Caam

Community

Dicklesworthstone

caam

Manage AI coding CLI accounts with sub-100ms switching. Use when hitting rate limits on Claude Max, GPT Pro, or Gemini Ultra subscriptions and need instant account swapping without browser OAuth.

Overview

Publisher	Dicklesworthstone
Repository	`agent_flywheel_clawdbot_skills_and_integrations`
Skill name	`caam`
Stars	73
Forks	16
Bundled files	3
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Dicklesworthstone on GitHub. Read the source before you install it.

Installation

Install the Caam AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/tree/main/skills/caam
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/tree/main/skills/caam

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations.git /tmp/agent_flywheel_clawdbot_skills_and_integrations
mkdir -p .claude/skills
cp -r /tmp/agent_flywheel_clawdbot_skills_and_integrations/skills/caam .claude/skills/caam

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Caam in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Caam on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Caam is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

CAAM — Coding Agent Account Manager

Core Problem: You hit rate limits on your $200/mo Claude Max subscription. Browser OAuth takes 30-60 seconds. CAAM swaps accounts in ~50ms.

Quick Start

bash
# Install
curl -fsSL "https://raw.githubusercontent.com/Dicklesworthstone/coding_agent_account_manager/main/install.sh?$(date +%s)" | bash

# Backup current account
caam backup claude alice@gmail.com

# Clear, login with another account, backup that too
caam clear claude
claude  # /login with bob@gmail.com
caam backup claude bob@gmail.com

# Switch instantly forever
caam activate claude alice@gmail.com   # ~50ms
caam activate claude bob@gmail.com     # ~50ms

THE EXACT PROMPT — Daily Commands

Check Status

bash
caam status

Shows active profile for each tool based on content hash matching.

Instant Switch

bash
caam activate claude bob@gmail.com

Restores auth files from vault. ~50ms, no browser.

Smart Auto-Switch

bash
caam activate claude --auto

Rotation algorithm picks best profile based on health, recency, cooldowns.

Mark Rate Limited

bash
caam cooldown set claude

Marks current profile for 60min. Rotation skips it.

Zero-Friction Aliases

bash
# Add to .bashrc/.zshrc
alias claude='caam run claude --'
alias codex='caam run codex --'
alias gemini='caam run gemini --'

# Now these auto-failover on rate limits
claude "explain this code"

How It Works

Each AI CLI stores OAuth tokens in plain files. CAAM backs them up and restores them:


~/.claude.json ←→ ~/.local/share/caam/vault/claude/alice@gmail.com/
~/.codex/auth.json ←→ ~/.local/share/caam/vault/codex/work@company.com/

That's it. No daemons, no databases, no network calls. Just cp with extra steps.

Supported Tools

Tool	Subscription	Auth Files
Claude Code	Claude Max ($200/mo)	`~/.claude.json`, `~/.config/claude-code/auth.json`
Codex CLI	GPT Pro ($200/mo)	`~/.codex/auth.json`
Gemini CLI	Gemini Ultra (~$275/mo)	`~/.gemini/settings.json`, `~/.gemini/oauth_credentials.json`

Smart Rotation

When you have multiple accounts, rotation picks the best one:

bash
# Preview what rotation would select
caam next claude

# Let it pick automatically
caam activate claude --auto

Health Indicators

Icon	Status	Meaning
🟢	Healthy	Token valid >1hr, no recent errors
🟡	Warning	Token expiring <1hr, minor issues
🔴	Critical	Token expired, repeated errors
⚪	Unknown	No health data yet

Rotation Algorithms

Algorithm	Description
`smart` (default)	Cooldown + health + recency + jitter
`round_robin`	Sequential, skipping cooldowns
`random`	Random among non-cooldown

Cooldown Tracking

bash
# Mark current profile (60min default)
caam cooldown set claude

# Specify profile and duration
caam cooldown set claude/work@company.com --minutes 120

# View active cooldowns
caam cooldown list

# Clear early
caam cooldown clear claude/work@company.com

TUI Dashboard

bash
caam tui

Keybindings

Key	Action
`↑/↓`	Navigate profiles
`Enter`	Activate selected
`p`	Set project association
`c`	Mark/clear cooldown
`r`	Refresh
`q`	Quit

Project Associations

Link profiles to directories:

bash
cd ~/projects/work-app
caam project set claude work@company.com

# Now in this directory:
caam activate claude  # Auto-uses work@company.com

Command Reference

Command	Description
`caam backup <tool> <email>`	Save current auth to vault
`caam activate <tool> <email>`	Restore auth from vault
`caam activate <tool> --auto`	Auto-select best profile
`caam status [tool]`	Show active profiles
`caam ls [tool]`	List saved profiles
`caam clear <tool>`	Remove auth files (logout)
`caam run <tool> [-- args]`	Wrap with auto-failover
`caam cooldown set <profile>`	Mark as rate limited
`caam cooldown list`	Show active cooldowns
`caam next <tool>`	Preview rotation selection
`caam tui`	Interactive dashboard

Flywheel Integration

Tool	Integration
NTM	Each tmux pane uses different account via isolated profiles
Agent Mail	Agents coordinate account switching across sessions
CASS	Search sessions by account for usage patterns

References

Topic	Reference
Complete commands	COMMANDS.md
Isolated profiles	ISOLATED-PROFILES.md
Vault structure	VAULT.md

Validation

bash
# Verify installation
caam --version

# Check all profiles
caam status

# Test switch
caam activate claude --auto && caam status

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Caam AI skill do?

Manage AI coding CLI accounts with sub-100ms switching. Use when hitting rate limits on Claude Max, GPT Pro, or Gemini Ultra subscriptions and need instant account swapping without browser OAuth.

Why use Caam on TypingMind?

Because you install it once and use it with any model. Caam is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Caam in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/tree/main/skills/caam. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Caam?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Caam?

As many as you like. As long as a model supports skills, you can use Caam with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Caam AI skill free?

It is published on GitHub by Dicklesworthstone. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Prototype Openclaw Tui

openclaw

OrganizationPopular

Build throwaway, fixture-driven OpenClaw Clack or Pi TUI prototypes and compare multiple interactive variants side by side in tmux without running the full application or touching live state.

Slacrawl

Slack archive: search, sync freshness, threads/DMs, SQL counts, and Slacrawl repo work.

Obsidian Vault Maintainer

openclaw

OrganizationPopular

Maintain an Obsidian-friendly memory wiki vault with wikilinks, frontmatter, and official Obsidian CLI awareness.

Control Ui

Operate and troubleshoot the OpenClaw Control UI: navigate connected clients, organize sessions, build session dashboards, and handle direct or Tailscale-hosted Gateways.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

CAAM — Coding Agent Account Manager

Quick Start

THE EXACT PROMPT — Daily Commands

Check Status

Instant Switch

Smart Auto-Switch

Mark Rate Limited

Zero-Friction Aliases

How It Works

Supported Tools

Smart Rotation

Health Indicators

Rotation Algorithms

Cooldown Tracking

TUI Dashboard

Keybindings

Project Associations

Command Reference

Flywheel Integration

References

Validation

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now