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 NVZver/claude-marketplace --skill decomposegit clone --depth 1 https://github.com/NVZver/claude-marketplaceWrote 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/nvzver/claude-marketplace/decompose)<a href="https://agentmods.dev/skills/nvzver/claude-marketplace/decompose"><img src="https://agentmods.dev/badge/skills/nvzver/claude-marketplace/decompose/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/nvzver/claude-marketplace/decompose"><img src="https://agentmods.dev/badge/skills/nvzver/claude-marketplace/decompose.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 | $0.00093 | $0.01193 |
| Opus 5 | $0.00046 | $0.00596 |
| Sonnet 5 | $0.00019 | $0.00239 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
decompose 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 9d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace. On load, print first:
=============== [manager/skills/decompose/SKILL.md] [manager] ===============
Decompose
Decompose a pitch into epics ready for the LSA build cycle. Dispatches the project-manager agent with the pitch, runs the epic-approval gate, and on approval invokes the staged lsa:discover handoff with the agent's first-epic seed. Does not contain decomposition logic — that lives in the agent and ../../knowledge/epic-decomposition.md. The dispatch → gate → re-render loop is the shared contract at ../../knowledge/roadmap-orchestration.md.
Goal
Turn an approved pitch into a list of independently-shippable epics — each keyed by a stable slug (<feature-slug>/<short-kebab-scope>, never a global ordinal) and scoped to one LSA cycle — and stage the first epic into discovery, without the user manually decomposing the pitch or invoking the agent directly. The slug is assigned once here and is immutable through commit and PR per ../../knowledge/epic-decomposition.md §"Epic key".
Input
- A pitch slug or path as the skill argument (e.g.
manager:decompose onboarding-checklistor a path under${specs_root}/pitches/). If no argument is given, the agent decomposes the highest-priority backlog pick (per../../agents/project-manager.mdStep 8). specs_rootfrom.lsa.yamlat repo root (defaults per../../../lsa/knowledge/conventions.md§".lsa.yamldefaults"). Used to resolve${specs_root}/...paths.
Steps
- Dispatch the project-manager and run the epic-approval gate — per the shared contract. Dispatch the
project-manageragent with an explicit intent carrying the pitch (intent: decompose <pitch>) and run its returned gates per../../knowledge/roadmap-orchestration.md. The agent reads the pitch, decomposes it per../../knowledge/epic-decomposition.md, and returns the full epic list as a pending gate — approve (recommended default) / reject / adjust (../../agents/project-manager.mdStep 10). This skill delivers the list and presents the gate via an interactive confirmation gate (AskUserQuestionin Claude Code); on reject/adjust it sends the feedback back and re-gates the fresh epic list. Observable result: epic list delivered; approve/reject/adjust gate resolved by the user.
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.
- 9d ago First seen · 59 lines · 93 tokens per session scan A 8578a2e64884
decompose is a skill published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 15d ago), licensed MIT. It adds 93 tokens to every session and 1,193 once invoked, about $0.0005 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
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
predictable-revenue
Build a scalable outbound B2B sales machine with specialized roles (SDR, AE, CSM). Use when the user mentions "outbound sales", "Cold Calling 2.0", "cold email sequences", "sales pipeline", "SDR process", "sales development", "build an outbound sales team", or "fill my pipeline". Also trigger when setting up a B2B…
team-topologies
Organize business and technology teams for fast flow using Skelton & Pais's "Team Topologies". Use when the user mentions "team topologies", "Conway's law", "platform team", "stream-aligned team", "team boundaries", "cognitive load", "how should we split teams", "who owns this service", "team dependencies", or…
glab
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
foreman
The one entrance to Foreman — say what you want in plain language and this routes it. Covers the six things Foreman does to a project: add work, show status, correct work, check the roadmap, pick work, or reconcile and pick. It owns no flow of its own; each intent is handed to the skill that already implements it, so…
missive
Invoke only when spawning a quest from a GitHub issue reference. Fetches GitHub issue context for quest spawning. Parses issue references, retrieves structured data via gh, and produces branch suggestions and PR keywords. Used standalone or as input to quest orchestration.