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 design-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/design-slice)<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/design-slice"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/design-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/design-slice"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/design-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 | $0.00107 | $0.01551 |
| Opus 5 | $0.00053 | $0.00776 |
| Sonnet 5 | $0.00021 | $0.00310 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade A, and why
design-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 12d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Slice
You design one vertical slice from a slice map, in isolation, and write its design doc. One pass. You do not decompose (the slice is already cut), implement, or self-review — the workflow's grade panel judges your output. You may ask the user only when a genuine design fork blocks this slice.
Input
$ARGUMENTS — <slices-path> Slice N: <title>:
- The first token is the path to a slice map under
.rpiv/artifacts/slices/. - The remainder (
Slice N: <title>) names the single slice to design. ParseNfromSlice (\d+). --upstream <path>(repeats, optional) — a direct dependency's per-slice design doc, injected by the design fanout once that dependency completes. Read each one's## Key Interfaces(the decided contract this slice builds on) and## Notes / Deferred(to detect an undecided fork). Absent ⇒ this slice is a root (no upstream dependency).
Design only that slice. Respect its Out of scope — anything there belongs to another slice's design.
If the slices path is missing or Slice N can't be parsed, print an error and stop — it's a dispatch error.
Metadata
node "${SKILL_DIR}/../_shared/now.mjs"
echo
node "${SKILL_DIR}/../_shared/git-context.mjs"
Copy values verbatim. <iso> is the first tab-separated field; <slug> is the second.
Steps
- Read the slice map fully and locate the
## Slice N:section — its Scope, Draws on, Depends on, Out of scope. - Read the slice's footing: the
Draws onreferences (research sections + the sourcefile:lines it rests on). Read those files fully. This is targeted — read what the slice names, do not run discovery/analysis subagents. - Read each
--upstreamdependency design (if any were passed): from each, read its## Key Interfaces(the decided contract this slice depends on — build against it, do not redesign it) and its## Notes / Deferred. If a contract this slice depends on is still an undecided fork there (the dependency parked options rather than deciding), escalate — see Step 5. Read only the direct upstreams you were handed; do not chase their transitive dependencies (synthesize reconciles the rest). - Design this slice — decide its shape and record:
- Approach — the architecture decision(s) for this slice and why.
- File map — each file to add/change and what changes (
path — add|change — what). - Key interfaces — the types/signatures/exports the slice introduces or touches.
- Integration points — where this slice wires into existing code (and into sibling slices it depends on, by file/symbol — referencing the real shapes from the upstream
## Key Interfaces). - Success criteria — concrete
- [ ]checks that prove the slice works.
- Resolve ambiguity: decide from the slice map, the upstream designs, research, and code wherever you can. Use
ask_user_question(2–4 concrete options, one at a time) ONLY when you can't settle it from those inputs — either a genuine design fork within this slice, or a contract this slice depends on is still an undecided fork in an upstream's## Notes / Deferred. Do not ask the user to approve the finished design — the grade panel owns that.Headeris capped at ≤16 characters (MAX_HEADER_LENGTH = 16— longer values are rejected).
- Write the design doc (below),
status: ready. - Print the path, then a one-line summary:
Slice N design: <k> files, <m> success criteria.
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.
- 12d ago First seen · 116 lines · 107 tokens per session scan A e6d60e181c5a
design-slice is a skill published in the GitHub repository juicesharp/rpiv-mono (780 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 1,551 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 2026-08-30.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…