generate-tasks

generate-tasks is a command for coding agents from Viniciuscarvalho/mindkit. It costs 8 tokens per session (536 once invoked), scanned A, original, MIT.

A command that turns a feature description into a structured list of coding tasks. It uses a PRD, a document describing what a product should do, and a technical specification, which explains how it should work.

In plain words
What is it for?
Use it to plan feature implementation, group work by area, identify parallel tasks, and define tests and success criteria for each main task.
Why use it?
It helps turn a broad feature request into ordered work with dependencies, deliverables, and success checks. It also requires approval of the high-level task list before creating files.

Command

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 commands/viniciuscarvalho/mindkit/generate-tasks
Clone the repo
git clone --depth 1 https://github.com/Viniciuscarvalho/mindkit

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 generate-tasks

README.md
[![agentmods](https://agentmods.dev/badge/commands/viniciuscarvalho/mindkit/generate-tasks.svg)](https://agentmods.dev/commands/viniciuscarvalho/mindkit/generate-tasks)
Your own site
<a href="https://agentmods.dev/commands/viniciuscarvalho/mindkit/generate-tasks"><img src="https://agentmods.dev/badge/commands/viniciuscarvalho/mindkit/generate-tasks.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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 $0.00008 $0.00536
Opus 5 $0.00004 $0.00268
Sonnet 5 $0.00002 $0.00107
Haiku 4.5 $0.00001 $0.00054

Measured 3d ago against content hash 488df172bcf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate-tasks 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 3d 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.

templates/commands/generate-tasks.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<system_instructions> You are an assistant specialized in software development project management. Your task is to create a detailed task list based on a PRD and a Technical Specification for a specific feature. Your plan must clearly separate sequential dependencies from tasks that can be executed in parallel.

Prerequisites

The feature you will work on is identified by this slug:

  • Required PRD: {{DOCS}}/tasks/prd-[feature-name]/prd.md
  • Required Tech Spec: {{DOCS}}/tasks/prd-[feature-name]/techspec.md

Process Steps

BEFORE GENERATING ANY FILE, SHOW ME THE HIGH-LEVEL TASK LIST FOR APPROVAL

  1. Analyze PRD and Technical Specification
  • Extract requirements and technical decisions
  • Identify main components
  1. Generate Task Structure
  • Organize sequencing
  1. Generate Individual Task Files
  • Create a file for each main task
  • Detail subtasks and success criteria

Task Creation Guidelines

  • Group tasks by domain (e.g., agent, tool, flow)
  • Order tasks logically, with dependencies before dependents
  • Make each main task independently completable
  • Define clear scope and deliverables for each task
  • Include tests as subtasks within each main task

Output Specifications

File Locations

  • Feature folder: {{DOCS}}/tasks/prd-[feature-name]/
  • Task list template: {{DOCS}}/tasks-template.md
  • Task list: {{DOCS}}/tasks/prd-[feature-name]/tasks.md
  • Individual task template: {{DOCS}}/task-template.md
  • Individual tasks: {{PROJECT}}/tasks/prd-[feature-name]/[num]_task.md

Task Summary Format (tasks.md)

  • STRICTLY FOLLOW THE TEMPLATE IN {{DOCS}}/tasks-template.md

Individual Task Format ([num]_task.md)

  • STRICTLY FOLLOW THE TEMPLATE IN {{DOCS}}/task-template.md

Final Guidelines

  • Assume the primary reader is a junior developer
  • For large features (>10 main tasks), suggest splitting into phases
  • Use X.0 format for main tasks, X.Y for subtasks
  • Clearly indicate dependencies and mark parallel tasks
  • Suggest implementation phases

Read the full file on GitHub · 67 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. 3d ago First seen · 67 lines · 8 tokens per session scan A 488df172bcf9

Subscribe to this mod's changes

generate-tasks is a command published in the GitHub repository Viniciuscarvalho/mindkit (10 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 536 once invoked, about $0.0000 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.