create-tasks

A task-backlog generator that turns a project scope, specification, or feature list into technical tasks grouped by phases, dependencies, and importance. A backlog is a prioritized list of work to complete.

In plain words
What is it for?
Creating task documents from specifications or standalone requirements, then linking the backlog to planning, analysis, execution, and review steps.
Why use it?
It breaks a large or vague piece of work into smaller units that can be planned, checked, and executed in order.

Skill for Claude CodeCodex

Part of the cstk plugin — 21 skills, 7 commands, 7 agents shipped together

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

Made for: Claude Code, Codex.

Or install cstk, the plugin that ships this one along with the rest of its 21 skills, 7 commands, 7 agents.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,253 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 $0.00058 $0.06253
Opus 5 $0.00029 $0.03127
Sonnet 5 $0.00012 $0.01251
Haiku 4.5 $0.00006 $0.00625

Measured 3d ago against content hash a63f558cb758, 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/next-task-id.sh, scripts/validate-tasks-template.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/cstk/skills/create-tasks/SKILL.md · 514 lines

How it starts

The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Criar Backlog de Tarefas

Crie um documento de backlog de tarefas tecnicas seguindo o padrao estruturado abaixo.

Pre-requisitos

Recomendado (fluxo SDD): plan.md e spec.md ja existentes em docs/specs/{feature}/. Com eles, o backlog se liga a fases tecnicas claras.

Alternativa standalone: descricao textual do escopo ou lista de features. Neste caso, salva em docs/tasks-{nome-escopo}.md.

Proximos passos

  1. /analyze — validar consistencia entre spec, plan e tasks
  2. /execute-task {id} — comecar execucao pela primeira tarefa critica
  3. /review-task — acompanhar progresso conforme tarefas sao concluidas

Argumentos

$ARGUMENTS

Instrucoes

Analise o argumento fornecido. Ele pode ser:

  1. Descricao do escopo: Uma descricao textual do que o MVP/projeto deve cobrir
  2. Documento de referencia: Um arquivo existente com requisitos, casos de uso ou especificacoes
  3. Lista de funcionalidades: Lista de features/modulos a serem organizados em tarefas

Deteccao de Origem (Spec vs Standalone)

ANTES de iniciar, determine se o argumento se origina de uma especificacao:

  1. Verifique se o argumento referencia um arquivo em docs/specs/ (ex: docs/specs/foo/spec.md)
  2. Verifique se o argumento menciona o nome de uma spec existente — liste docs/specs/*/spec.md com Glob
  3. Se o contexto da conversa indica que uma spec foi criada/usada recentemente, considere-a como origem

Se originado de uma spec (docs/specs/{spec-name}/spec.md):

  • Salvar em: docs/specs/{spec-name}/tasks.md
  • Usar o conteudo da spec como documento de referencia principal

Se chamado de forma isolada (sem spec associada):

  • Manter o comportamento padrao: docs/tasks-{nome-escopo}.md

Deteccao de reabertura (feature-00c --reopen) — continuidade de backlog

Aplicavel somente quando o state da execucao corrente tem .previous_round preenchido (contexto de reabertura via /feature-00c --reopen — mesma deteccao usada por plugins/cstk/skills/specify/SKILL.md §0.0/0.5) e o tasks.md-alvo (docs/specs/{spec-name}/tasks.md) ja existe (preservado/restaurado de round anterior, com fases/checkboxes concluidos). Fora desses dois criterios simultaneos, ignore esta secao e siga o fluxo normal (feature-reopen FR-015, Decision 11 de research.md: mesmo padrao ja praticado pela skill converge sobre tasks.md existente).

Read the full file on GitHub · 514 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 514 lines · 58 tokens per session scan A a63f558cb758

Subscribe to this mod's changes

create-tasks is a skill published in the GitHub repository JotJunior/cstk (22 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 6,253 once invoked, about $0.0003 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

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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