evyasys-create-subtask

evyasys-create-subtask is a skill for Claude Code from Evyasys-Software-Solutions/EvyaGovernance. It costs 130 tokens per session (1,274 once invoked), scanned A, original, MIT.

A planning tool that breaks user stories—requests for a software change—into small developer-ready tasks. It can also expand an epic, which is a larger piece of work containing several stories.

In plain words
What is it for?
Use it to create implementation and QA tasks for one story or a group of related stories, without writing code.
Why use it?
It turns broad requirements into manageable tasks while checking shared files, dependencies, risks, and acceptance criteria.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the evyasys plugin — 15 skills, 15 commands shipped together

Good fit Use it to create implementation and QA tasks for one story or a group of related stories, without writing code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evyasys-software-solutions/evyagovernance/evyasys-create-subtask
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.

Any agent
npx skills add Evyasys-Software-Solutions/EvyaGovernance --skill evyasys-create-subtask
Clone the repo
git clone --depth 1 https://github.com/Evyasys-Software-Solutions/EvyaGovernance

Made for: Claude Code.

Or install evyasys, the plugin that ships this one along with the rest of its 15 skills, 15 commands.

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 evyasys-create-subtask

README.md
[![agentmods](https://agentmods.dev/badge/skills/evyasys-software-solutions/evyagovernance/evyasys-create-subtask/github.svg)](https://agentmods.dev/skills/evyasys-software-solutions/evyagovernance/evyasys-create-subtask)
Your own site
<a href="https://agentmods.dev/skills/evyasys-software-solutions/evyagovernance/evyasys-create-subtask"><img src="https://agentmods.dev/badge/skills/evyasys-software-solutions/evyagovernance/evyasys-create-subtask/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 evyasys-create-subtask

Your own site · 80×15
<a href="https://agentmods.dev/skills/evyasys-software-solutions/evyagovernance/evyasys-create-subtask"><img src="https://agentmods.dev/badge/skills/evyasys-software-solutions/evyagovernance/evyasys-create-subtask.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,274 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 $0.00130 $0.01274
Opus 5 $0.00065 $0.00637
Sonnet 5 $0.00026 $0.00255
Haiku 4.5 $0.00013 $0.00127

Measured 10d ago against content hash 56f89e01516d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

evyasys-create-subtask 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (hooks.js), 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.

skills/evyasys-create-subtask/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: evyasys-create-subtask

/evyasys:CreateSubtask decomposes one story or an entire epic's worth of stories in a single run.


What it does

  1. Resolves inputs — expands epic IDs to all their story IDs; deduplicates
  2. Loads all story files in one batch — extracts ACs and Impacted Areas per story
  3. Builds shared knowledge base once — quality-gate docs from .evyasys/docs/ (or derived from codebase if docs absent); union of all domain docs based on all stories' flags
  4. Unified code analysis — unions all impacted areas, reads each file once; builds shared technical inventory
  5. Cross-story dependency analysis — shared files, shared infrastructure tasks, sequence requirements, parallelism opportunities, merge-conflict risk
  6. Single Gate — consolidated plan table (all stories, strategy, task count, cross-story notes) — one approval for the whole batch
  7. Drafts all subtasks — functional headlines + business rules + AC Coverage Map + Data Flow + Error & Recovery + deep Technical Guidance per task, using shared context (no re-reading); no code in any task; maximum 5 tasks per story (4 implementation + 1 QA)
  8. Shared task handling — tasks serving multiple stories written once in the owning story; reference entries in others
  9. Cross-story consistency check — every AC covered, no contradictions across shared files, QA regression rows cover cross-story touchpoints
  10. Saves and syncs (progressive) — two modes:
    • Story input: each story is saved locally → PM-synced → notified immediately before moving to the next
    • Epic input: all stories in the epic are saved locally first, then PM-synced together, then a single notification fires for that epic; the next epic starts immediately after
  11. Playwright spec scaffolding — one spec file per story from QA test scenarios
  12. Notificationssubtasks-batch-created fires per story (story mode) or per epic (epic mode) — never waits for the entire batch to complete

Read the full file on GitHub · 105 lines

Files

What ships with it

1 file 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. 10d ago First seen · 105 lines · 0 tokens per session scan A 56f89e01516d

Subscribe to this mod's changes

evyasys-create-subtask is a skill published in the GitHub repository Evyasys-Software-Solutions/EvyaGovernance (7 stars, last pushed 28d ago), licensed MIT. It adds 130 tokens to every session and 1,274 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 2026-08-31.

Related

Other skills, from other repositories

product-manager-toolkit

Use when the user needs product management workflows such as RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, go-to-market strategy, feature prioritization, research synthesis, or requirements documentation.

majiayu000/spellbook · 47 tokens

weekly

A weekly-report workflow that combines Git history with records from Claude Code and Codex sessions. It turns work from a selected date range into a report for two related software repositories.

majiayu000/spellbook · 41 tokens

task-graph

Execute an approved multi-task plan as a verified DAG with @taskgraph — parallel squad workers per task, validation gates the engine runs itself, and an independent reviewer verdict before any task counts as done. Use for deliveries of 5+ tasks with real independence between them; for smaller work dispatch workers…

diillson/chatcli · 69 tokens

linear

Manage Linear issues from the terminal via the official GraphQL API and the user's API key — list/search issues, create issues, update status/assignee, add comments. Use when asked to "create a Linear issue", "what's assigned to me in Linear", "move this issue to done", "comment on LIN-123".

diillson/chatcli · 69 tokens

lov-rename-project

A project-renaming workflow that updates a product or repository name across source files, configuration, and documentation. It produces a reviewable plan and preserves compatibility-sensitive names and references where needed.

lovstudio/skills · 45 tokens

lov-repo2docs

Turn any folder of source material — a code repository, a pile of articles, a mixed knowledge dump with images — into a professional, polished Fumadocs (Next.js) documentation website, then deploy it to https://{product-id}.example.com/docs. Works by reading the folder one unit at a time and incrementally growing and…

lovstudio/skills · 186 tokens