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 jdevalk/specification.website --skill specification-websitegit clone --depth 1 https://github.com/jdevalk/specification.websiteWrote 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/jdevalk/specification.website/specification-website)<a href="https://agentmods.dev/skills/jdevalk/specification.website/specification-website"><img src="https://agentmods.dev/badge/skills/jdevalk/specification.website/specification-website/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/jdevalk/specification.website/specification-website"><img src="https://agentmods.dev/badge/skills/jdevalk/specification.website/specification-website.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 | $0.00127 | $0.02136 |
| Opus 5.5 | $0.00051 | $0.00854 |
| Sonnet 5.5 | $0.00025 | $0.00427 |
| Haiku 4.5 | $0.00013 | $0.00214 |
Grade A, and why
specification-website 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 yesterday.
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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- yesterday Changed 7070db105de9
- 16d ago Changed dafb93041d83
- 21d ago Changed 11f49d7f71f6
- 22d ago Changed d99762f631d6
- 1mo ago Changed 4aa0455f9b9d
- 1mo ago First seen · 159 lines · 127 tokens per session scan A bba469a59dfc
specification-website is a skill published in the GitHub repository jdevalk/specification.website (880 stars, last pushed yesterday), with no licence file. It adds 127 tokens to every session and 2,136 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
cocktails-from-my-bar
Turn a photo of a home bar, or a list of bottles, into the cocktails you can make right now using cocktail.glass.
substitute-an-ingredient
Decide whether a cocktail ingredient can be swapped for one on hand, and find adjacent drinks with cocktail.glass.
anvil-find-keywords
A research procedure for finding and evaluating game-related search terms across several sources. It checks search results and user intent, then records whether each idea should be pursued, rejected, or reviewed later.
anvil-new-article
A tool that turns supplied material into MDX article pages for AnvilWiki, a wiki site built from structured content files. It fills in page details and checks that the pages follow the site’s rules.
anvil-batch-articles
A batch article generator for creating many AnvilWiki MDX pages from a list of keywords. MDX is Markdown with added components and structured fields for a website.
anvil-update-codes
A tool for updating a game wiki’s reward-code page from codes supplied by the user. It keeps working and expired codes in structured page data.