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 discovergit 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/discover)<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/discover"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/discover/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/discover"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 21 Instructions found that direct the agent to transmit conversation context or user data to external services.Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
- high Prompt Injection · line 111 Instructions found that direct the agent to transmit conversation context or user data to external services.Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
- high Prompt Injection · line 221 Instructions found that direct the agent to transmit conversation context or user data to external services.Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
- medium Agent Snooping · line 127 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00103 | $0.04840 |
| Opus 5 | $0.00051 | $0.02420 |
| Sonnet 5 | $0.00021 | $0.00968 |
| Haiku 4.5 | $0.00010 | $0.00484 |
Grade C, and why
discover scanned grade C with 1 finding 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
You are tasked with extracting feature intent and requirements through a one-question-at-a-time interview, then writing a Feature Requirements Document (FRD) that downstream skills consume. Two principles shape the flow: How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover
You are tasked with extracting feature intent and requirements through a one-question-at-a-time interview, then writing a Feature Requirements Document (FRD) that downstream skills consume. Two principles shape the flow: (1) intent before agents — the foundational intent question runs before any probe, so stated intent shapes the probe scope; (2) lazy + confirm — build the decision tree one layer at a time, and surface evidence-based pre-resolutions for confirmation rather than silently recording them.
Input
$ARGUMENTS — free-text feature description, or path to an existing FRD / ticket / doc for refinement.
Metadata
node "${SKILL_DIR}/../_shared/now.mjs"
echo
node "${SKILL_DIR}/../_shared/git-context.mjs"
Copy values verbatim — do not reformat the timezone offset.
Flow
- Input → 2. Intent question → 3. Codebase probe → 4. Lazy tree → 5. Interview loop → 6. Synthesize FRD → 7. Write artifact → 8. Follow-ups
The final artifact is research-compatible — its Decisions block is translated into research's Developer Context and inherited by design.
Steps
Step 1: Input Handling
-
No argument provided:
I'll capture feature intent into an FRD. Provide one of: `/skill:discover [free-text feature description]` — fresh interview, write a new FRD `/skill:discover [existing artifact path]` — refine an existing FRD/ticket/doc via fresh interviewThen wait for input.
-
Detect input shape — parse the input:
- If the argument is an existing file path (resolves to a readable
.mdunder.rpiv/artifacts/, or any path the user mentions for refinement context), read it FULLY using the Read tool WITHOUT limit/offset. Treat its content as baseline context — the interview surfaces gaps, missing requirements, and unstated assumptions relative to what's already documented. - Plain free-text input → fresh-feature mode: the entire argument is the free-text feature description.
- If the argument is an existing file path (resolves to a readable
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 · 239 lines · 103 tokens per session scan C eaff3a5f82a2
discover is a skill published in the GitHub repository juicesharp/rpiv-mono (773 stars, last pushed 2d ago), licensed MIT. It adds 103 tokens to every session and 4,840 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). 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…