session-cleanup — session-cleanup install session-cleanup, session-harbor, community, session-cleanup install, ide skills, automated session archiving, low-signal session management, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Dialogue Agents requiring efficient conversation history management and session optimization. session-cleanup is a skill that automates the archiving of old, low-signal sessions based on user-message count and age, while preserving sessions with meaningful content or metadata.

Features

Runs cleanup script in dry-run mode to review low-signal session candidates
Archives sessions with `--apply` command based on user-defined cutoff and threshold
Treats sessions as low-signal if all heuristics are met, including user-message count and age
Preserves sessions with meaningful content or metadata
Allows for customizable cutoff dates and user-message thresholds

# Core Topics

innoisotechnology innoisotechnology
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The session-cleanup skill by innoisotechnology is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for session-cleanup install, automated session archiving, low-signal session management.

Ideal Agent Persona

Ideal for Dialogue Agents requiring efficient conversation history management and session optimization.

Core Value

Empowers agents to identify and archive low-signal sessions based on user-message count and age, utilizing heuristics and metadata to preserve meaningful content, and supporting dry-run mode for review and explicit archiving with the --apply flag.

Capabilities Granted for session-cleanup

Automating session cleanup based on customizable thresholds
Archiving low-activity conversations with minimal metadata
Preserving sessions with significant user engagement or relevant content

! Prerequisites & Limits

  • Requires configuration of cutoff dates or days ago thresholds
  • Dependent on accurate user-message count and session metadata
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

session-cleanup

Install session-cleanup, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Session Cleanup

Overview

Use this skill to identify and archive old, low-signal sessions based on user-message count and age, while keeping any session with meaningful content or metadata.

Workflow

  1. Decide the cutoff (days ago or explicit date) and user-message threshold.
  2. Run the cleanup script in dry-run mode to review candidates.
  3. Re-run with --apply to archive sessions that are still low-signal.

Heuristics

Treat a session as low-signal if ALL are true:

  • user_message_count <= max_user_messages (after removing boilerplate)
  • Session is older than the cutoff date
  • No name, tags, or notes
  • No meaningful user/assistant text (beyond boilerplate)

Boilerplate includes: AGENTS.md instructions, environment context blocks, empty strings, and single "." messages.

Quick Start

Dry-run for sessions older than 1 day with at most 1 user message:

bash
1python3 /Users/innoiso/.codex/skills/session-cleanup/scripts/cleanup_sessions.py --min-age-days 1 --max-user-messages 1

Apply archiving with the same filters:

bash
1python3 /Users/innoiso/.codex/skills/session-cleanup/scripts/cleanup_sessions.py --min-age-days 1 --max-user-messages 1 --apply

Target an explicit cutoff date (UTC):

bash
1python3 /Users/innoiso/.codex/skills/session-cleanup/scripts/cleanup_sessions.py --cutoff-date 2026-01-24 --max-user-messages 2

Output

The script prints:

  • total candidates
  • kept vs archived
  • sample IDs for review (in dry-run)

Resources

scripts/

  • cleanup_sessions.py: paginate sessions, count user messages, detect boilerplate, and archive eligible sessions.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is session-cleanup?

Ideal for Dialogue Agents requiring efficient conversation history management and session optimization. session-cleanup is a skill that automates the archiving of old, low-signal sessions based on user-message count and age, while preserving sessions with meaningful content or metadata.

How do I install session-cleanup?

Run the command: npx killer-skills add innoisotechnology/session-harbor/session-cleanup. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for session-cleanup?

Key use cases include: Automating session cleanup based on customizable thresholds, Archiving low-activity conversations with minimal metadata, Preserving sessions with significant user engagement or relevant content.

Which IDEs are compatible with session-cleanup?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for session-cleanup?

Requires configuration of cutoff dates or days ago thresholds. Dependent on accurate user-message count and session metadata.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add innoisotechnology/session-harbor/session-cleanup. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use session-cleanup immediately in the current project.

Related Skills

Looking for an alternative to session-cleanup or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI