claude
Official page: https://claude.ai/install.sh
2.1.29
A Bash script can be started as install.sh [stable|latest|VERSION], which is done as follows,
curl -fsSL https://claude.ai/install.sh | env HOME="$CEUADMIN/claude/2.1.29" bash -s -- latest
claude --help
with screen output
Setting up Claude Code...
✔ Claude Code successfully installed!
Version: 2.1.29
Location: ~/.local/bin/claude
Next: Run claude --help to get started
⚠ Setup notes:
• Native installation exists but ~/.local/bin is not in your PATH. Run:
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc && source ~/.bashrc
$ claude --help
Usage: claude [options] [command] [prompt]
Claude Code - starts an interactive session by default, use -p/--print for
non-interactive output
Arguments:
prompt Your prompt
Options:
--add-dir <directories...> Additional directories to allow tool access to
--agent <agent> Agent for the current session. Overrides the 'agent' setting.
--agents <json> JSON object defining custom agents (e.g. '{"reviewer": {"description": "Reviews code", "prompt": "You are a code reviewer"}}')
--allow-dangerously-skip-permissions Enable bypassing all permission checks as an option, without it being enabled by default. Recommended only for sandboxes with no internet access.
--allowedTools, --allowed-tools <tools...> Comma or space-separated list of tool names to allow (e.g. "Bash(git:*) Edit")
--append-system-prompt <prompt> Append a system prompt to the default system prompt
--betas <betas...> Beta headers to include in API requests (API key users only)
--chrome Enable Claude in Chrome integration
-c, --continue Continue the most recent conversation in the current directory
--dangerously-skip-permissions Bypass all permission checks. Recommended only for sandboxes with no internet access.
-d, --debug [filter] Enable debug mode with optional category filtering (e.g., "api,hooks" or "!statsig,!file")
--debug-file <path> Write debug logs to a specific file path (implicitly enables debug mode)
--disable-slash-commands Disable all skills
--disallowedTools, --disallowed-tools <tools...> Comma or space-separated list of tool names to deny (e.g. "Bash(git:*) Edit")
--fallback-model <model> Enable automatic fallback to specified model when default model is overloaded (only works with --print)
--file <specs...> File resources to download at startup. Format: file_id:relative_path (e.g., --file file_abc:doc.txt file_def:img.png)
--fork-session When resuming, create a new session ID instead of reusing the original (use with --resume or --continue)
--from-pr [value] Resume a session linked to a PR by PR number/URL, or open interactive picker with optional search term
-h, --help Display help for command
--ide Automatically connect to IDE on startup if exactly one valid IDE is available
--include-partial-messages Include partial message chunks as they arrive (only works with --print and --output-format=stream-json)
--input-format <format> Input format (only works with --print): "text" (default), or "stream-json" (realtime streaming input) (choices: "text", "stream-json")
--json-schema <schema> JSON Schema for structured output validation. Example: {"type":"object","properties":{"name":{"type":"string"}},"required":["name"]}
--max-budget-usd <amount> Maximum dollar amount to spend on API calls (only works with --print)
--mcp-config <configs...> Load MCP servers from JSON files or strings (space-separated)
--mcp-debug [DEPRECATED. Use --debug instead] Enable MCP debug mode (shows MCP server errors)
--model <model> Model for the current session. Provide an alias for the latest model (e.g. 'sonnet' or 'opus') or a model's full name (e.g. 'claude-sonnet-4-5-20250929').
--no-chrome Disable Claude in Chrome integration
--no-session-persistence Disable session persistence - sessions will not be saved to disk and cannot be resumed (only works with --print)
--output-format <format> Output format (only works with --print): "text" (default), "json" (single result), or "stream-json" (realtime streaming) (choices: "text", "json", "stream-json")
--permission-mode <mode> Permission mode to use for the session (choices: "acceptEdits", "bypassPermissions", "default", "delegate", "dontAsk", "plan")
--plugin-dir <paths...> Load plugins from directories for this session only (repeatable)
-p, --print Print response and exit (useful for pipes). Note: The workspace trust dialog is skipped when Claude is run with the -p mode. Only use this flag in directories you trust.
--replay-user-messages Re-emit user messages from stdin back on stdout for acknowledgment (only works with --input-format=stream-json and --output-format=stream-json)
-r, --resume [value] Resume a conversation by session ID, or open interactive picker with optional search term
--session-id <uuid> Use a specific session ID for the conversation (must be a valid UUID)
--setting-sources <sources> Comma-separated list of setting sources to load (user, project, local).
--settings <file-or-json> Path to a settings JSON file or a JSON string to load additional settings from
--strict-mcp-config Only use MCP servers from --mcp-config, ignoring all other MCP configurations
--system-prompt <prompt> System prompt to use for the session
--tools <tools...> Specify the list of available tools from the built-in set. Use "" to disable all tools, "default" to use all tools, or specify tool names (e.g. "Bash,Edit,Read").
