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 Tenon-Net/TenonAdmin --skill visual-ralphgit clone --depth 1 https://github.com/Tenon-Net/TenonAdminWrote 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/tenon-net/tenonadmin/visual-ralph)<a href="https://agentmods.dev/skills/tenon-net/tenonadmin/visual-ralph"><img src="https://agentmods.dev/badge/skills/tenon-net/tenonadmin/visual-ralph/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/tenon-net/tenonadmin/visual-ralph"><img src="https://agentmods.dev/badge/skills/tenon-net/tenonadmin/visual-ralph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.00443 |
| Opus 5.5 | $0.00014 | $0.00177 |
| Sonnet 5.5 | $0.00007 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
visual-ralph 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 today.
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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Ralph
The name is retained for compatibility. Use this skill for frontend work with a visual target; perform the work with ordinary repository editing, capture, comparison, and verification tools.
Repository-wide authority, state, and verification rules live in AGENTS.md.
Workflow
- Inspect the frontend stack, route, tokens, reusable components, screenshot tooling, and relevant commands.
- Establish the reference, viewport, route and state, visible interactions, and exclusions. For a live URL, record its source and authorized scope. For a generated concept, use
$imagegenwith the requested dimensions, text, visual constraints, and feasible UI details, then copy the selected artifact into.omx/artifacts/visual-ralph/<slug>/reference.png. - Treat a user-specified reference, or a reference already authorized for the current task, as approved. Ask only when an unresolved design choice would materially change the result; do not repeat an approval already given.
- Implement with existing components and tokens. Capture the same viewport and state, compare it with the reference, turn observed differences into the next edit, and repeat until the requested match is reached or a concrete blocker remains.
- Use image inspection and pixel-diff overlays when they improve comparison. Preserve the reference, final screenshot, reproduction command, and useful diff artifacts.
- Run the repository's applicable build, lint, tests, and accessibility checks for the changed surface.
Quality and stopping
Honor an explicit pixel-diff or similarity threshold from the user. Otherwise judge completion from visible layout, typography, color, spacing, states, interactions, and the user's stated fidelity; a model-generated score is supporting judgment, not an objective quality fact.
Finish when the result reproduces at the recorded viewport and state, relevant checks pass, and remaining visible differences are documented. Encode reusable values in the repository's existing token or component system when the implementation actually introduces them.
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.
- today First seen · 28 lines · 34 tokens per session scan A a1f26713c70c
visual-ralph is a skill published in the GitHub repository Tenon-Net/TenonAdmin (41 stars, last pushed 14d ago), licensed Apache-2.0. It adds 34 tokens to every session and 443 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-07.
visual-ralph compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| visual-ralphTenon-Net/TenonAdmin | Skill | 41 | 14d ago | Apache-2.0 | A | 34 | Codex |
| csharp-dotnetericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 89 | Claude Code, Codex |
| antdant-design/ant-design-cli | Skill | 261 | 2d ago | MIT | A | 69 | Claude Code |
| adminforth-i18n-staticdevforth/adminforth | Skill | 392 | yesterday | MIT | A | 44 | Claude Code |
| bwfc-migrationFritzAndFriends/BlazorWebFormsComponents | Skill | 455 | 4mo ago | MIT | A | 115 | Claude Code, Codex |
| webforms-migrationFritzAndFriends/BlazorWebFormsComponents | Skill | 455 | 4mo ago | MIT | A | 63 | Claude Code, Codex |
| migration-standardsFritzAndFriends/BlazorWebFormsComponents | Skill | 455 | 4mo ago | MIT | A | 79 | Claude Code, Codex |