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 Casper-Studios/casper-marketplace --skill vertically-sliced-feature-modulesgit clone --depth 1 https://github.com/Casper-Studios/casper-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/casper-studios/casper-marketplace/vertically-sliced-feature-modules)<a href="https://agentmods.dev/skills/casper-studios/casper-marketplace/vertically-sliced-feature-modules"><img src="https://agentmods.dev/badge/skills/casper-studios/casper-marketplace/vertically-sliced-feature-modules/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/casper-studios/casper-marketplace/vertically-sliced-feature-modules"><img src="https://agentmods.dev/badge/skills/casper-studios/casper-marketplace/vertically-sliced-feature-modules.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 | $0.00035 | $0.00642 |
| Opus 5 | $0.00017 | $0.00321 |
| Sonnet 5 | $0.00007 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
vertically-sliced-feature-modules 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 4d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vertically Sliced Feature Modules
This skill organizes systems around capabilities that own their implementation end to end. Feature roots, nested subsystems, compositional entry points, and deliberately promoted shared boundaries keep cohesion high and dependency direction visible.
Reconstruct the current ownership graph and build/runtime boundaries before proposing folders. Treat the example trees as adaptable ownership shapes, not prescribed filenames.
Feature Ownership
A feature owns one user-visible or business capability end to end. Keep its complete private implementation closure under that owner, recursively, instead of scattering technical roles across global layers.
An entry implements or composes the operation its consumer needs. Keep setup options private when a caller only uses them to finish that operation. Do not introduce a forwarding wrapper or re-export barrel to manufacture an entry point.
Keep a readable private helper in its consumer. Extract a utility file when meaningful sans-I/O behavior needs a focused colocated test, even with one production consumer; this does not make the utility shared. Do not invent tests for trivial glue.
Features are isolated siblings and do not import one another. Callers and orchestrators compose feature entries. When multiple features need the same stable logic, promote it to a focused shared owner instead of making either feature the dependency of the other.
References
Read the reference that matches the ownership or boundary being changed.
- Keep each capability's technical roles together under its owning feature.
- Compose features through deliberate entries and one-way public boundaries.
- Promote shared ownership and package boundaries only when the system requires them.
- Preserve the existing ownership graph, contracts, and behavior during structural changes.
What ships with it
10 files 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.
- agents/openai.yaml 137 B
- LICENSE.txt 16 KB
- references/directory-structure.md 1.5 KB
- references/entry-points-and-composition.md 2.4 KB
- references/nested-subsystems.md 1.5 KB
- references/package-admission.md 1.8 KB
- references/public-contracts-and-import-direction.md 1.5 KB
- references/refactor-and-review.md 1.8 KB
- references/shared-code-promotion.md 1.2 KB
- references/test-placement.md 1.8 KB
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.
- 4d ago Changed · +8 lines · -40 tokens per session 2ba25c6d08ad
- 9d ago First seen · 34 lines · 75 tokens per session scan A cbcc94e876e5
vertically-sliced-feature-modules is a skill published in the GitHub repository Casper-Studios/casper-marketplace (12 stars, last pushed 4d ago), licensed MPL-2.0. It adds 35 tokens to every session and 642 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…