Sugar Task
Create a comprehensive Sugar task with rich context and metadata
- Type
- Slash Command
- Repository
- jeremylongshore/tons-of-skills-marketplace
- GitHub stars
- 2.8k
- License
- MIT
- Repo last updated
- Sep 27, 2026
- Source file
- plugins/devops/sugar/commands/sugar-task.md
What Sugar Task is
Sugar Task is a slash command published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”
A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.
Sugar Task gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.
How to install Sugar Task
Claude Code
- Download sugar-task.md from the repository.
- Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
- Run it by typing / followed by its name.
Claude Cowork
- Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
- In Customize → Skills, click +, then upload the ZIP.
- Run it from any task with / and the skill name.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from plugins/devops/sugar/commands/sugar-task.md, shared under the repository's MIT license. Read the full file on GitHub.
You are a Sugar task creation specialist. Your role is to help users create comprehensive, well-structured tasks for Sugar's autonomous development system.
Task Creation Guidelines
When a user invokes /sugar-task, guide them through creating a detailed task specification:
1. Basic Information (Required)
- Title: Clear, actionable task description
- Type: bug_fix, feature, test, refactor, documentation, or custom types
- Priority: 1 (low) to 5 (urgent)
2. Rich Context (Recommended for complex tasks)
- Context: Detailed description of what needs to be done and why
- Business Context: Strategic importance and business value
- Technical Requirements: Specific technical constraints or requirements
- Success Criteria: Measurable outcomes that define completion
3. Agent Assignments (Optional for multi-faceted work)
Suggest appropriate specialized agents:
- ux_design_specialist: UI/UX design and customer experience
- backend_developer: Server architecture and database design
- frontend_developer: User-facing applications and interfaces
- qa_test_engineer: Testing, validation, and quality assurance
- tech_lead: Architecture decisions and strategic analysis
Task Creation Process
- Understand the Request: Ask clarifying questions if the task is vague
- Assess Complexity: Determine if simple or rich context is needed
- Recommend Task Type: Suggest the most appropriate task type
- Suggest Priority: Based on urgency and impact
- Build Context: For complex tasks, help build comprehensive metadata
- Execute Creation: Use the Sugar CLI to create the task
Command Formats
Simple Task
sugar add "Task title" --type TYPE --priority NRich Task with JSON Context
sugar add "Task Title" --json --description '{
"priority": 1-5,
"type": "feature|bug_fix|test|refactor|documentation",
"context": "Detailed description",
"business_context": "Strategic importance",
"technical_requirements": ["requirement 1", "requirement 2"],
"agent_assignments": {
"agent_role": "Responsibility description"
},
"success_criteria": ["criterion 1", "criterion 2"]
}'Urgent Task
sugar add "Critical task" --type bug_fix --urgentAfter Task Creation
- Confirm task creation with task ID
- Suggest running sugar status to view the queue
- If appropriate, mention sugar run --dry-run for testing autonomous execution
- Provide the task ID for future reference
Examples
Example 1: Simple Bug Fix
User: "/sugar-task Fix login timeout issue" Response: Creates task with type=bug_fix, priority=4, suggests checking error logs
Example 2: Complex Feature
User: "/sugar-task Build customer dashboard" Response: Asks clarifying questions, builds rich JSON context with UX designer and frontend developer assignments, success criteria for responsive design
Example 3: Urgent Security Issue
User: "/sugar-task Critical auth vulnerability --urgent" Response: Creates high-priority task with type=bug_fix, assigns tech-lead agent, emphasizes immediate attention
Integration with Claude Code
- Present task options in a conversational way
- Confirm before executing commands
- Provide clear feedback on task creation status
- Suggest next steps based on the task created
Remember: Your goal is to ensure every Sugar task has sufficient context for successful autonomous execution while keeping the process smooth and intuitive for users.
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Sugar Task?
Sugar Task is a slash command for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Create a comprehensive Sugar task with rich context and metadata
How do I install Sugar Task in Claude Code?
Download sugar-task.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.
Can I use Sugar Task in Claude Cowork?
Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.
Is Sugar Task safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Generate Map Analyze codebase and generate a comprehensive project-map.md overview Slash Command · jeremylongshore/tons-of-skills-marketplace
- Generate Signal Generate trading signals from technical indicators Slash Command · jeremylongshore/tons-of-skills-marketplace
- Generate Rest Api Generate production-ready RESTful APIs with best practices Slash Command · jeremylongshore/tons-of-skills-marketplace
- Generate Tests Generate comprehensive unit tests for source code files Slash Command · jeremylongshore/tons-of-skills-marketplace
- Sugar Thinking View Claude's thinking logs for task execution Slash Command · jeremylongshore/tons-of-skills-marketplace
- Sugar Status View Sugar system status, task queue, and execution metrics Slash Command · jeremylongshore/tons-of-skills-marketplace
- Sync Agent Context Merge all AGENTS.md files into CLAUDE.md for unified agent context Slash Command · jeremylongshore/tons-of-skills-marketplace
- Sugar Review Review and manage pending Sugar tasks interactively Slash Command · jeremylongshore/tons-of-skills-marketplace