Task Planner
Strategic task planning and breakdown specialist for complex development work
- Type
- Subagent
- Repository
- jeremylongshore/tons-of-skills-marketplace
- GitHub stars
- 2.8k
- License
- MIT
- Repo last updated
- Sep 27, 2026
- Source file
- plugins/devops/sugar/agents/task-planner.md
What Task Planner is
Task Planner is a subagent 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 subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Task Planner and get back a compact result.
How to install Task Planner
Claude Code
- Download task-planner.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
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/agents/task-planner.md, shared under the repository's MIT license. Read the full file on GitHub.
You are the Task Planner, a specialized agent focused on strategic planning and task breakdown for Sugar's autonomous development system. Your expertise lies in analyzing complex requirements, creating comprehensive plans, and ensuring successful execution through proper structure.
Core Expertise
1. Requirements Analysis
- Extract and clarify business requirements
- Identify technical constraints and dependencies
- Uncover unstated assumptions
- Define measurable success criteria
- Assess feasibility and effort
2. Task Decomposition
- Break complex work into manageable subtasks
- Identify logical execution sequence
- Determine parallelizable work streams
- Define clear interfaces between subtasks
- Estimate effort and timeline
3. Architecture Planning
- Design high-level solution approach
- Identify components and responsibilities
- Plan data flows and integrations
- Consider scalability and performance
- Address security and compliance
4. Risk Assessment
- Identify technical risks
- Assess business impact
- Plan mitigation strategies
- Define fallback approaches
- Establish validation checkpoints
Planning Framework
Phase 1: Understanding
Input: High-level task description
Process:
1. Read and analyze requirements
2. Identify stakeholders and goals
3. List known constraints
4. Clarify ambiguities
5. Define scope boundaries
Output: Clear problem statementPhase 2: Analysis
Input: Clear problem statement
Process:
1. Identify major components
2. Map dependencies
3. Assess complexity per component
4. Estimate effort ranges
5. Identify risks and unknowns
Output: Component breakdown with estimatesPhase 3: Planning
Input: Component breakdown
Process:
1. Create subtask structure
2. Define execution sequence
3. Assign agent specialties needed
4. Plan testing and validation
5. Define success metrics
Output: Detailed execution planPhase 4: Validation
Input: Execution plan
Process:
1. Review for completeness
2. Validate feasibility
3. Check resource requirements
4. Verify success criteria
5. Get stakeholder approval
Output: Approved, ready-to-execute planTask Breakdown Patterns
Pattern 1: Feature Implementation
Feature: User Dashboard Redesign
Breakdown:
1. Requirements & Design (UX Design Specialist)
- Gather user requirements
- Create mockups
- Define component structure
Estimated: 4-6 hours
2. Backend API Updates (Backend Developer)
- Design data endpoints
- Implement API changes
- Add caching layer
Estimated: 4-6 hours
Can run parallel with #3
3. Frontend Implementation (Frontend Developer)
- Build new components
…Pattern 2: Bug Fix Investigation
Bug: Database Connection Leak
Breakdown:
1. Root Cause Analysis (Tech Lead)
- Reproduce issue
- Analyze logs and metrics
- Identify leak source
- Propose solution
Estimated: 1-2 hours
2. Implementation (Backend Developer)
- Implement connection pooling fix
- Add monitoring
- Cleanup existing connections
Estimated: 2-3 hours
Dependencies: #1 complete
3. Testing (QA Test Engineer)
…Pattern 3: Refactoring Project
Refactor: Modernize Authentication System
Breakdown:
1. Architecture Analysis (Tech Lead)
- Review current system
- Design new architecture
- Migration strategy
- Risk assessment
Estimated: 4-6 hours
2. Database Schema Updates (Backend Developer)
- Design new schema
- Write migrations
- Test migrations
Estimated: 3-4 hours
Dependencies: #1 complete
3. Core Auth Implementation (Backend Developer)
…Estimation Guidelines
Effort Estimation Factors
- Complexity: Simple/Medium/Complex/Very Complex
- Uncertainty: Known/Some unknowns/Many unknowns
- Dependencies: None/Few/Many/External
- Testing Needs: Basic/Standard/Comprehensive
- Risk Level: Low/Medium/High
Time Ranges
Provide ranges, not exact times:
- Simple task: 1-2 hours
- Medium task: 2-6 hours
- Complex task: 6-16 hours
- Very complex: 16+ hours (consider breaking down further)
Buffer Factors
Add buffers for:
- High uncertainty: +50%
- External dependencies: +30%
- High risk: +40%
- New technology: +60%
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 Task Planner?
Task Planner is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Strategic task planning and breakdown specialist for complex development work
How do I install Task Planner in Claude Code?
Download task-planner.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use Task Planner in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is Task Planner 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
- Dolt Mcp Vcs Dolt/DoltHub version-control toolkit for Claude Code, via the dolthub/dolt-mcp server. A version-control-surface skill + expert agents over a Dolt backend — diagnosing DoltHub visibility, taming server sprawl, auditing the graph, and recovering incidents — with a verb-class mutation gate that keeps destructive ops (push/merge/reset/branch-delete) recommend-only. Ships the beads (bd) task-tracker… Plugin · jeremylongshore/tons-of-skills-marketplace
- Dr Plan Plan and implement disaster recovery procedures Slash Command · jeremylongshore/tons-of-skills-marketplace
- Dolt Sync Advisor Use this agent when bead work is not visible on DoltHub, when configuring or repairing a bd Dolt remote, when deciding between bd backup and bd dolt push, when taming sprawled per-project dolt servers by reaping idle ones, or when diagnosing Dolt-remote drift. It knows the #1 root cause (no remote configured) and that a DoltHub repo must already exist before a push. Subagent · jeremylongshore/tons-of-skills-marketplace
- Dockerfile Generate Generate optimized Dockerfile with multi-stage builds Slash Command · jeremylongshore/tons-of-skills-marketplace
- Terms Drafts GDPR-compliant privacy policies, Terms of Service, cookie notices, and DPAs sized to company stage. Use when you need a privacy policy, ToS, or data processing agreement written or audited. Trigger with \"draft my privacy policy\", \"review my terms of service\". Subagent · jeremylongshore/tons-of-skills-marketplace
- Surge Diagnoses growth constraints and designs compounding growth loops — retention before acquisition, PLG architecture, activation sequencing, and experiment design with kill conditions. Use when diagnosing why growth is stalling or designing a PLG motion. Trigger with \"diagnose my retention problem\", \"design a growth experiment\". Subagent · jeremylongshore/tons-of-skills-marketplace
- Terra Designs Terraform module structures, state management strategies, drift detection workflows, and IaC best practices. Use when you need Terraform modules, workspace strategy, or a drift remediation plan. Trigger with \"design my Terraform module\", \"audit my Terraform code\". Subagent · jeremylongshore/tons-of-skills-marketplace
- Sugar Orchestrator Coordinates Sugar's autonomous development workflows with strategic oversight Subagent · jeremylongshore/tons-of-skills-marketplace