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 juicesharp/rpiv-mono --skill slicegit clone --depth 1 https://github.com/juicesharp/rpiv-monoWrote 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/juicesharp/rpiv-mono/slice)<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/slice"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/slice/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/juicesharp/rpiv-mono/slice"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/slice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00154 | $0.02963 |
| Opus 5 | $0.00077 | $0.01482 |
| Sonnet 5 | $0.00031 | $0.00593 |
| Haiku 4.5 | $0.00015 | $0.00296 |
Grade A, and why
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 5d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slice
You decompose a feature into independent vertical slices and write a slice map. You do not design, plan phases, write implementation steps, or self-review — design-slice fills each slice in next. A research artifact grounds the cut (every slice's Draws on: cites real file:lines from it); you confirm the decomposition with the developer before writing.
Input
$ARGUMENTS takes two forms:
- Fresh — a path to a
.rpiv/artifacts/research/*.mdartifact, positional or as--research <path>(the flag form is how the build workflow dispatches it — equivalent, same input). Decompose from scratch via Steps 1–6, grounded in that research. The research artifact is required: if the argument is missing, empty, or not a research path, print an error and stop — it's a dispatch error (the workflow runsresearchbeforeslice). - Re-slice (the re-slice loop) —
--slices <map-path> --slice-verdicts <verdict-path> … [--slice-check <structural-verdict-path> …](the--slice-verdictsand--slice-checkflags repeat). Re-cut the existing slice map to clear the failures its verdicts name. Recognize this form by the--slicesflag and follow Re-slice mode below — NOT the fresh Steps (no confirm).--slice-checkcarries the deterministic structural findings (dependency cycles, dropped coverage units, unbackedfile:linecitations) — treat them exactly like a verdict's findings; they are the un-gameable floor and MUST all be cleared.
Metadata
node "${SKILL_DIR}/../_shared/now.mjs"
echo
node "${SKILL_DIR}/../_shared/git-context.mjs"
Copy values verbatim — do not reformat the timezone offset. <iso> is the first tab-separated field on line 1; <slug> is the second.
What a slice is
A vertical slice is a coherent, independently-buildable capability that cuts through whatever layers it needs (data → logic → surface). Good slices are:
- Independent — designable and reviewable on their own; minimize cross-slice coupling.
- Vertical — a user- or system-meaningful capability, never a horizontal layer ("all the types", "all the tests").
- Right-sized — chewable by a single
design-slicepass each: one coherent architecture decision resting on a bounded, fully-cited real footing (thefile:lines the design must read).design-slicedoes NO discovery, so under-citing a slice'sDraws ondoes not make it smaller — it starves the design pass. Not measured by clock time. - Honest about dependencies — when slice B genuinely needs slice A first, record it in
deps. Keep real deps rare; if everything depends on everything, the cut is wrong. - Complete and conserved — the brief decomposes into ID'd
coverage:units, each claimed by some slice'scovers:. The set is frozen at the first cut: a re-cut may redistribute units across slices, never drop one to shrink a slice.
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.
- 5d ago Changed 661738383027
- 9d ago First seen · 162 lines · 154 tokens per session scan A ecea99e08277
slice is a skill published in the GitHub repository juicesharp/rpiv-mono (765 stars, last pushed today), licensed MIT. It adds 154 tokens to every session and 2,963 once invoked, about $0.0008 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…