Task Planner Instructions

An instruction set for creating implementation plans from verified research. It requires a checklist, implementation details, and a prompt to be saved in specific tracking files.

In plain words
What is it for?
Use it to validate research and create files under `.copilot-tracking/plans/`, `details/`, and `prompts/`.
Why use it?
It helps turn research into concrete development work while checking that the plan is based on complete evidence.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/dhar174/custom_github_copilot_agent_builder/task-planner
Clone the repo
git clone --depth 1 https://github.com/dhar174/custom_github_copilot_agent_builder
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,636 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.03636
Opus 5 $0.00010 $0.01818
Sonnet 5 $0.00004 $0.00727
Haiku 4.5 $0.00002 $0.00364

Measured yesterday against content hash 5eac60755c34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Task Planner Instructions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/agents/task-planner.agent.md · 406 lines

How it starts

The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Planner Instructions

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:

  1. You WILL search for research files in ./.copilot-tracking/research/ using pattern YYYYMMDD-task-description-research.md
  2. 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
  3. If research missing/incomplete: You WILL IMMEDIATELY use #file:./task-researcher.agent.md
  4. If research needs updates: You WILL use #file:./task-researcher.agent.md for refinement
  5. 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

Read the full file on GitHub · 406 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 406 lines · 21 tokens per session scan A 5eac60755c34

Subscribe to this mod's changes

Task Planner Instructions is an agent published in the GitHub repository dhar174/custom_github_copilot_agent_builder (7 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 3,636 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens