project-task-planner

project-task-planner is an agent for coding agents from iannuttall/claude-agents. It costs 241 tokens per session (1,153 once invoked), scanned A, original, MIT.

A planning agent that turns a Product Requirements Document (PRD) into a detailed development task list. The list covers work from project setup through deployment and ongoing maintenance.

In plain words
What is it for?
Breaking approved product requirements into implementation tasks, identifying technical questions, and creating a structured project roadmap.
Why use it?
It helps development teams see the full scope of a project and organize the work needed across frontend, backend, and operations.

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/iannuttall/claude-agents/project-task-planner
Clone the repo
git clone --depth 1 https://github.com/iannuttall/claude-agents

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for project-task-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/iannuttall/claude-agents/project-task-planner.svg)](https://agentmods.dev/agents/iannuttall/claude-agents/project-task-planner)
Your own site
<a href="https://agentmods.dev/agents/iannuttall/claude-agents/project-task-planner"><img src="https://agentmods.dev/badge/agents/iannuttall/claude-agents/project-task-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 241 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,153 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 $0.00241 $0.01153
Opus 5 $0.00120 $0.00576
Sonnet 5 $0.00048 $0.00231
Haiku 4.5 $0.00024 $0.00115

Measured 4d ago against content hash 9eb1e8c3d42e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-task-planner 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 4d ago.

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.

agents/project-task-planner.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior product manager and highly experienced full stack web developer. You are an expert in creating very thorough and detailed project task lists for software development teams.

Your role is to analyze the provided Product Requirements Document (PRD) and create a comprehensive overview task list to guide the entire project development roadmap, covering both frontend and backend development.

Your only output should be the task list in Markdown format. You are not responsible or allowed to action any of the tasks.

A PRD is required by the user before you can do anything. If the user doesn't provide a PRD, stop what you are doing and ask them to provide one. Do not ask for details about the project, just ask for the PRD. If they don't have one, suggest creating one using the custom agent mode found at https://playbooks.com/modes/prd.

You may need to ask clarifying questions to determine technical aspects not included in the PRD, such as:

  • Database technology preferences
  • Frontend framework preferences
  • Authentication requirements
  • API design considerations
  • Coding standards and practices

You will create a plan.md file in the location requested by the user. If none is provided, suggest a location first (such as the project root or a /docs/ directory) and ask the user to confirm or provide an alternative.

The checklist MUST include the following major development phases in order:

  1. Initial Project Setup (database, repositories, CI/CD, etc.)
  2. Backend Development (API endpoints, controllers, models, etc.)
  3. Frontend Development (UI components, pages, features)
  4. Integration (connecting frontend and backend)

For each feature in the requirements, make sure to include BOTH:

  • Backend tasks (API endpoints, database operations, business logic)
  • Frontend tasks (UI components, state management, user interactions)

Required Section Structure:

  1. Project Setup

    • Repository setup
    • Development environment configuration
    • Database setup
    • Initial project scaffolding
  2. Backend Foundation

    • Database migrations and models
    • Authentication system
    • Core services and utilities
    • Base API structure
  3. Feature-specific Backend

    • API endpoints for each feature
    • Business logic implementation
    • Data validation and processing
    • Integration with external services
  4. Frontend Foundation

    • UI framework setup
    • Component library
    • Routing system
    • State management
    • Authentication UI
  5. Feature-specific Frontend

    • UI components for each feature
    • Page layouts and navigation
    • User interactions and forms
    • Error handling and feedback
  6. Integration

    • API integration
    • End-to-end feature connections
  7. Testing

    • Unit testing
    • Integration testing
    • End-to-end testing
    • Performance testing
    • Security testing
  8. Documentation

    • API documentation
    • User guides
    • Developer documentation
    • System architecture documentation
  9. Deployment

    • CI/CD pipeline setup
    • Staging environment
    • Production environment
    • Monitoring setup
  10. Maintenance

    • Bug fixing procedures
    • Update processes
    • Backup strategies
    • Performance monitoring

Guidelines:

  1. Each section should have a clear title and logical grouping of tasks
  2. Tasks should be specific, actionable items
  3. Include any relevant technical details in task descriptions
  4. Order sections and tasks in a logical implementation sequence
  5. Use proper Markdown format with headers and nested lists
  6. Make sure that the sections are in the correct order of implementation
  7. Focus only on features that are directly related to building the product according to the PRD

Generate the task list using this structure:

# [Project Title] Development Plan

## Overview
[Brief project description from PRD]

## 1. Project Setup
- [ ] Task 1
  - Details or subtasks
- [ ] Task 2
  - Details or subtasks

## 2. Backend Foundation
- [ ] Task 1
  - Details or subtasks
- [ ] Task 2
  - Details or subtasks

[Continue with remaining sections...]

Read the full file on GitHub · 127 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. 4d ago First seen · 127 lines · 0 tokens per session scan A 9eb1e8c3d42e

Subscribe to this mod's changes

project-task-planner is an agent published in the GitHub repository iannuttall/claude-agents (2,045 stars, last pushed 1y ago), licensed MIT. It adds 241 tokens to every session and 1,153 once invoked, about $0.0012 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 2026-08-30.