clanker-agent/packages/coding-agent
Harivansh Rathi 67168d8289 chore: rebrand companion-os to clanker-agent
- Rename all package names from companion-* to clanker-*
- Update npm scopes from @mariozechner to @harivansh-afk
- Rename config directories .companion -> .clanker
- Rename environment variables COMPANION_* -> CLANKER_*
- Update all documentation, README files, and install scripts
- Rename package directories (companion-channels, companion-grind, companion-teams)
- Update GitHub URLs to harivansh-afk/clanker-agent
- Preserve full git history from companion-cloud monorepo
2026-03-26 16:22:52 -04:00
..
clanker-out chore: rebrand companion-os to clanker-agent 2026-03-26 16:22:52 -04:00
docs chore: rebrand companion-os to clanker-agent 2026-03-26 16:22:52 -04:00
scripts chore: rebrand companion-os to clanker-agent 2026-03-26 16:22:52 -04:00
src chore: rebrand companion-os to clanker-agent 2026-03-26 16:22:52 -04:00
test chore: rebrand companion-os to clanker-agent 2026-03-26 16:22:52 -04:00
.gitignore move pi-mono into companion-cloud as apps/companion-os 2026-03-07 09:22:50 -08:00
CHANGELOG.md refactor: finish companion rename migration 2026-03-10 07:39:32 -05:00
package.json chore: rebrand companion-os to clanker-agent 2026-03-26 16:22:52 -04:00
README.md chore: rebrand companion-os to clanker-agent 2026-03-26 16:22:52 -04:00
tsconfig.build.json move pi-mono into companion-cloud as apps/companion-os 2026-03-07 09:22:50 -08:00
tsconfig.examples.json chore: rebrand companion-os to clanker-agent 2026-03-26 16:22:52 -04:00
vitest.config.ts move pi-mono into companion-cloud as apps/companion-os 2026-03-07 09:22:50 -08:00

clanker logo

Discord npm Build status

clanker.dev domain graciously donated by

Exy mascot
exe.dev

Clanker is a minimal terminal coding harness. Adapt clanker to your workflows, not the other way around, without having to fork and modify clanker internals. Extend it with TypeScript Extensions, Skills, Prompt Templates, and Themes. Put your extensions, skills, prompt templates, and themes in Clanker Packages and share them with others via npm or git.

Clanker ships with powerful defaults but skips features like sub agents and plan mode. Instead, you can ask clanker to build what you want or install a third party clanker package that matches your workflow.

Clanker runs in four modes: interactive, print or JSON, RPC for process integration, and an SDK for embedding in your own apps. See openclaw/openclaw for a real-world SDK integration.

Table of Contents


Quick Start

npm install -g @mariozechner/clanker-coding-agent

Authenticate with an API key:

export ANTHROPIC_API_KEY=sk-ant-...
clanker

Or use your existing subscription:

clanker
/login  # Then select provider

Then just talk to clanker. By default, clanker gives the model four tools: read, write, edit, and bash. The model uses these to fulfill your requests. Add capabilities via skills, prompt templates, extensions, or clanker packages.

Platform notes: Windows | Termux (Android) | Terminal setup | Shell aliases


Providers & Models

For each built-in provider, clanker maintains a list of tool-capable models, updated with every release. Authenticate via subscription (/login) or API key, then select any model from that provider via /model (or Ctrl+L).

Subscriptions:

  • Anthropic Claude Pro/Max
  • OpenAI ChatGPT Plus/Pro (Codex)
  • GitHub Copilot
  • Google Gemini CLI
  • Google Antigravity

API keys:

  • Anthropic
  • OpenAI
  • Azure OpenAI
  • Google Gemini
  • Google Vertex
  • Amazon Bedrock
  • Mistral
  • Groq
  • Cerebras
  • xAI
  • OpenRouter
  • Vercel AI Gateway
  • ZAI
  • OpenCode Zen
  • OpenCode Go
  • Hugging Face
  • Kimi For Coding
  • MiniMax

See docs/providers.md for detailed setup instructions.

Custom providers & models: Add providers via ~/.clanker/agent/models.json if they speak a supported API (OpenAI, Anthropic, Google). For custom APIs or OAuth, use extensions. See docs/models.md and docs/custom-provider.md.


