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 designgit 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)<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/design"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/design/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"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/design.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 | $0.00121 | $0.08696 |
| Opus 5 | $0.00060 | $0.04348 |
| Sonnet 5 | $0.00024 | $0.01739 |
| Haiku 4.5 | $0.00012 | $0.00870 |
Grade A, and why
design 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 11d 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 — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design
You are tasked with designing how code will be shaped for a feature or change. This iterative variant decomposes features into vertical slices and generates code slice-by-slice with developer micro-checkpoints between slices. The design artifact feeds directly into plan, which sequences it into phases.
Input
$ARGUMENTS takes two forms:
- Start — path to a research artifact (
.rpiv/artifacts/research/*.md) or a solutions artifact (.rpiv/artifacts/solutions/*.md). - Resume —
--resume <path-to-.rpiv/artifacts/designs/*.md>. The design must havestatus: in-progress; the artifact, not a compaction summary, is authoritative for locked slices and the next pending slice.
Metadata
node "${SKILL_DIR}/../_shared/now.mjs"
echo
node "${SKILL_DIR}/../_shared/git-context.mjs"
echo
echo "### recent (read only in case of empty user input)"
echo "recent research:"
node "${SKILL_DIR}/../_shared/list-recent.mjs" .rpiv/artifacts/research 4
echo
echo "recent solutions:"
node "${SKILL_DIR}/../_shared/list-recent.mjs" .rpiv/artifacts/solutions 4
Copy values verbatim — do not reformat the timezone offset.
Flow
- Input → 2. Research → 3. Dimension sweep → 4. Checkpoint → 5. Decompose → 6. Generate slices (code + Success Criteria) → 7. Finalize → 8. Present artifact → 9. Handle follow-ups
The final artifact is plan-compatible: ## Slices boundaries become phase boundaries 1:1, and Success Criteria pass through unchanged. Post-finalization code + coverage review runs inside /skill:plan Step 4.
Steps
Step 1: Input Handling
When this command is invoked:
- Resume mode first — when
$ARGUMENTScontains--resume:- Parse exactly one design artifact path after the flag. If it is missing, outside
.rpiv/artifacts/designs/, unreadable, or notstatus: in-progress, print the specific error and stop. - Read the design artifact FULLY. Extract Decisions, Architecture, Slices, Verification Notes, Developer Context, and Design History.
- Find the first Design History entry still marked
pending. Treat every earlierapprovedentry and its persisted code fences/Success Criteria as locked; never reconstruct them from conversation or a compaction summary. - Read the current source files for that pending slice FULLY, plus Architecture entries for files the slice shares with locked predecessors.
- Skip Steps 2–5. Enter Step 6 at the pending slice. If no slice is pending, go directly to Step 7.
- Parse exactly one design artifact path after the flag. If it is missing, outside
What ships with it
1 file 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.
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.
- 11d ago First seen · 488 lines · 121 tokens per session scan A f2f5cc16890a
design is a skill published in the GitHub repository juicesharp/rpiv-mono (779 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 8,696 once invoked, about $0.0006 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…