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 cpliakas/claude-code-engineering-leaders --skill decompose-requirementgit clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leadersWrote 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/cpliakas/claude-code-engineering-leaders/decompose-requirement)<a href="https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/decompose-requirement"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/decompose-requirement.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00992 |
| Opus 5 | $0.00017 | $0.00496 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
decompose-requirement 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 8d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decompose Requirement
Break a requirement into sequenced child items.
Input
$ARGUMENTS = title or description of the requirement to decompose.
Process
1. Handle Missing Input
If $ARGUMENTS is empty or contains no actionable description, prompt the user for the requirement to decompose. Present a single consolidated prompt:
- What requirement needs decomposition? — Paste the epic, story, or describe the requirement in a few sentences.
Do not proceed until the user has provided a requirement description.
2. Gather Context
- Read the project's CLAUDE.md for architecture, conventions, and domain context
- Scan for a roadmap or backlog file if one exists (Glob for roadmap*, backlog*, TODO*)
- Understand the domain well enough to identify meaningful vertical slices
3. Parse the Input
Determine the decomposition level:
- If the input describes an epic-level scope → decompose into stories (5-15 children)
- If the input describes a story-level scope → decompose into subtasks/tasks (2-8 children)
- If ambiguous, ask the user or infer from scope signals (breadth of outcomes, number of user roles involved, estimated delivery span)
4. Apply Decomposition Strategy
Use vertical slicing (mandatory) — each child delivers a thin, user-visible slice of functionality across all layers. Pick the best-fit strategy:
- Workflow steps: One child per step in a user workflow
- Business rules: One child per rule variation
- User roles: One child per role's interaction with the feature
- CRUD: One child per operation (when each has distinct value)
- Happy path first: Core flow as child 1, then edge cases and error handling
Explicitly avoid horizontal slicing (e.g., "build the database layer", "build the API", "build the UI") — these produce children with no standalone user value.
5. Sequence the Children
Order by priority, applying these criteria in order:
- Dependencies — what must exist before other children can start?
- Risk — what has the most technical uncertainty? Do it early.
- Value — front-load children that deliver user-visible value.
- Learning — children that resolve unknowns enable better estimates for later ones.
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.
- 8d ago First seen · 125 lines · 34 tokens per session scan A a5148adbb47a
decompose-requirement is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 992 once invoked, about $0.0002 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.