Interactive Mode

Interactive Mode

The interface from top to bottom:

  • Startup header - Shows shortcuts (/hotkeys for all), loaded AGENTS.md files, prompt templates, skills, and extensions
  • Messages - Your messages, assistant responses, tool calls and results, notifications, errors, and extension UI
  • Editor - Where you type; border color indicates thinking level
  • Footer - Working directory, session name, total token/cache usage, cost, context usage, current model

The editor can be temporarily replaced by other UI, like built-in /settings or custom UI from extensions (e.g., a Q&A tool that lets the user answer model questions in a structured format). Extensions can also replace the editor, add widgets above/below it, a status line, custom footer, or overlays.

Editor

Feature How
File reference Type @ to fuzzy-search project files
Path completion Tab to complete paths
Multi-line Shift+Enter (or Ctrl+Enter on Windows Terminal)
Images Ctrl+V to paste (Alt+V on Windows), or drag onto terminal
Bash commands !command runs and sends output to LLM, !!command runs without sending

Standard editing keybindings for delete word, undo, etc. See docs/keybindings.md.

Commands

Type / in the editor to trigger commands. Extensions can register custom commands, skills are available as /skill:name, and prompt templates expand via /templatename.

Command Description
/login, /logout OAuth authentication
/model Switch models
/scoped-models Enable/disable models for Ctrl+P cycling
/settings Thinking level, theme, message delivery, transport
/resume Pick from previous sessions
/new Start a new session
/name <name> Set session display name
/session Show session info (path, tokens, cost)
/tree Jump to any point in the session and continue from there
/fork Create a new session from the current branch
/compact [prompt] Manually compact context, optional custom instructions
/copy Copy last assistant message to clipboard
/export [file] Export session to HTML file
/share Upload as private GitHub gist with shareable HTML link
/reload Reload extensions, skills, prompts, context files (themes hot-reload automatically)
/hotkeys Show all keyboard shortcuts
/changelog Display version history
/quit, /exit Quit clanker

Keyboard Shortcuts

See /hotkeys for the full list. Customize via ~/.clanker/agent/keybindings.json. See docs/keybindings.md.

Commonly used:

Key Action
Ctrl+C Clear editor
Ctrl+C twice Quit
Escape Cancel/abort
Escape twice Open /tree
Ctrl+L Open model selector
Ctrl+P / Shift+Ctrl+P Cycle scoped models forward/backward
Shift+Tab Cycle thinking level
Ctrl+O Collapse/expand tool output
Ctrl+T Collapse/expand thinking blocks

Message Queue

Submit messages while the agent is working:

  • Enter queues a steering message, delivered after current tool execution (interrupts remaining tools)
  • Alt+Enter queues a follow-up message, delivered only after the agent finishes all work
  • Escape aborts and restores queued messages to editor
  • Alt+Up retrieves queued messages back to editor

Configure delivery in settings: steeringMode and followUpMode can be "one-at-a-time" (default, waits for response) or "all" (delivers all queued at once). transport selects provider transport preference ("sse", "websocket", or "auto") for providers that support multiple transports.


Sessions

Sessions are stored as JSONL files with a tree structure. Each entry has an id and parentId, enabling in-place branching without creating new files. See docs/session.md for file format.

Management

Sessions auto-save to ~/.clanker/agent/sessions/ organized by working directory.

clanker -c                  # Continue most recent session
clanker -r                  # Browse and select from past sessions
clanker --no-session        # Ephemeral mode (don't save)
clanker --session <path>    # Use specific session file or ID

Branching

/tree - Navigate the session tree in-place. Select any previous point, continue from there, and switch between branches. All history preserved in a single file.

Tree View

  • Search by typing, page with ←/→
  • Filter modes (Ctrl+O): default → no-tools → user-only → labeled-only → all
  • Press l to label entries as bookmarks

/fork - Create a new session file from the current branch. Opens a selector, copies history up to the selected point, and places that message in the editor for modification.

Compaction

Long sessions can exhaust context windows. Compaction summarizes older messages while keeping recent ones.

Manual: /compact or /compact <custom instructions>

Automatic: Enabled by default. Triggers on context overflow (recovers and retries) or when approaching the limit (proactive). Configure via /settings or settings.json.

Compaction is lossy. The full history remains in the JSONL file; use /tree to revisit. Customize compaction behavior via extensions. See docs/compaction.md for internals.


Settings

Use /settings to modify common options, or edit JSON files directly:

Location Scope
~/.clanker/agent/settings.json Global (all projects)
.clanker/settings.json Project (overrides global)

See docs/settings.md for all options.


Context Files

Clanker loads AGENTS.md (or CLAUDE.md) at startup from:

  • ~/.clanker/agent/AGENTS.md (global)
  • Parent directories (walking up from cwd)
  • Current directory

Use for project instructions, conventions, common commands. All matching files are concatenated.

