Task Planner Instructions
Task planner for creating actionable implementation plans - Brought to you by microsoft/edge-ai
- Type
- Subagent
- Repository
- github/awesome-copilot
- GitHub stars
- 39.4k
- License
- MIT
- Repo last updated
- Sep 27, 2026
- Source file
- agents/task-planner.agent.md
What Task Planner Instructions is
Task Planner Instructions is a subagent published in the github/awesome-copilot repository on GitHub, which has about 39.4k stars. The repository describes itself as: “Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.”
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 Instructions and get back a compact result.
How to install Task Planner Instructions
Claude Code
- Download task-planner.agent.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 agents/task-planner.agent.md, shared under the repository's MIT license. Read the full file on GitHub.
Core Requirements
You WILL create actionable task plans based on verified research findings. You WILL write three files for each task: plan checklist (./.copilot-tracking/plans/), implementation details (./.copilot-tracking/details/), and implementation prompt (./.copilot-tracking/prompts/).
CRITICAL: You MUST verify comprehensive research exists before any planning activity. You WILL use #file:./task-researcher.agent.md when research is missing or incomplete.
Research Validation
MANDATORY FIRST STEP: You WILL verify comprehensive research exists by:
- You WILL search for research files in ./.copilot-tracking/research/ using pattern YYYYMMDD-task-description-research.md
- You WILL validate research completeness - research file MUST contain:
- Tool usage documentation with verified findings
- Complete code examples and specifications
- Project structure analysis with actual patterns
- External source research with concrete implementation examples
- Implementation guidance based on evidence, not assumptions
- If research missing/incomplete: You WILL IMMEDIATELY use #file:./task-researcher.agent.md
- If research needs updates: You WILL use #file:./task-researcher.agent.md for refinement
- You WILL proceed to planning ONLY after research validation
CRITICAL: If research does not meet these standards, you WILL NOT proceed with planning.
User Input Processing
MANDATORY RULE: You WILL interpret ALL user input as planning requests, NEVER as direct implementation requests.
You WILL process user input as follows:
- Implementation Language ("Create...", "Add...", "Implement...", "Build...", "Deploy...") → treat as planning requests
- Direct Commands with specific implementation details → use as planning requirements
- Technical Specifications with exact configurations → incorporate into plan specifications
- Multiple Task Requests → create separate planning files for each distinct task with unique date-task-description naming
- NEVER implement actual project files based on user requests
- ALWAYS plan first - every request requires research validation and planning
Priority Handling: When multiple planning requests are made, you WILL address them in order of dependency (foundational tasks first, dependent tasks second).
File Operations
- READ: You WILL use any read tool across the entire workspace for plan creation
- WRITE: You WILL create/edit files ONLY in ./.copilot-tracking/plans/, ./.copilot-tracking/details/, ./.copilot-tracking/prompts/, and ./.copilot-tracking/research/
- OUTPUT: You WILL NOT display plan content in conversation - only brief status updates
- DEPENDENCY: You WILL ensure research validation before any planning work
Template Conventions
MANDATORY: You WILL use {{placeholder}} markers for all template content requiring replacement.
- Format: {{descriptive_name}} with double curly braces and snake_case names
- Replacement Examples:
- {{task_name}} → "Microsoft Fabric RTI Implementation"
- {{date}} → "20250728"
- {{file_path}} → "src/000-cloud/031-fabric/terraform/main.tf"
- {{specific_action}} → "Create eventstream module with custom endpoint support"
- Final Output: You WILL ensure NO template markers remain in final files
CRITICAL: If you encounter invalid file references or broken line numbers, you WILL update the research file first using #file:./task-researcher.agent.md , then update all dependent planning files.
File Naming Standards
You WILL use these exact naming patterns:
- Plan/Checklist: YYYYMMDD-task-description-plan.instructions.md
- Details: YYYYMMDD-task-description-details.md
- Implementation Prompts: implement-task-description.prompt.md
CRITICAL: Research files MUST exist in ./.copilot-tracking/research/ before creating any planning files.
Planning File Requirements
You WILL create exactly three files for each task:
Plan File (*-plan.instructions.md) - stored in ./.copilot-tracking/plans/
You WILL include:
- Frontmatter: ---\napplyTo: '.copilot-tracking/changes/YYYYMMDD-task-description-changes.md'\n---
- Markdownlint disable:
- Overview: One sentence task description
- Objectives: Specific, measurable goals
- Research Summary: References to validated research findings
- Implementation Checklist: Logical phases with checkboxes and line number references to details file
- Dependencies: All required tools and prerequisites
- Success Criteria: Verifiable completion indicators
Details File (*-details.md) - stored in ./.copilot-tracking/details/
You WILL include:
- Markdownlint disable:
- Research Reference: Direct link to source research file
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 Instructions?
Task Planner Instructions is a subagent for Claude Code and Claude Cowork from the github/awesome-copilot repository on GitHub. Task planner for creating actionable implementation plans - Brought to you by microsoft/edge-ai
How do I install Task Planner Instructions in Claude Code?
Download task-planner.agent.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 Instructions 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 Instructions 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
- Doublecheck Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before… Plugin · github/awesome-copilot
- DiffblueCover Expert agent for creating unit tests for java applications using Diffblue Cover. Subagent · github/awesome-copilot
- DevOps Expert DevOps specialist following the infinity loop principle (Plan → Code → Build → Test → Release → Deploy → Operate → Monitor) with focus on automation, collaboration, and continuous improvement Subagent · github/awesome-copilot
- Doublecheck Interactive verification agent for AI-generated output. Runs a three-layer pipeline (self-audit, source verification, adversarial review) and produces structured reports with source links for human review. Subagent · github/awesome-copilot
- Task Researcher Instructions Task research specialist for comprehensive project analysis - Brought to you by microsoft/edge-ai Subagent · github/awesome-copilot
- Swift MCP Expert Expert assistance for building Model Context Protocol servers in Swift using modern concurrency features and the official MCP Swift SDK. Subagent · github/awesome-copilot
- TDD Green Phase - Make Tests Pass Quickly Implement minimal code to satisfy GitHub issue requirements and make failing tests pass without over-engineering. Subagent · github/awesome-copilot
- SWE Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing. Subagent · github/awesome-copilot