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 koaning/wigglystuff --skill explain-diff-htmlgit clone --depth 1 https://github.com/koaning/wigglystuffWrote 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/koaning/wigglystuff/explain-diff-html)<a href="https://agentmods.dev/skills/koaning/wigglystuff/explain-diff-html"><img src="https://agentmods.dev/badge/skills/koaning/wigglystuff/explain-diff-html/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/koaning/wigglystuff/explain-diff-html"><img src="https://agentmods.dev/badge/skills/koaning/wigglystuff/explain-diff-html.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 | $0.00892 |
| Opus 5.5 | $0.00014 | $0.00357 |
| Sonnet 5.5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
explain-diff-html 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain Diff (HTML)
Produce a self-contained HTML file that explains a code change — a diff, a branch, or a PR — with the clarity and flow of Martin Kleppmann. The reader should come away with genuine understanding, not just a summary.
Output Format
Write a single self-contained HTML file (no external dependencies) to /tmp/ with a filename starting with today's date: /tmp/YYYY-MM-DD-explanation-<slug>.html.
The file must include embedded CSS and JavaScript for interactive features. No external stylesheets or scripts.
Required Sections
The HTML page is one long page with a table of contents at the top.
1. Background
Two parts:
Deep background (skippable). Explain the existing system broadly. Assume a capable engineer who may not know this particular codebase. Context from surrounding modules, the problem domain, and relevant history.
Narrow background. Focus on the specific area the change touches. What was the state of the code before this diff? What pain points or limitations existed?
2. Intuition
The core idea of the change, explained with concrete examples and toy data. Use HTML-based diagrams throughout — never ASCII art.
Good diagram types:
- Simplified UI mockups (use HTML/CSS elements)
- System / data-flow diagrams showing how data moves between components
- Before/after comparisons (use a two-column grid)
- Annotated code snippets that highlight what changes
Use callout boxes for key concepts, definitions, and important edge cases. Mark them visually distinct from the main text.
3. Code Walkthrough
Group changes in a logical order (not file-by-file or line-by-line). For each group:
- What was the problem / motivation
- What the new code does
- How it connects to the rest of the change
Use <pre> tags for code blocks. Every <pre> element must have white-space: pre-wrap or white-space: pre in its CSS — scan the output to confirm this before saving.
4. Quiz
Five interactive multiple-choice questions that test genuine understanding of the diff. Each question:
- Has 4 options (A/B/C/D)
- Shows correct/incorrect feedback on click (use JavaScript)
- Includes an explanation of the correct answer
- Is tough enough that you need to understand the substance to answer, but not a gotcha
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 First seen · 89 lines · 34 tokens per session scan A 5b222456fe6c
explain-diff-html is a skill published in the GitHub repository koaning/wigglystuff (450 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 892 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 2026-10-14.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Fetches URLs and PDFs, then summarizes or returns clean Markdown. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.