spekka: Command for Claude Code

.claude/commands/spekka/create-tasks.md

create-tasks is a command for Claude Code from johnreitano/spekka. It costs 0 tokens per session (421 once invoked), scanned A, original, MIT.

A command that turns a software specification or requirements document into an ordered list of implementation tasks.

In plain words
What is it for?
It is for reading project planning documents and creating a tasks.md file that groups and sequences the work.
Why use it?
It removes the need to manually break a feature plan into smaller, actionable pieces.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is johnreitano/spekka's own configuration. It tells Claude Code how to work on spekka itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spekka configures →

Reuse

Borrowing it

Nothing to install: this file belongs to johnreitano/spekka. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/johnreitano/spekka/main/.claude/commands/spekka/create-tasks.md
Clone the repo
git clone --depth 1 https://github.com/johnreitano/spekka

Made for: Claude Code.

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 create-tasks

README.md
[![agentmods](https://agentmods.dev/badge/commands/johnreitano/spekka/create-tasks/github.svg)](https://agentmods.dev/commands/johnreitano/spekka/create-tasks)
Your own site
<a href="https://agentmods.dev/commands/johnreitano/spekka/create-tasks"><img src="https://agentmods.dev/badge/commands/johnreitano/spekka/create-tasks/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for create-tasks

Your own site · 80×15
<a href="https://agentmods.dev/commands/johnreitano/spekka/create-tasks"><img src="https://agentmods.dev/badge/commands/johnreitano/spekka/create-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00421
Opus 5.5 $0.00000 $0.00168
Sonnet 5.5 $0.00000 $0.00084
Haiku 4.5 $0.00000 $0.00042

Measured 2mo ago against content hash 6265053b0785, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.claude/commands/spekka/create-tasks.md · 41 lines

What it actually says

Task List Creation Process

You are creating a tasks breakdown from a given spec and requirements for a new feature.

PHASE 1: Get and read the spec.md and/or requirements document(s)

You will need ONE OR BOTH of these files to inform your tasks breakdown:

  • spekka/specs/[this-spec]/spec.md
  • spekka/specs/[this-spec]/planning/requirements.md

IF you don't have ONE OR BOTH of those files in your current conversation context, then ask user to provide direction on where to you can find them by outputting the following request then wait for user's response:

I'll need a spec.md or requirements.md (or both) in order to build a tasks list.

Please direct me to where I can find those.  If you haven't created them yet, you can run /spekka:shape-spec or /spekka:write-spec.

PHASE 2: Create tasks.md

Once you have spec.md AND/OR requirements.md, use the tasks-list-creator subagent to break down the spec and requirements into an actionable tasks list with strategic grouping and ordering.

Provide the tasks-list-creator:

  • spekka/specs/[this-spec]/spec.md (if present)
  • spekka/specs/[this-spec]/planning/requirements.md (if present)
  • spekka/specs/[this-spec]/planning/visuals/ and its' contents (if present)

The tasks-list-creator will create tasks.md inside the spec folder.

PHASE 3: Inform user

Once the tasks-list-creator has created tasks.md output the following to inform the user:

Your tasks list ready!

✅ Tasks list created: `spekka/specs/[this-spec]/tasks.md`

NEXT STEP 👉 Run `/spekka:implement-tasks` (simple, effective) or `/spekka:orchestrate-tasks` (advanced, powerful) to start building!
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. 2mo ago First seen · 41 lines · 0 tokens per session scan A 6265053b0785

Subscribe to this mod's changes

create-tasks is a command published in the GitHub repository johnreitano/spekka (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 421 tokens. 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.

Related

create-tasks compared with commands from other repositories

create-tasks next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
create-tasksjohnreitano/spekkaCommand59mo agoMITA0Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code
clarifygithub/spec-kitCommand148kyesterdayMITA27Claude Code
specifygithub/spec-kitCommand148kyesterdayMITA13Claude Code
analyzegithub/spec-kitCommand148kyesterdayMITA26Claude Code
convergegithub/spec-kitCommand148kyesterdayMITA35Claude Code
implementgithub/spec-kitCommand148kyesterdayMITA14Claude Code