--verbose Override verbose mode setting from config
-v, --version Output the version number
Commands:
doctor Check the health of your Claude Code auto-updater
install [options] [target] Install Claude Code native build. Use [target] to specify version (stable, latest, or specific version)
mcp Configure and manage MCP servers
plugin Manage Claude Code plugins
setup-token Set up a long-lived authentication token (requires Claude subscription)
update Check for updates and install if available
Anthropic API via Ollama
This section offers a flavour of Anthropic API from Ollama/0.15.2 onwards, whose local/cloud models can be used for free. From
module load ceuadmin/ollama/0.15.2
ollama serve &
ollama list
We see
NAME ID SIZE MODIFIED
qwen3-coder:480b-cloud e30e45586389 - 3 months ago
deepseek-v3.1:671b-cloud d3749919e45f - 4 months ago
gpt-oss:20b aa4295ac10c3 13 GB 4 months ago
llava:7b 8dd30f6b0cb1 4.7 GB 8 months ago
phi4:latest ac896e5b8b34 9.1 GB 9 months ago
gemma3:latest c0494fe00251 3.3 GB 10 months ago
qwen:latest d53d04290064 2.3 GB 10 months ago
mistral:latest f974a74358d6 4.1 GB 10 months ago
vicuna:latest 370739dc897b 3.8 GB 11 months ago
so it is ready for
export ANTHROPIC_AUTH_TOKEN=ollama
export ANTHROPIC_API_KEY=
export ANTHROPIC_BASE_URL="http://localhost:11434"
claude --model gpt-oss:20b --allow-dangerously-skip-permissions
claude --model qwen3-coder:480b-cloud --allow-dangerously-skip-permissions
The first model gives,
$ claude --model gpt-oss:20b --allow-dangerously-skip-permissions
╭─── Claude Code v2.1.29 ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ │ Tips for getting started │
│ Welcome back! │ Run /init to create a CLAUDE.md file with instructions for Claude │
│ │ ───────────────────────────────────────────────────────────────── │
│ │ Recent activity │
│ ▐▛███▜▌ │ No recent activity │
│ ▝▜█████▛▘ │ │
│ ▘▘ ▝▝ │ │
│ gpt-oss:20b · API Usage Billing │ │
│ ~/Downloads │ │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
/model to try Opus 4.5
──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
❯ Try "edit <filepath> to..."
❯ write a Python program which outputs "Hello, world!"
· Reticulating…
As expected, this is very slow and we turn to the second model,
$ claude --model qwen3-coder:480b-cloud --allow-dangerously-skip-permissions
> create a kanban style app that allows the user to create/update tasks and move them between the TODO, In Progress and Completed
sections. The app should be contained in a single HTML file with CSS and javascript that I can open in my browser
● I'll create a Kanban-style task management app in a single HTML file. Let me think through the structure and implementation.
● Write(kanban-app.html)
⎿ Wrote 461 lines to kanban-app.html
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Kanban Board</title>
<style>
* {
box-sizing: border-box;
margin: 0;
… +451 lines (ctrl+o to expand)
✽ Fiddle-faddling… (9m 29s · ↓ 389 tokens)
● I've created a complete Kanban-style task management app in a single HTML file. Here's what the app includes:
Features:
1. Three Columns: To Do, In Progress, and Completed
- Add new tasks with title and description
- Edit existing tasks
- Delete tasks
- Move tasks between columns
3. Drag and Drop: Move tasks between columns by dragging
4. Persistent Storage: Tasks are saved in your browser's localStorage
5. Responsive Design: Works on both desktop and mobile devices
How to Use:
1. Add a Task:
- Fill in the task title and description
- Select the column where you want to add the task
- Click "Add Task"
2. Edit a Task:
- Click the pencil icon on any task
- Modify the details in the form
- Click "Update Task"
3. Move Tasks:
- Drag and drop tasks between columns
- Or edit a task and change its column in the form
4. Delete a Task:
- Click the trash can icon on any task
The app automatically saves your tasks, so they'll still be there when you reopen the file. You can open this HTML file directly in any
modern browser to start using your Kanban board.
✻ Cooked for 9m 29s
❯
From the working directory, one sees kanban-app.html.
Additionally, https://towardsdatascience.com/run-claude-code-for-free-with-local-and-cloud-models-from-ollama/ gives kanban.html.
On the first attempt it also gives,
Overview
Features
1. Create new tasks with titles
2. Move tasks between columns by dragging
3. Update task titles by clicking to edit
4. Delete tasks
5. Responsive design that works in any modern browser
Technical Approach
- Single HTML file containing HTML, CSS, and JavaScript
- Drag and drop functionality using HTML5 Drag and Drop API
- Local storage for persistence
- Clean, modern UI with CSS Grid/Flexbox
- Event delegation for efficient event handling
Detailed Implementation
HTML Structure
- Main container div
- Header with title and task creation form
- Three column containers (TODO, In Progress, Completed)
- Each column has:
- Column header
- Task list container
- Add task button/form
CSS Styling
- CSS variables for consistent colors
- Flexbox for main layout
- Card-style design for tasks
- Visual feedback for drag operations
- Responsive design with media queries
JavaScript Functionality
- Task data model with id, title, status
- DOM manipulation functions
- Drag and drop event handlers
- Local storage save/load functions
- Event listeners for user interactions
File Structure
- Single file: kanban.html (contains all HTML, CSS, and JavaScript)
Implementation Steps
1. Create basic HTML structure with three columns
2. Add CSS styling for layout and appearance
3. Implement JavaScript functionality:
- Task creation
- Drag and drop between columns
- Task editing
- Task deletion
- Local storage persistence
4. Add responsive design considerations
5. Test functionality in browser
Verification
1. Open file in browser
2. Create several tasks
3. Drag tasks between columns
4. Edit task titles
5. Delete tasks
6. Refresh page to verify persistence
╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
Claude has written up a plan and is ready to execute. Would you like to proceed?
❯ 1. Yes, clear context and bypass permissions
2. Yes, and bypass permissions
3. Yes, manually approve edits
4. Type here to tell Claude what to change
ctrl-g to edit in Pico · ~/.claude/plans/snoopy-coalescing-lemon.md