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 agentmods add skills/aigentive/ralphx/task-decompositionnpx skills add aigentive/RalphX --skill task-decompositiongit clone --depth 1 https://github.com/aigentive/RalphXWhat 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 | $0.00014 | $0.01280 |
| Opus 5 | $0.00007 | $0.00640 |
| Sonnet 5 | $0.00003 | $0.00256 |
| Haiku 4.5 | $0.00001 | $0.00128 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Decomposition Skill
This skill helps break down complex features into atomic, independently implementable tasks.
Core Principles
1. Right-Sized Tasks
Each task should be:
- Completable in 1-4 hours of focused work
- Independently testable
- Shippable on its own (even if feature is incomplete)
- Clear enough that someone else could pick it up
2. Vertical Slices
Prefer vertical slices over horizontal layers:
Good (Vertical):
- "Add login button that shows login modal"
- "Implement password validation on login form"
- "Add remember me checkbox to login"
Avoid (Horizontal):
- "Create all auth UI components"
- "Write all auth business logic"
- "Add all auth tests"
3. Dependency Minimization
Order tasks to minimize blocking:
- Foundation tasks (types, interfaces, infrastructure)
- Core functionality (main features)
- Enhancements (polish, edge cases)
- Integration (connecting pieces)
Decomposition Patterns
Pattern: Feature -> Tasks
Feature: "Dark mode support" Decomposition:
- Define color tokens (CSS variables)
- Create theme context
- Add theme toggle component
- Update navigation to use theme colors
- Update cards to use theme colors
- Update modals to use theme colors
- Persist theme preference
- Detect system preference
Pattern: CRUD -> Tasks
Feature: "Task comments" Decomposition:
- Add comments field to task entity
- Create comment repository
- Add create comment command
- Add list comments command
- Create comment list component
- Create comment input component
- Integrate comments into task detail view
Pattern: Integration -> Tasks
Feature: "Connect to external API" Decomposition:
- Define API response types
- Create API client module
- Implement authentication
- Add fetch method for resource
- Create loading states
- Add error handling
- Implement retry logic
- Add caching layer
Pattern: Targeted Testing
Every plan decomposition MUST include a testing strategy that scales with the implementation — not blanket full-suite runs at every gate.
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.
- yesterday First seen · 177 lines · 14 tokens per session scan A 1ea4b1830be9
task-decomposition is a skill published in the GitHub repository aigentive/RalphX (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 1,280 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…