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.
npx skills add Pixel-Process-UG/superkit-agents --skill task-decompositiongit clone --depth 1 https://github.com/Pixel-Process-UG/superkit-agentsWrote 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.
[](https://agentmods.dev/skills/pixel-process-ug/superkit-agents/task-decomposition)<a href="https://agentmods.dev/skills/pixel-process-ug/superkit-agents/task-decomposition"><img src="https://agentmods.dev/badge/skills/pixel-process-ug/superkit-agents/task-decomposition/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.
<a href="https://agentmods.dev/skills/pixel-process-ug/superkit-agents/task-decomposition"><img src="https://agentmods.dev/badge/skills/pixel-process-ug/superkit-agents/task-decomposition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.04216 |
| Opus 5.5 | $0.00030 | $0.01686 |
| Sonnet 5.5 | $0.00015 | $0.00843 |
| Haiku 4.5 | $0.00007 | $0.00422 |
Grade A, and why
task-decomposition 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Decomposition
Overview
Task decomposition breaks complex tasks into manageable, well-defined subtasks with clear dependencies, effort estimates, and parallelization opportunities. It covers hierarchical work breakdown structures (WBS), dependency graph construction, critical path analysis, task sizing, and identification of concurrent execution opportunities. Essential for planning multi-step implementations, project estimation, and autonomous loop task selection.
Announce at start: "I'm using the task-decomposition skill to break this work into a structured hierarchy with dependencies and estimates."
Trigger Conditions
- Complex task needs to be broken into subtasks
- Dependency mapping is needed between work items
- Effort estimation is required for planning
- Parallelization opportunities need to be identified
/decomposecommand invoked- Transition from planning skill for complex plans
- Autonomous loop needs task selection guidance
Phase 1: Scope Definition
Goal: Define clear boundaries for the decomposition.
- Define the overall deliverable and acceptance criteria
- Identify the boundaries (what is in scope, what is not)
- Determine the decomposition granularity level
- Identify stakeholders and their requirements
- Establish constraints (time, resources, dependencies)
Granularity Decision Table
| Context | Target Level | Typical Duration | Rationale |
|---|---|---|---|
| Autonomous loop (Ralph) | L3-L4 (Task/Subtask) | 15 min - 4 hours | ONE task per loop iteration |
| Sprint planning | L2-L3 (Story/Task) | 0.5-2 days | Sprint-sized work items |
| Roadmap planning | L0-L1 (Epic/Feature) | 2-8 weeks | High-level milestone tracking |
| Bug fix | L3-L4 (Task/Subtask) | 15 min - 2 hours | Focused, specific fixes |
Granularity Levels
| Level | Name | Typical Duration | Example |
|---|---|---|---|
| L0 | Epic | 2-8 weeks | "User authentication system" |
| L1 | Feature | 2-5 days | "OAuth2 login flow" |
| L2 | Story | 0.5-2 days | "Google OAuth provider integration" |
| L3 | Task | 1-4 hours | "Implement Google callback handler" |
| L4 | Subtask | 15-60 minutes | "Parse OAuth token response" |
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.
- 1mo ago First seen · 411 lines · 75 tokens per session scan A 2039d8615b68
task-decomposition is a skill published in the GitHub repository Pixel-Process-UG/superkit-agents (3 stars, last pushed 7mo ago), licensed MIT. It adds 75 tokens to every session and 4,216 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
outlook-calendar
A skill for managing Microsoft Outlook and Microsoft 365 calendar events through a connected account.
cron
Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/pause/resume/delete/run, and always pass --agent-id explicitly.
cron
A scheduling tool for running tasks at a future time or repeating them on a set schedule. It manages scheduled jobs such as reminders, checks, and reports.
to-tickets
Slice a spec or a ticket into tracer-bullet tickets with blocking edges, published through the repo's tracker: .specs/tickets/ .md by default.
to-spec
Turn the settled conversation into a spec (PRD), published through the repo's tracker: .specs/specs/ .md by default.
pm-init
Skill "pm-init" from wei63w/pm-manager, covering user input, outline, 1. scaffold, 2. lifecycle and type and 3. detect spec kit (required).