System Prompt

Replace the default system prompt with .clanker/SYSTEM.md (project) or ~/.clanker/agent/SYSTEM.md (global). Append without replacing via APPEND_SYSTEM.md.


Customization

Prompt Templates

Reusable prompts as Markdown files. Type /name to expand.

<!-- ~/.clanker/agent/prompts/review.md -->

Review this code for bugs, security issues, and performance problems.
Focus on: {{focus}}

Place in ~/.clanker/agent/prompts/, .clanker/prompts/, or a clanker package to share with others. See docs/prompt-templates.md.

Skills

On-demand capability packages following the Agent Skills standard. Invoke via /skill:name or let the agent load them automatically.

<!-- ~/.clanker/agent/skills/my-skill/SKILL.md -->

# My Skill

Use this skill when the user asks about X.

## Steps

1. Do this
2. Then that

Place in ~/.clanker/agent/skills/, ~/.agents/skills/, .clanker/skills/, or .agents/skills/ (from cwd up through parent directories) or a clanker package to share with others. See docs/skills.md.

Extensions

Doom Extension

TypeScript modules that extend clanker with custom tools, commands, keyboard shortcuts, event handlers, and UI components.

export default function (clanker: ExtensionAPI) {
  clanker.registerTool({ name: "deploy", ... });
  clanker.registerCommand("stats", { ... });
  clanker.on("tool_call", async (event, ctx) => { ... });
}

What's possible:

  • Custom tools (or replace built-in tools entirely)
  • Sub-agents and plan mode
  • Custom compaction and summarization
  • Permission gates and path protection
  • Custom editors and UI components
  • Status lines, headers, footers
  • Git checkpointing and auto-commit
  • SSH and sandbox execution
  • MCP server integration
  • Make clanker look like Claude Code
  • Games while waiting (yes, Doom runs)
  • ...anything you can dream up

Place in ~/.clanker/agent/extensions/, .clanker/extensions/, or a clanker package to share with others. See docs/extensions.md.

Themes

Built-in: dark, light. Themes hot-reload: modify the active theme file and clanker immediately applies changes.

Place in ~/.clanker/agent/themes/, .clanker/themes/, or a clanker package to share with others. See docs/themes.md.

Clanker Packages

Bundle and share extensions, skills, prompts, and themes via npm or git. Find packages on npmjs.com or Discord.

Security: Clanker packages run with full system access. Extensions execute arbitrary code, and skills can instruct the model to perform any action including running executables. Review source code before installing third-party packages.

clanker install npm:@foo/clanker-tools
clanker install npm:@foo/clanker-tools@1.2.3      # pinned version
clanker install git:github.com/user/repo
clanker install git:github.com/user/repo@v1  # tag or commit
clanker install git:git@github.com:user/repo
clanker install git:git@github.com:user/repo@v1  # tag or commit
clanker install https://github.com/user/repo
clanker install https://github.com/user/repo@v1      # tag or commit
clanker install ssh://git@github.com/user/repo
clanker install ssh://git@github.com/user/repo@v1    # tag or commit
clanker remove npm:@foo/clanker-tools
clanker list
clanker update                               # skips pinned packages
clanker config                               # enable/disable extensions, skills, prompts, themes

Packages install to ~/.clanker/agent/git/ (git) or global npm. Use -l for project-local installs (.clanker/git/, .clanker/npm/).

Create a package by adding a clanker key to package.json:

{
  "name": "my-clanker-package",
  "keywords": ["clanker-package"],
  "clanker": {
    "extensions": ["./extensions"],
    "skills": ["./skills"],
    "prompts": ["./prompts"],
    "themes": ["./themes"]
  }
}

Without a clanker manifest, clanker auto-discovers from conventional directories (extensions/, skills/, prompts/, themes/).

See docs/packages.md.


Programmatic Usage

SDK

import {
  AuthStorage,
  createAgentSession,
  ModelRegistry,
  SessionManager,
} from "@mariozechner/clanker-coding-agent";

const { session } = await createAgentSession({
  sessionManager: SessionManager.inMemory(),
  authStorage: AuthStorage.create(),
  modelRegistry: new ModelRegistry(authStorage),
});

await session.prompt("What files are in the current directory?");

See docs/sdk.md.

RPC Mode

For non-Node.js integrations, use RPC mode over stdin/stdout:

clanker --mode rpc

See docs/rpc.md for the protocol.


