cline/Roo/Continue) · Zed · Opencode · Codex · Gemini CLI · Goose
Carry both answers through all remaining steps.
---
## Step 1 — Check if Already Installed
Read the IDE's MCP config file (see config paths table below) and check whether an `"octocode"` or `"octocode-mcp"` server entry already exists.
| IDE | Config path (macOS) | Config path (Linux) | Config path (Windows) |
|-----|---------------------|---------------------|-----------------------|
| Cursor | `~/.cursor/mcp.json` | `~/.cursor/mcp.json` | `%APPDATA%\Cursor\mcp.json` |
| Claude Code | `~/.claude.json` | `~/.claude.json` | `%USERPROFILE%\.claude.json` |
| Claude Desktop | `~/Library/Application Support/Claude/claude_desktop_config.json` | `~/.config/claude/claude_desktop_config.json` | `%APPDATA%\Claude\claude_desktop_config.json` |
| Windsurf | `~/.codeium/windsurf/mcp_config.json` | `~/.codeium/windsurf/mcp_config.json` | `%USERPROFILE%\.codeium\windsurf\mcp_config.json` |
| Trae | `~/Library/Application Support/Trae/mcp.json` | `~/.config/Trae/mcp.json` | `%APPDATA%\Trae\mcp.json` |
| Kiro | `~/.kiro/mcp.json` | `~/.kiro/mcp.json` | `%APPDATA%\Kiro\mcp.json` |
| Antigravity | `~/.gemini/antigravity/mcp_config.json` | `~/.gemini/antigravity/mcp_config.json` | `~/.gemini/antigravity/mcp_config.json` |
| VS Code (Cline) | `~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json` | `~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json` | `%APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json` |
| VS Code (Roo) | `~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/mcp_settings.json` | `~/.config/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/mcp_settings.json` | `%APPDATA%\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\mcp_settings.json` |
| VS Code (Continue) | `~/.continue/config.json` | `~/.continue/config.json` | `~/.continue/config.json` |
| Zed | `~/.config/zed/settings.json` | `~/.config/zed/settings.json` | `%APPDATA%\Zed\settings.json` |
| Opencode | `~/Library/Application Support/opencode/config.json` | `~/.config/opencode/config.json` | `%APPDATA%\opencode\config.json` |
| Codex | `~/.codex/config.toml` | `~/.codex/config.toml` | `~/.codex/config.toml` |
| Gemini CLI | `~/.gemini/settings.json` | `~/.gemini/settings.json` | `~/.gemini/settings.json` |
| Goose | `~/Library/Application Support/goose/config.yaml` | `~/.config/goose/config.yaml` | `%APPDATA%\goose\config.yaml` |
Also run:
```bash
npx octocode-cli status
```
**If octocode-mcp is already configured in the IDE AND authenticated:**
> Tell the user: "Octocode is already installed and authenticated in your IDE. You're all set!"
>
> Offer: "Would you like to **update** (`npx octocode-cli install --ide <key> --force`), **install skills**, or **change config**?"
**STOP here** — do not continue with Steps 2–6 unless the user asks to update, reinstall, or add something.
---
## Step 2 — Node.js
```bash
node --version
```
- **v18+** → continue
- **Missing or old** → tell the user to install it, then wait for confirmation:
- macOS: `brew install node` or [nodejs.org](https://nodejs.org)
- Windows: `winget install OpenJS.NodeJS` or [nodejs.org](https://nodejs.org)
> Ask: "Does `node --version` show v18 or higher now?"
---
## Step 3 — GitHub Authentication
**Ask the user:**
> "How would you like to authenticate with GitHub?"
> 1. **`npx octocode-cli login`** — Octocode OAuth (opens browser, stores token automatically)
> 2. **`gh auth login`** — GitHub CLI (if `gh` is already installed)
> 3. **GitHub PAT (token)** — paste a token manually; always works, required on Windows if browser auth fails
---
### Option 1 — Octocode OAuth (recommended)
```bash
npx octocode-cli login
```
- Opens browser → approve the device code → done
- Token stored encrypted at `~/.octocode/credentials.json`
- Automatically used by `octocode-mcp` — no env var needed
> **Windows**: If the browser doesn't open or the command hangs, switch to Option 3 (PAT).
---
### Option 2 — GitHub CLI
Requires `gh` already installed ([cli.github.com](https://cli.github.com)):
```bash
gh auth login
```
- Follow the interactive prompts
- `octocode-mcp` reads the token via `gh auth token` automatically
---
### Option 3 — GitHub PAT (always works, required on Windows if OAuth fails)
1. Create token at [github.com/settings/tokens/new](https://github.com/settings/tokens/new)
- Scopes: `repo` + `read:org`
2. Copy the token — you'll paste it as `GITHUB_TOKEN` in the MCP config (Step 4)
---
**After auth, verify:**
```bash
npx octocode-cli status
```
Expected: `✓ Authenticated as <username>`
If not authenticated — repeat the chosen option or switch to Option 3.
---
## Step 4 — Install MCP for IDE
**If IDE is unknown, ask:**
> "Which IDE/client do you want to install octocode-mcp into?"
Run:
```bash
npx octocode-cli install --ide <key>
```
| IDE | `<key>` | Aliases |
|-----|---------|---------|
| Cursor | `cursor` | |
| Claude Code | `claude-code` | `claudecode` |
| Claude Desktop | `claude-desktop` | `claude`, `claudedesktop` |
| Windsurf | `windsurf` | |
| Trae | `trae` | |
| Kiro | `kiro` | |
| Antigravity | `antigravity` | |
| VS Code (Cline) | `vscode-cline` | `cline` |
| VS Code (Roo) | `vscode-roo` | `roo`, `roo-cline` |
| VS Code (Continue) | `vscode-continue` | `continue` |
| Zed | `zed` | |
| Opencode | `opencode` | |
| Codex | `codex` | |
| Gemini CLI | `gemini-cli` | `gemini`, `geminicli` |
| Goose | `goose` | |
The CLI writes the config file automatically. Then confirm the result:
### What the config looks like
```json
{
"mcpServers": {
"octocode": {
"command": "npx",
"args": ["octocode-mcp@latest"]
}
}
}
```
### Ask — enable local tools
> "Do you want to enable **local codebase tools** (search files, LSP, browse dirs)? **Recommended — Yes.**"
> → Yes: add `"ENABLE_LOCAL": "true"` to `"env"`
> "Did you use a PAT (Option 3) for auth, or is `npx octocode-cli status` not showing authenticated?"
> → Yes: add `"GITHUB_TOKEN": "ghp_xxx"` to `"env"`
### Full config with all options:
```json
{
"mcpServers": {
"octocode": {
"command": "npx",
"args": ["octocode-mcp@latest"],
"env": {
"GITHUB_TOKEN": "ghp_xxxx",
"ENABLE_LOCAL": "true"
}
}
}
}
```
> **Token resolution order** (octocode-mcp picks the first found):
> `OCTOCODE_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` → `~/.octocode/credentials.json` → `gh auth token`
> If you used OAuth or `gh auth login`, you can omit `GITHUB_TOKEN`.
**Restart the IDE after saving the config.**
---
## Step 5 — Install Octocode Skills
**Ask the user:**
> "Would you like to install all Octocode skills? These add research, planning, code review, documentation, and more to your AI assistant."
- **No** → skip to Step 6
- **Yes** → ask which targets:
> "Which AI clients should skills be installed into?"
> - **Current IDE only** (detected in Step 0)
> - **All supported platforms** (cursor, claude-code, claude-desktop, codex, opencodRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.