Sessions logo

Sessions

CommunityPopular
alsk1992
sessions

Session management, conversation history, and checkpoints

Overview

Publisheralsk1992
RepositoryCloddsBot
Skill namesessions
Stars
3K
Forks
353
Bundled files
1
LicenseMIT
Links
  • 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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by alsk1992 on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/sessions
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/alsk1992/CloddsBot.git /tmp/CloddsBot
mkdir -p .claude/skills
cp -r /tmp/CloddsBot/src/skills/bundled/sessions .claude/skills/sessions
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sessions 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 Sessions 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 Sessions 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.

Sessions - Complete API Reference

Manage conversation sessions, history, checkpoints, and resets across channels.


Chat Commands

Session Control

/new                                        Start new conversation
/reset                                      Reset current session
/session                                    View session info
/session list                               List active sessions

Checkpoints

/checkpoint save "before refactor"          Save checkpoint
/checkpoint list                            List checkpoints
/checkpoint restore <id>                    Restore checkpoint
/checkpoint delete <id>                     Delete checkpoint

History

/history                                    View conversation history
/history export                             Export as markdown
/history clear                              Clear history (keeps session)

Settings

/session scope main                         Use main session
/session scope channel                      Per-channel sessions
/session scope peer                         Per-user sessions
/session reset-time 00:00                   Set daily reset time
/session idle-reset 30                      Reset after 30 min idle

TypeScript API Reference

Create Session Manager

typescript
import { createSessionManager } from 'clodds/sessions';

const sessions = createSessionManager({
  // Session scope
  scope: 'per-channel-peer',  // 'main' | 'per-peer' | 'per-channel-peer'

  // Auto-reset
  dailyResetHour: 0,  // Reset at midnight
  idleResetMinutes: 30,  // Reset after 30 min idle

  // Storage
  storage: 'sqlite',
  dbPath: './sessions.db',

  // Encryption
  encryptTranscripts: true,
  encryptionKey: process.env.SESSION_KEY,
});

Get or Create Session

typescript
const session = await sessions.getOrCreateSession({
  userId: 'user-123',
  channelId: 'telegram-456',
  peerId: 'peer-789',
});

console.log(`Session ID: ${session.id}`);
console.log(`Created: ${session.createdAt}`);
console.log(`Messages: ${session.messageCount}`);
console.log(`Last activity: ${session.lastActivityAt}`);

Add Message to History

typescript
// Add user message
await sessions.addMessage({
  sessionId: session.id,
  role: 'user',
  content: 'What is my portfolio value?',
});

// Add assistant message
await sessions.addMessage({
  sessionId: session.id,
  role: 'assistant',
  content: 'Your portfolio is worth $10,234.56',
  usage: {
    inputTokens: 500,
    outputTokens: 200,
  },
});

Get History

typescript
// Get conversation history
const history = await sessions.getHistory(session.id, {
  limit: 50,
  format: 'messages',  // 'messages' | 'markdown' | 'text'
});

for (const msg of history) {
  console.log(`[${msg.role}] ${msg.content}`);
}

Clear History

typescript
// Clear conversation but keep session
await sessions.clearHistory(session.id);

Reset Session

typescript
// Full reset (new session)
await sessions.reset({
  userId: 'user-123',
  channelId: 'telegram-456',
});

Checkpoints

typescript
// Save checkpoint
const checkpoint = await sessions.saveCheckpoint({
  sessionId: session.id,
  name: 'Before major change',
  description: 'Saving state before refactoring trading strategy',
});

console.log(`Checkpoint ID: ${checkpoint.id}`);
console.log(`Messages saved: ${checkpoint.messageCount}`);

// List checkpoints
const checkpoints = await sessions.listCheckpoints(session.id);

for (const cp of checkpoints) {
  console.log(`${cp.id}: ${cp.name} (${cp.messageCount} messages)`);
}

// Restore checkpoint
await sessions.restoreCheckpoint(checkpoint.id);

// Delete checkpoint
await sessions.deleteCheckpoint(checkpoint.id);

Export Session

typescript
// Export as markdown
const markdown = await sessions.export(session.id, {
  format: 'markdown',
  includeMetadata: true,
});

// Export as JSON
const json = await sessions.export(session.id, {
  format: 'json',
});

Session Cleanup

typescript
// Delete old sessions
await sessions.cleanup({
  olderThan: '30d',  // Delete sessions older than 30 days
  keepCheckpoints: true,
});

Session Scopes

ScopeDescriptionUse Case
mainSingle global sessionPersonal use
per-peerSession per userMulti-user, shared channels
per-channel-peerSession per user per channelFull isolation

Auto-Reset Behavior

TriggerBehavior
Daily resetNew session at configured hour
Idle resetNew session after inactivity
Manual resetUser runs /new or /reset

Encryption

When encryptTranscripts: true:

  • All messages encrypted with AES-256-GCM
  • Per-session encryption keys
  • Secure key derivation from master key

Context Window Management

typescript
// Get context-aware history (for LLM)
const context = await sessions.getContextHistory({
  sessionId: session.id,
  maxTokens: 100000,  // Fit in context window
  strategy: 'smart',  // 'recent' | 'smart' | 'summarize'
});

// 'smart' keeps system messages + recent + important messages
// 'summarize' compresses old messages into summaries

Best Practices

  1. Choose appropriate scope — Per-channel-peer for multi-user
  2. Use checkpoints — Before major changes or experiments
  3. Export regularly — Keep backups of important conversations
  4. Set idle reset — Prevents stale context
  5. Enable encryption — For sensitive conversations

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 Sessions AI skill do?

Session management, conversation history, and checkpoints

Why use Sessions on TypingMind?

Because you install it once and use it with any model. Sessions 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 Sessions in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/sessions. 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 Sessions?

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 Sessions?

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

Is the Sessions AI skill free?

Yes. It is published on GitHub by alsk1992 under the MIT license. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