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 ractive/hyalo --skill hyalo-madrgit clone --depth 1 https://github.com/ractive/hyaloWrote 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/ractive/hyalo/hyalo-madr)<a href="https://agentmods.dev/skills/ractive/hyalo/hyalo-madr"><img src="https://agentmods.dev/badge/skills/ractive/hyalo/hyalo-madr/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/ractive/hyalo/hyalo-madr"><img src="https://agentmods.dev/badge/skills/ractive/hyalo/hyalo-madr.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 | $0.00024 | $0.00174 |
| Opus 5.5 | $0.00010 | $0.00070 |
| Sonnet 5.5 | $0.00005 | $0.00035 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
hyalo-madr 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 1mo 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
Architecture decision records
Inspect hyalo config, hyalo types show adr, and hyalo madr --help.
Use hyalo lint --profile madr --format text for conformance and
hyalo madr toc --dry-run to inspect table-of-contents drift.
Keep numbering, status transitions, supersession links, and the configured ADR path consistent with the existing collection. Use the relevant command's help before creating or superseding records. Do not infer that an accepted decision is superseded from age alone. Apply requested metadata changes with Hyalo and prose with ordinary editing tools. After edits, lint affected records and preview the table of contents again.
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.
- 1mo ago First seen · 19 lines · 24 tokens per session scan A 48fa58ccf004
hyalo-madr is a skill published in the GitHub repository ractive/hyalo (27 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 174 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 2026-09-07.
Other skills, from other repositories
llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.
digest
Write one page about an article, blog post, news item, release note, or talk (slides) from its URL into this Scraps wiki, without dialogue - a short summary of what the source says, linked to the pages the wiki already has. Use this when the user hands over the URL of something they read or want to keep up with and…
learn
Learn a source together with the user and record only what they understood as a new page in this Scraps wiki. Explains the source with a diagram anchored on the pages the wiki already has, checks comprehension with questions, then writes one page from the points that passed; when understanding is not reached, nothing…
ingest
Create a new scrap from a source (prompt, URL, or arbitrary markdown), update cross-links in related scraps, and run a sanity check. Use this when the user wants to add a scrap, summarize an article, save synthesized content to the wiki, or file back a Q&A result.
query
Answer questions about the wiki by searching, reading, and synthesizing relevant scraps with [[Title]] citations. Use this when the user wants to query the wiki, ask what they have written about a topic, compare scraps, find related notes, or pull a synthesized overview from existing scraps.
planning-with-scratchpad
Use when user explicitly requests planning with a scratchpad, or asks for persistent tracking of a complex task that the human can browse visually. Backs planning files with the scratch CLI so a pad's files are registered and viewable.