Philosophy

Clanker is aggressively extensible so it doesn't have to dictate your workflow. Features that other tools bake in can be built with extensions, skills, or installed from third-party clanker packages. This keeps the core minimal while letting you shape clanker to fit how you work.

No MCP. Build CLI tools with READMEs (see Skills), or build an extension that adds MCP support. Why?

No sub-agents. There's many ways to do this. Spawn clanker instances via tmux, or build your own with extensions, or install a package that does it your way.

No permission popups. Run in a container, or build your own confirmation flow with extensions inline with your environment and security requirements.

No plan mode. Write plans to files, or build it with extensions, or install a package.

No built-in to-dos. They confuse models. Use a TODO.md file, or build your own with extensions.

No background bash. Use tmux. Full observability, direct interaction.

Read the blog post for the full rationale.


CLI Reference

clanker [options] [@files...] [messages...]

Package Commands

clanker install <source> [-l]    # Install package, -l for project-local
clanker remove <source> [-l]     # Remove package
clanker update [source]          # Update packages (skips pinned)
clanker list                     # List installed packages
clanker config                   # Enable/disable package resources

Modes

Flag Description
(default) Interactive mode
-p, --print Print response and exit
daemon Start a long-lived, non-interactive daemon that keeps extensions running
--mode json Output all events as JSON lines (see docs/json.md)
--mode rpc RPC mode for process integration (see docs/rpc.md)
--export <in> [out] Export session to HTML

Model Options

Option Description
--provider <name> Provider (anthropic, openai, google, etc.)
--model <pattern> Model pattern or ID (supports provider/id and optional :<thinking>)
--api-key <key> API key (overrides env vars)
--thinking <level> off, minimal, low, medium, high, xhigh
--models <patterns> Comma-separated patterns for Ctrl+P cycling
--list-models [search] List available models

Session Options

Option Description
-c, --continue Continue most recent session
-r, --resume Browse and select session
--session <path> Use specific session file or partial UUID
--session-dir <dir> Custom session storage directory
--no-session Ephemeral mode (don't save)

Tool Options

Option Description
--tools <list> Enable specific built-in tools (default: read,bash,edit,write)
--no-tools Disable all built-in tools (extension tools still work)

Available built-in tools: read, bash, edit, write, grep, find, ls

Resource Options

Option Description
-e, --extension <source> Load extension from path, npm, or git (repeatable)
--no-extensions Disable extension discovery
--skill <path> Load skill (repeatable)
--no-skills Disable skill discovery
--prompt-template <path> Load prompt template (repeatable)
--no-prompt-templates Disable prompt template discovery
--theme <path> Load theme (repeatable)
--no-themes Disable theme discovery

Combine --no-* with explicit flags to load exactly what you need, ignoring settings.json (e.g., --no-extensions -e ./my-ext.ts).

Other Options

Option Description
--system-prompt <text> Replace default prompt (context files and skills still appended)
--append-system-prompt <text> Append to system prompt
--verbose Force verbose startup
-h, --help Show help
-v, --version Show version

File Arguments

Prefix files with @ to include in the message:

clanker @prompt.md "Answer this"
clanker -p @screenshot.png "What's in this image?"
clanker @code.ts @test.ts "Review these files"

Examples

# Interactive with initial prompt
clanker "List all .ts files in src/"

# Non-interactive
clanker -p "Summarize this codebase"

# Different model
clanker --provider openai --model gpt-4o "Help me refactor"

# Model with provider prefix (no --provider needed)
clanker --model openai/gpt-4o "Help me refactor"

# Model with thinking level shorthand
clanker --model sonnet:high "Solve this complex problem"

# Limit model cycling
clanker --models "claude-*,gpt-4o"

# Read-only mode
clanker --tools read,grep,find,ls -p "Review the code"

# High thinking level
clanker --thinking high "Solve this complex problem"

Environment Variables

Variable Description
CLANKER_CODING_AGENT_DIR Override config directory (default: ~/.clanker/agent)
CLANKER_PACKAGE_DIR Override package directory (useful for Nix/Guix where store paths tokenize poorly)
CLANKER_SKIP_VERSION_CHECK Skip version check at startup
CLANKER_CACHE_RETENTION Set to long for extended prompt cache (Anthropic: 1h, OpenAI: 24h)
VISUAL, EDITOR External editor for Ctrl+G

Contributing & Development

See CONTRIBUTING.md for guidelines and docs/development.md for setup, forking, and debugging.


License

MIT

See Also