Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Persistent Cross Session Task Tracker

BSecurity

Manage tasks and projects across sessions with persistent tracking.

19 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgobashapidatabasesecuritydocumentation

Works with

api

Security Analysis

B75/100
criticalModifies startup scripts or system services for persistence

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill persistent-cross-session-task-tracker --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Persistent Cross Session Task Tracker?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Persistent Cross Session Task Tracker
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-persistent-cross-session-task-tracker/badge)](https://www.skillsdirectory.com/skills/rondoflow-persistent-cross-session-task-tracker)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: persistent-cross-session-task-tracker
description: "Manage tasks and projects across sessions with persistent tracking."
category: "Productivity"
author: community
version: "1.0.1"
icon: check-square
---

# Task Runner

Manage tasks and projects across sessions with persistent tracking.

## Quick Start

### Add a task
```bash
task_runner.py add "<description>" [project] [priority]
```

### List all tasks
```bash
task_runner.py list
```

### List tasks for a specific project
```bash
task_runner.py list "<project>"
```

### Complete a task
```bash
task_runner.py complete <task_id>
```

### Change task priority
```bash
task_runner.py priority <task_id> <low|medium|high>
```

### Export project to markdown
```bash
task_runner.py export "<project>" "<output_file>"
```

## Features

- **Persistent storage** - Tasks survive session restarts (stored in `~/.openclaw/workspace/tasks_db.json`)
- **Project organization** - Group tasks by project for better organization
- **Priority levels** - low, medium (default), high
- **Status tracking** - pending vs completed with timestamps
- **Flexible filtering** - View all tasks or filter by project
- **Markdown export** - Export projects to clean markdown for sharing

## Security

### Path Validation (v1.0.1+)
The `export` function validates output paths to prevent malicious writes:
- ✅ Allowed: `~/.openclaw/workspace/`, `/tmp/`, and home directory
- ❌ Blocked: System paths (`/etc/`, `/usr/`, `/var/`, etc.)
- ❌ Blocked: Sensitive dotfiles (`~/.bashrc`, `~/.ssh`, etc.)

This prevents prompt injection attacks that could attempt to write to system files for privilege escalation.

### Task Storage
The task storage is JSON-based and only writes to `~/.openclaw/workspace/tasks_db.json`.

## Usage Patterns

### For multi-session projects
```bash
# Add experiment tasks
task_runner.py add "Setup development environment" "project-x" "high"
task_runner.py add "Write initial tests" "project-x" "medium"
task_runner.py add "Document API endpoints" "project-x" "low"

# List project progress
task_runner.py list "project-x"

# Complete tasks as you go
task_runner.py complete 1
task_runner.py complete 2
```

### For autonomous agent workflows
Track your own tasks across sessions:
```bash
# Plan experiments
task_runner.py add "Build and publish skill" "income-experiments" "high"
task_runner.py add "Test content pipeline" "income-experiments" "medium"

# Update priorities based on learning
task_runner.py priority 2 "high"

# Export progress reports
task_runner.py export "income-experiments" "./progress-report.md"
```

### For sprint planning
```bash
# Plan week's work
task_runner.py.py add "Build feature X" "sprint-5" "high"
task_runner.py.py add "Fix bug Y" "sprint-5" "high"
task_runner.py.py add "Update documentation" "sprint-5" "medium"

# Review progress
task_runner.py list "sprint-5"

# Export for standup
task_runner.py export "sprint-5" "./standup.md"
```

## Task Priorities

| Priority | Emoji | When to Use |
|----------|-------|-------------|
| high | 🔴 | Blocking issues, urgent, must do now |
| medium | 🟡 | Normal work, do soon | 
| low | 🟢 | Nice to have, backlog items |

## Output Format

Task listing shows:
- Status icon (✅ completed, ⏳ pending)
- Project name
- Task ID number
- Priority emoji
- Creation date
- Task description
- Completion date (if completed)

## Export Format

Markdown export includes:
- Project title with task counts
- Pending tasks section
- Completed tasks section (most recent first)
- Task IDs, priorities, and timestamps

## Examples

### Managing a coding project
```bash
# Setup
task_runner.py add "Clone repository" "my-project" "high"
task_runner.py add "Install dependencies" "my-project" "high"
task_runner.py add "Set up database" "my-project" "medium"

# Track progress
task_runner.py list "my-project"
task_runner.py complete 1
task_runner.py complete 2

# Export for documentation
task_runner.py export "my-project" "./my-project-tasks.md"
```

### Tracking autonomous agent experiments
```bash
# Plan experiments
task_runner.py add "Experiment 1: Publish skills" "autonomous-income" "high"
task_runner.py add "Experiment 2: Content automation" "autonomous-income" "medium"
task_runner.py add "Experiment 3: Service MVP" "autonomous-income" "low"

# Work through them
task_runner.py list "autonomous-income"
task_runner.py complete 1

# Adjust based on learning
task_runner.py add "Experiment 2a: Research tools without API keys" "autonomous-income" "high"
task_runner.py priority 2 "low"
```

### Daily task management
```bash
# Plan the day
task_runner.py add "Review pull requests" "daily" "high"
task_runner.py add "Write documentation" "daily" "medium"
task_runner.py add "Respond to emails" "daily" "low"

# End-of-day review
task_runner.py list

# Archive completed work
task_runner.py export "daily" "./$(date +%Y-%m-%d)-tasks.md"
```

## Best Practices

1. **Use meaningful project names** - `income-experiments` not `ideas`
2. **Set priorities consistently** - helps with focus
3. **Mark tasks complete promptly** - keeps list clean
4. **Export before major changes** - backup progress
5. **Review and clean up** - archive old projects regularly

## Integration with Other Skills

Combine with **research-assistant** for complete project management:
- Use `research-assistant` for notes and knowledge
- Use `task-runner` for actionable tasks
- Export both to create comprehensive project docs

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →