Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add RadOrigin-LLC/RAD-Claude-Skills/plugin install rad-explainWrote 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/radorigin-llc/rad-claude-skills/explain-document)<a href="https://agentmods.dev/skills/radorigin-llc/rad-claude-skills/explain-document"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/explain-document/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/radorigin-llc/rad-claude-skills/explain-document"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/explain-document.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 | $0.00150 | $0.02035 |
| Opus 5 | $0.00075 | $0.01018 |
| Sonnet 5 | $0.00030 | $0.00407 |
| Haiku 4.5 | $0.00015 | $0.00203 |
Grade A, and why
explain-document 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 8d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain Document — Interpret a specific repo file
You are reading a specific document in the repo and producing a plain-English interpretation. The output answers questions the document doesn't make obvious on first read:
- What is this document actually saying? (interpretation)
- What does it commit me to? (commitments)
- What does it assume? (assumptions, named and unstated)
- Where could this go wrong? (risks, gotchas, conditions for failure)
This is the inverse of writing a doc — you're decompiling one. Useful when:
- An AI generated a plan / spec / proposal and you want to know what you're actually agreeing to before approving it
- You're onboarding to a repo and need to understand an existing ADR / architecture doc
- You're reviewing a contract-shaped doc (terms of service, license, agreement) in the repo
- A complex config file's effects aren't obvious from the syntax
Foundational rules
- Grounded. Every interpretation must trace to the document or to clearly cross-referenced source. If you say "this commits you to X", you must be able to point at the line that says X.
- Not overpromising. No "this is the only way to do Y" / "this is the best approach" — you're interpreting, not pitching.
- Honest about uncertainty. If the document is ambiguous, say "this could mean X or Y" rather than picking one.
Modes
interpret (default)
The general case: plain-English summary of what the document is saying, structured for a reader who didn't write it.
Output structure:
- What this document is (one paragraph: what kind of doc, what it's for, who wrote it if knowable)
- The core message (1-3 paragraphs: what it actually says in plain words)
- The structure (how the doc is organized; helps the reader navigate the original)
- Key terms defined (any jargon or shorthand the doc uses, translated)
commitments
Specifically focused on what the document commits the project (or its readers) to.
Output structure:
- Hard commitments (things the doc says will / must happen)
- Soft commitments (things the doc proposes / recommends but doesn't lock)
- Out of scope (things the doc explicitly says it won't do — surface these because they bound the commitment)
- What approval means (if the doc is a proposal: what specifically is the user agreeing to if they sign off?)
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.
- 8d ago First seen · 202 lines · 150 tokens per session scan A 6d1c9ff8598a
explain-document is a skill published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 22d ago), licensed Apache-2.0. It adds 150 tokens to every session and 2,035 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
Other skills, from other repositories
create_note
Capture findings or context as a persistent note in the thoughts system.
context-bundler
Interactively creates targeted code, design, and documentation bundles for external review (Markdown or ZIP). Includes a comprehensive library of review & delegation persona templates (Adversarial Security, Plan Critique, Refactoring Quality, Sub-Agent Task Handoff, Documentation Synthesis, Architecture, Compliance…
convert-mermaid
Translate .mmd diagram files into PNG images with configurable resolution (retina/HQ/scale), supporting rasterization (raster, rasterize, rasterization). V2 includes L5 Delegated Constraint Verification via verifypng for strict binary linting and Puppeteer-based rendering.
tikz-figure-review
Review and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered…
parse-integration
Extract structured data from documents (invoices, receipts, purchase orders, bills of lading, bank statements, contracts, forms, ID documents, scans, photos of paper) with Parse by Conversion Tools, and build a production integration against its API. Covers getting an API key, defining an extraction schema, submitting…
guide-from-screenshots
Generates polished markdown guides from a directory of screenshots and a narrative. Visually reads each image, filters out redundant or irrelevant captures, organizes them contextually, and produces a Notion-compatible markdown file with image placeholders and structured sections. Use when you have screenshots and…