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/danhnm1203/scrollytelling/claude-mdgit clone --depth 1 https://github.com/danhnm1203/scrollytellingWrote 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/danhnm1203/scrollytelling/claude-md)<a href="https://agentmods.dev/instructions/danhnm1203/scrollytelling/claude-md"><img src="https://agentmods.dev/badge/instructions/danhnm1203/scrollytelling/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 5.1 | $0.00892 | $0.00892 |
| Opus 5 | $0.00446 | $0.00446 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
scrollytelling 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scrollytelling
An npm CLI + skill that turns a video into a scroll-scrubbed hero page — Next, Nuxt, Astro or plain HTML.
- Design (source of truth): docs/superpowers/specs/2026-08-04-scrollytelling-design.md
- Task order: the CEO review (T1–T23) and Eng review (E1–E17)
- Deliberately deferred: TODOS.md
Layout
bin/cli.mjs argument dispatch only; commands live in scripts/
lib/cli-args.mjs pure arg parsing (no fs, no exit, no console)
lib/scroll-math.mjs the primitives — scale, easing, fade, scrim. pure, fully tested
lib/scroll-engine-state.mjs
what the runtime decides, composed from those primitives:
load state, decode window, draw parameters. pure, no DOM
lib/social-card.mjs what a link preview says. one answer for four templates,
each of which still puts it in a head its own way. copied
into every project, like scroll-math
lib/template-manifest.mjs
where each template keeps its things — one list, read by
the scaffolder and the frame pipeline
scripts/frames.mjs extract, measure, encode (sharp + ffmpeg-static live HERE)
scripts/scaffold.mjs copy templates/<name>/ (node:fs only)
templates/<name>/ one directory per template; templates/next/ is the default
tests/ node:test, no build step
ci/ the per-template build gate — installs, bundles, and checks
the emitted files. Needs a network, so it runs in CI, not
in `npm test`. Not in package.json `files`.
tools/ `npm run sample` — scaffolds a real project into
.sample-<template>/ and starts it, so a change can be
looked at rather than only tested. Split pure/impure the
way ci/ is; its output is gitignored. Also holds the two
inputs of the published demo page (demo-story.js and
demo-clip.mp4), which ARE committed. Not in package.json
`files`, so none of it ships.
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.
- 5d ago First seen · 66 lines · 892 tokens per session scan A f842ce11670f
scrollytelling CLAUDE.md is an instructions file published in the GitHub repository danhnm1203/scrollytelling (5 stars, last pushed 27d ago), licensed MIT. It adds 892 tokens to every session, about $0.0045 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
starwind-ui AGENTS.md
AGENTS.md instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
vscode-angular-snippets AGENTS.md
AGENTS.md instructions for johnpapa/vscode-angular-snippets, covering angular snippets for vs code — agent guide, repository structure, tech stack, build & run and test in browser (vscode.dev mode).
react-svg AGENTS.md
AGENTS.md instructions for tanem/react-svg, covering agents.md, writing, architecture, build & test and releases.
stardrive AGENTS.md
AGENTS.md instructions for peltmonger/stardrive, covering 🛑 critical: repository bootstrap directive 🛑, general information and guidelines for ai agents, analyze your high-level use case first, how the .ai guidance files relate and this is an astro project.
vscode-angular-snippets copilot-instructions.md
Copilot instructions for johnpapa/vscode-angular-snippets, covering copilot instructions — vscode-angular-snippets, project type, snippet conventions, prefix naming and snippet body.
html-tools CLAUDE.md
Claude Code instructions for chicogong/html-tools, covering claude.md, 项目概述, 开发命令, 数据与生成边界 and 首页架构.