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 boykush/scraps --skill digestgit clone --depth 1 https://github.com/boykush/scrapsWrote 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/boykush/scraps/digest)<a href="https://agentmods.dev/skills/boykush/scraps/digest"><img src="https://agentmods.dev/badge/skills/boykush/scraps/digest/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/boykush/scraps/digest"><img src="https://agentmods.dev/badge/skills/boykush/scraps/digest.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 | $0.00125 | $0.01182 |
| Opus 5.5 | $0.00050 | $0.00473 |
| Sonnet 5.5 | $0.00025 | $0.00236 |
| Haiku 4.5 | $0.00013 | $0.00118 |
Grade A, and why
digest 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Digest
Take the URL of an article or talk and write one page about that source, start to finish, without dialogue.
Digest is for keeping up with incoming material. The page records what the source says and where it touches what the wiki already holds, so the user can take it in quickly. It does not claim the user understood it; that is learn's job. The subject is therefore always the source itself (who said what, and where), never a term or a tool. A page named after a concept stands for something the user understood, and only learn writes those.
Do not ask questions along the way. Where judgment could go either way, decide by the rules here and record the decision in the report. If the rules do not decide it, leave that part unwritten and report it. The user can read a diff and fix it, but an understanding that was silently added goes unnoticed.
Scope
Digest handles URLs where the page's subject is the source itself: technical blog posts, news articles, talks, release notes, and explanatory pages of official documentation.
When the URL points at the official site of a tool or product, the subject is the thing rather than the source (the Scalafix site becomes a page named Scalafix). Hand those to learn, along with any URL you cannot classify.
Boundaries
- Do not change existing pages at all. Connect only through links from the new page; backlinks are computed automatically. Turning mentions in existing pages into links needs a judgment of context (some languages have no word boundaries), which
learnmakes together with the user in its step 6. - One page per source. Given several URLs, write them one at a time and never merge them into one page.
- Do not also create pages for the concepts the source mentions.
- Do not create pages for people, organizations, or publications. Without an existing page, write them as plain text.
- Do not create tags. If no existing tag fits, shorten the tag line.
- Do not widen the work into tidying or auditing the wiki.
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.
- 2d ago Changed e6c4f8cf9368
- 5d ago First seen · 70 lines · 125 tokens per session scan A dc1fd36b7176
digest is a skill published in the GitHub repository boykush/scraps (45 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 1,182 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 2026-10-11.
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.
processing-markdown
Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.
web-scraping
Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…
remem
Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.
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.
scratch
Organize knowledge from an agent session into a scratchpad — a folder of files plus a scratchpad.json manifest. Use when a task generates notes, snippets, command output, diagrams, or artifacts worth keeping together for a session/activity.