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 agentmods add instructions/angelopvtac/explainer-pack/claude-mdgit clone --depth 1 https://github.com/Angelopvtac/explainer-packWrote 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/instructions/angelopvtac/explainer-pack/claude-md)<a href="https://agentmods.dev/instructions/angelopvtac/explainer-pack/claude-md"><img src="https://agentmods.dev/badge/instructions/angelopvtac/explainer-pack/claude-md.svg" alt="Measured on agentmods" 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 | $0.01134 | $0.01134 |
| Opus 5 | $0.00567 | $0.00567 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
explainer-pack CLAUDE.md 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 3d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
explainer-pack — invariants
This repo is a public, distributable Claude Code skill pack. It will land on GitHub as MIT-licensed code and be installed by strangers.
Public-clean is non-negotiable
- No personal identifiers (no "Angelo", no
~/.claude/..., no references to other private projects). - No path assumptions beyond
./skills/Explainer/and./examples/. - Documentation speaks to a generic user, not the author.
- If you find personal residue, strip it — don't ask.
What's in the box
skills/Explainer/— the canonical skill:SKILL.md,Workflows/{Generate,Revise}.md,References/{Philosophy,Aesthetic,Components}.md,References/Boilerplate.html,Themes/*.css,Tools/{render,verify}.ts..claude-plugin/plugin.json— Claude Code plugin manifest. Schema:https://json.schemastore.org/claude-code-plugin-manifest.json.examples/sample-explainer.html— self-referential showcase (the format documenting itself, in the defaultanthropictheme).examples/samples/<theme>.html— same content, one render per theme. The visual catalogue.README.md,LICENSE(MIT).
Discipline is locked. Themes are a parameter.
The Explainer discipline is the product. It applies to every theme:
- Single chrome accent. Exactly one accent colour used for kicker, h2, links, primary callouts. Never a second.
- Color is semantic and lives in the data layer only. The five-hue data palette (
--data-sage,--data-clay,--data-amber,--data-dusty,--data-coral) is used INSIDE diagrams to carry meaning. It is never used in chrome. - Chrome retreats. No panel around diagrams by default. Hairline rules optional (
.viz.ruled). Cards lose their backgrounds; hierarchy comes from typography and spacing. - Inline SVG only. No external images, no JS, no CDNs. The HTML must work offline forever.
- Three font families with three jobs. Display for h1/h2sub/captions. Body for prose and SVG labels. Mono for code, data values, kickers, and file paths. (The
bloombergtheme intentionally breaks the third rule because mono-everywhere IS its identity — that's the exception that proves the rule.) - Diagrams carry meaning, prose is captions. If a section is prose-heavy, the diagram is wrong.
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.
- 3d ago First seen · 58 lines · 1,134 tokens per session scan A b8b2157d0f6f
explainer-pack CLAUDE.md is an instructions file published in the GitHub repository Angelopvtac/explainer-pack (1 stars, last pushed 3mo ago), licensed MIT. It adds 1,134 tokens to every session, about $0.0057 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 instructions, from other repositories
artifact-organizer AGENTS.md
Instructions for keepYaoung/artifact-organizer, covering agents.md — artifact-organizer, first run — ask three things, then remember them, what this project does, stacking documents and publishing (→ your repo, github pages sub-path).
vizwright CLAUDE.md
Instructions for blakefeiza/vizwright, covering vizwright — orchestrator, routing (automatic — no keywords needed), pipeline, artifact contracts and error handling.
UIX CLAUDE.md
Instructions for Deepractice/UIX, covering uix project rules, design system: lucid ui, colors, forbidden and preferred patterns.
marimo copilot-instructions.md
Copilot instructions for marimo-team/marimo: For example, if there is a frontend change to make a border thicker, how does this look in run mode, app-view and edit-view? For a backend change, has the user tested different scenarios?
www-sacred AGENTS.md
Instructions for internet-development/www-sacred, covering agents.md, what this repo is, repo map, conventions and the fonts menu previews.
openbridge-webcomponents docgen.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering doc generator cli, it never edits the original and keep the prompt aligned with the rules.