create-tasks

A tool for turning a feature plan or product requirements document into GitHub issues. GitHub issues are trackable work items for a software project.

In plain words
What is it for?
Use it to create a single issue, an epic with task issues, or a preview of the issues that would be created.
Why use it?
It saves you from manually breaking a plan into tasks and deciding whether the work needs one issue or a larger group of linked issues.

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

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,834 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 $0.00056 $0.01834
Opus 5 $0.00028 $0.00917
Sonnet 5 $0.00011 $0.00367
Haiku 4.5 $0.00006 $0.00183

Measured yesterday against content hash c37ff81a1ce5, 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 yesterday.

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/dev-workflow/skills/create-tasks/SKILL.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create GitHub Tasks

Analyze a feature plan or PRD and create the appropriate GitHub issue structure. Automatically decides whether to create a single issue or an epic with multiple task issues based on scope and complexity.

Configuration

Read cloudstack.json from the project root at the start of execution. Extract relevant fields:

  • REPO_OWNER / REPO_NAME = repository.owner / repository.name (default: detect from git remote -v)

If cloudstack.json does not exist, auto-detect by parsing the GitHub remote URL:

git remote get-url origin | sed -E 's|.*github\.com[:/]([^/]+)/([^/.]+).*|\1 \2|'

Arguments

  • {prd-path} -- Path to PRD file (optional, will search docs/prd/ or use conversation context)
  • --dry-run -- Show what would be created without actually creating issues
  • --epic-only -- Create only the epic issue, not individual tasks
  • --no-epic -- Create only task issues, no parent epic

Decision Logic: Single vs Multiple Issues

Create a SINGLE issue when:

  • Feature has <= 3 implementation tasks
  • All tasks affect the same service/layer
  • Work is small enough for one PR (roughly < 1 day of work)
  • No PRD exists -- just a simple feature plan from conversation

Create an EPIC + task issues when:

  • Feature has > 3 implementation tasks
  • Tasks span multiple services or layers
  • A PRD exists with structured sections
  • Tasks could be assigned to different people or done in separate PRs
  • --epic-only or --no-epic flags override this logic

Process

Step 1: Find the Plan

  1. If path provided, read that file
  2. Else search docs/prd/*.md for most recent PRD
  3. Else look for feature plan in conversation context
  4. If nothing found, ask user to describe the feature or run /plan-feature or /prd first

Step 2: Parse & Classify

Extract from the plan:

  • Title: Feature name
  • Summary: Description
  • Acceptance Criteria: All AC items
  • Tasks: Implementation tasks grouped by layer
  • Out of Scope: Exclusions
  • Labels: Derive from affected services (see Label Mapping below)

Read the full file on GitHub · 297 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. yesterday First seen · 297 lines · 56 tokens per session scan A c37ff81a1ce5

Subscribe to this mod's changes

create-tasks is a skill published in the GitHub repository makigjuro/cloudstack-ai-plugins (1 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 1,834 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 2026-08-31.

Related

Other skills, from other repositories