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 wix/skills --skill rp-source-evidencegit clone --depth 1 https://github.com/wix/skillsWrote 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/wix/skills/rp-source-evidence)<a href="https://agentmods.dev/skills/wix/skills/rp-source-evidence"><img src="https://agentmods.dev/badge/skills/wix/skills/rp-source-evidence/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/wix/skills/rp-source-evidence"><img src="https://agentmods.dev/badge/skills/wix/skills/rp-source-evidence.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 | $0.00020 | $0.00465 |
| Opus 5 | $0.00010 | $0.00233 |
| Sonnet 5 | $0.00004 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
rp-source-evidence 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 9d 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.
What it actually says
Source evidence
Load this resource only after project context is valid and when source evidence is missing or stale. It owns extraction and generated planning artifacts; it does not implement the clone.
Read references/workflow.md, references/extraction-schema.md,
references/interaction-runtime-contract.md,
references/layout-blueprint-contract.md,
references/control-and-visual-fidelity-contract.md, and
references/ui-normalization-contract.md.
Run site-clone.mjs using the active mode and refresh canonical docs/site-clone/
artifacts before generating new ones. Emit stage-level progress. Browser extraction is
mandatory: capture source screenshots at required viewports and use browser evidence for
shared chrome and first-viewport content, not SEO metadata or an HTML-only fallback.
Resolve the home page before capture. This resource implements home scope only; do not accept explicit additional URLs or silently run the previous multi-page artifact flow. An ambiguous or unreachable home identity is a global blocker with an exact unblock action.
Capture observations, then project and freeze the source-of-truth tree under
docs/site-clone/extraction/<capture-id>/: page resolution/capture, foundation, metadata,
shared chrome, recursively owned section/component specs, gap records, spec index, and the
immutable extraction manifest. Write extraction/latest.json as the stable pointer. The
builder receives only the manifest-derived build plan, never observations or the source.
Preserve evidence rather than inference: source @font-face tuples and files, exact logo
variants/rendered dimensions, structured navigation hierarchy, visible hero text, repeaters,
core interaction scenes and timelines, background-media roles, composition geometry, and
responsive behavior. Safe probing is public/unauthenticated and presentation-only; block and
record navigation, forms, commerce/account actions, mutation, and unclassified controls.
Local gaps never block unrelated units. Use at most two distinct targeted recovery attempts, then freeze the affected dependency closure provisionally with explicit assumptions and omissions. Only a global blocker prevents manifest freeze. Once the manifest passes integrity verification, return to the root supervisor so it can load implementation instructions.
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.
- 9d ago First seen · 43 lines · 20 tokens per session scan A 3a07c8d07bf8
rp-source-evidence is a skill published in the GitHub repository wix/skills (29 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 465 once invoked, about $0.0001 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…