A task-planning command that turns a product requirements document and technical specification into separate implementation tasks in dependency order. A product requirements document describes what should be built; a technical specification describes how.

Use it when the required PRD and tech spec already exist and you need task files that another agent can implement without further clarification.

It breaks a large feature into clear pieces that can be completed independently. Dependencies are made explicit so work can happen in a sensible order.

tasks — Skill by strvcom

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 skills/strvcom/flutter-template/tasks

Any agent

npx skills add strvcom/flutter-template --skill tasks

Clone the repo

git clone --depth 1 https://github.com/strvcom/flutter-template

Made for: Claude Code, Codex.

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,557 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.

Model	Per session	Once invoked
Fable 5	$0.00113	$0.01557
Opus 5	$0.00056	$0.00779
Sonnet 5	$0.00023	$0.00311
Haiku 4.5	$0.00011	$0.00156

Measured 2d ago against content hash d4c2f544623a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/skills/tasks/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Breakdown

You are specialized in breaking down features into discrete, manageable implementation tasks.

Objectives

Break down the feature into independently completable tasks
Establish clear dependency ordering
Create task files that an agent can execute without ambiguity

Prerequisites

PRD: .claude/tasks/[feature-name]/prd.md
Tech Spec: .claude/tasks/[feature-name]/techspec.md

Workflow

CRITICAL: Do NOT ask for approval.

The user does not want to review the task list before implementation. Generate the tasks, keep the total count reasonable (aim for cohesive tasks, not micro-tasks), and stop after reporting. The caller (/start-job or the user directly) decides what runs next.

Step 0: Load Shared Context

Before reading the PRD and tech spec, check whether .claude/tasks/[feature-name]/context.md exists. If it does, read it. Use its contents to skip re-deriving already-captured decisions — the problem statement, target platforms, architectural choices, and files to create are already settled. Do not re-ask the user about items already recorded there.

Step 1: Analyze PRD and Tech Spec

Read both documents and identify:

All components that need to be built
The dependency graph between components
Which tasks can be parallelized

Step 2: Generate Task Structure

Order tasks following this Flutter-stack progression (mirrors the .agents/templates/task-list.md phases):

Foundation (data layer) — DTOs in lib/common/data/dto/ (@freezed with generated fromJson factories), domain entities in lib/common/data/entity/, and Riverpod use cases/providers. Run make gen after annotation changes.
Core implementation (state + UI) — @riverpod notifiers, *_state.dart / *_event.dart (feature-scoped freezed types), and the page split: *_page.dart (thin @RoutePage widget) + *_page_content.dart (heavier UI).
Integration (navigation, services, platform) — @RoutePage wiring in lib/app/, Firebase / platform integrations, analytics events, permissions, native channels.
Tests and verification — only when explicitly required by the PRD / techspec. Standard analyze / test / build verification is handled by build-verify at the end of the flow, so don't add a "run analyze" task unless the feature itself requires custom coverage.

Read the full file on GitHub · 150 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.

2d ago First seen · 150 lines · 113 tokens per session scan A d4c2f544623a

Subscribe to this mod's changes

tasks is a skill published in the GitHub repository strvcom/flutter-template (24 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 1,557 once invoked, about $0.0006 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.

Data and AI Documents Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens