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/etr/groundwork/vertical-slicenpx skills add etr/groundwork --skill vertical-slicegit clone --depth 1 https://github.com/etr/groundworkWhat 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 | $0.00041 | $0.01029 |
| Opus 5 | $0.00020 | $0.00515 |
| Sonnet 5 | $0.00008 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
vertical-slice 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vertical Slice
Overview
Build a feature as a sequence of thin vertical slices. Each slice cuts through the full stack — UI → logic → data — and delivers exactly one observable behavior, kept behind a feature flag until it is complete and tested.
Core principle: thin vertical slice (defined in ${CLAUDE_PLUGIN_ROOT}/references/engineering-principles.md). The opposite is horizontal building — finishing the whole data layer, then the whole logic layer, then the whole UI. Horizontal work integrates last, which means every integration risk surfaces at the end, all at once, when there is no budget left to absorb it. Vertical slices integrate first and continuously: each slice proves the stack connects before you build the next one.
A slice is the unit of progress. Finish one — flagged, end-to-end, tested, committed — before starting the next. Cutting a feature into sliced tasks happens during planning ([[create-tasks]]); this skill governs building each slice. See [[work-on]] for driving the work item end-to-end and [[test-driven-development]] for the inner loop of each slice.
When to Use
- A feature that touches more than one layer (endpoint + service + table; component + handler + store)
- Any work big enough to tempt "I'll build all the models first, then wire them up"
- Work that must ship incrementally or be safe to pause and resume
Skip for a change confined to one layer, or a fix small enough that there is nothing to slice.
Process
1. Cut the feature into thin slices
List slices, each delivering one behavior a user or caller can observe. "User sees their order total" is a slice; "build the orders table" is not — it is a layer. If a slice can't be stated as an observable behavior, it is horizontal; re-cut it. Prefer the thinnest slice that still demonstrates the stack end-to-end (a single happy path through every layer beats a complete-but-disconnected layer).
2. Put the flag in first
Add the feature flag before building the slice, defaulting off. The slice's new path lives behind it. This keeps main shippable at every commit and lets unfinished slices merge without exposing half-built behavior.
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.
- 2d ago First seen · 71 lines · 41 tokens per session scan A 24ec0e5836d9
vertical-slice is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 21d ago), licensed MIT. It adds 41 tokens to every session and 1,029 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.
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…