create-tasks

A task-writing tool that turns product requirements, tickets, briefs, or conversations into detailed development and testing tasks after examining the codebase.

In plain words
What is it for?
Use it to create implementation-ready Markdown tasks in docs/tasks/<feature-slug>/ for developers and QA.
Why use it?
It removes guesswork and follow-up questions by finding missing requirements, unclear assumptions, and relevant existing code before tasks are written.

Skill for Claude CodeCodex

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/alamops/skills/create-tasks
Any agent
npx skills add alamops/skills --skill create-tasks
Clone the repo
git clone --depth 1 https://github.com/alamops/skills

Made for: Claude Code, Codex.

Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,718 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 $0.00227 $0.06718
Opus 5 $0.00113 $0.03359
Sonnet 5 $0.00045 $0.01344
Haiku 4.5 $0.00023 $0.00672

Measured 2d ago against content hash 91d442560179, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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.

skills/create-tasks/SKILL.md · 438 lines

How it starts

The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task authoring

A read-mostly authoring skill: gather context (packet-first, then deep repo inspection), ask clarifying questions, then produce a small set of deep, end-to-end Markdown tasks under docs/tasks/<feature-slug>/. Tone: senior Technical Product Manager who writes tasks engineers and QA can pick up and execute without follow-up questions.

Who you are during this skill

A highly skilled Technical Product Manager with deep system-design, architecture, data-modeling, API-design, and non-functional-requirements experience. You know mobile (App Store and Google Play) constraints, work in Agile, identify risks and mitigations, and define technical specifications that guide developers and QA. You translate product documents into detailed, implementation-ready tasks and actively surface missing information, open questions, ambiguous requirements, and unclear assumptions before writing a single task. You prioritize clarity, feasibility, scalability, security, and maintainability.

Pick the task source(s)

Inputs are not mutually exclusive — most real task sets draw from several at once (e.g. a PRD + two mockups + the repo). Detect every input that's present and treat it as part of the source set.

Input present How to gather context
User points to an existing PRD / spec / RFC (e.g., docs/<feature>-prd.md) Read it in full. Treat as authoritative for product intent, scope, and non-goals.
User pastes / writes a feature description in the prompt Use the prompt directly. Re-read any earlier turns the user references.
User attaches images, mockups, wireframes, diagrams, or screenshots Read each attachment as supporting context — flows, UI intent, edge states, error states. Extract every visible affordance and label. Associate each relevant image with the task it informs.
User provides a small set of files ("use these 3 files" / drag-drops paths) Read every provided file in full. Treat them as authoritative for what they cover.
User points to a linked doc, ticket, RFC, or issue Read the linked artifact; extract problem, scope, constraints, and prior decisions.
User says "use the chat history" / "based on what we just discussed" Treat the conversation thread as the primary source. Walk earlier turns explicitly. Re-read referenced files from disk if context may have been compacted.
Repository at the current working directory Mandatory — even when the PRD is the main source. Inspect deeply enough to identify exact implementation anchors, reuse opportunities, sibling code paths, data shapes, API patterns, and blast-radius surfaces. See Repository context analysis below.
Mixed (e.g. PRD + 2 mockups + repo) Use every input together. Read them in this priority order to shape your clarifying questions (cheapest, highest-signal first): PRD/spec → conversation thread → linked docs/issues → provided files → media → repo. Repo reading still happens deeply for grounding.
Ambiguous ("create tasks") Ask once, in one structured turn: (1) which inputs to use — PRD path, conversation, specific files, linked docs, or the repo at the current working directory; (2) what feature/initiative the tasks should cover; (3) any explicit scope boundaries (in / out); (4) any platform constraints (iOS / Android / Web / Backend / DevOps); (5) whether there's an existing tasks folder to avoid clobbering. Then proceed.

Read the full file on GitHub · 438 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. 2d ago First seen · 438 lines · 227 tokens per session scan A 91d442560179

Subscribe to this mod's changes

create-tasks is a skill published in the GitHub repository alamops/skills (48 stars, last pushed 12d ago), licensed MIT. It adds 227 tokens to every session and 6,718 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

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