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/maxmilian/markout/claude-mdgit clone --depth 1 https://github.com/maxmilian/markoutWrote 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/maxmilian/markout/claude-md)<a href="https://agentmods.dev/instructions/maxmilian/markout/claude-md"><img src="https://agentmods.dev/badge/instructions/maxmilian/markout/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 | $0.01401 | $0.01401 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
markout 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build, test, run
The Xcode project is generated from project.yml by XcodeGen and is git-ignored — always regenerate after changing project.yml, adding/removing source files, or on a fresh checkout.
brew install xcodegen # one-time
xcodegen generate # (re)create Markout.xcodeproj
# full test suite (Swift Testing)
xcodebuild test -project Markout.xcodeproj -scheme Markout \
-destination 'platform=macOS' -derivedDataPath .build/dd
# a single suite or test
xcodebuild test -project Markout.xcodeproj -scheme Markout -destination 'platform=macOS' \
-only-testing:MarkoutTests/MarkdownFormatterTests
xcodebuild test ... -only-testing:MarkoutTests/MarkdownFormatterTests/boldWrapsSelection
# build and launch the app
xcodebuild build -project Markout.xcodeproj -scheme Markout \
-destination 'platform=macOS' -derivedDataPath .build/dd
open .build/dd/Build/Products/Debug/Markout.app
There is no linter configured. Target is macOS 14.0, Swift 5.9, ad-hoc signed (no sandbox entitlement).
Vendored preview assets (offline constraint)
The preview renders in a WKWebView with no network access — highlight.js, KaTeX (+fonts), and Mermaid are vendored under Resources/PreviewAssets/ and loaded relative to Bundle.main.resourceURL. Never reference a CDN.
project.ymlbundlesResources/PreviewAssetsas a folder reference (type: folder) so thekatex/,highlight/,mermaid/,themes/subdirectory structure is preserved in the app bundle. Adding it as a normal resource flattens the tree and breaks both the relative<script src="PreviewAssets/…">paths andBundle.main.url(forResource:"themes", subdirectory:"PreviewAssets")— and causes "Multiple commands produce" build errors on the duplicate.gitkeep/default.cssnames.- To bump versions, edit the pins in
Resources/PreviewAssets/fetch-assets.shand run it on a networked machine; record versions/licenses inVERSIONS.md.
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 · 60 lines · 1,401 tokens per session scan A d347690af086
markout CLAUDE.md is an instructions file published in the GitHub repository maxmilian/markout (10 stars, last pushed 6d ago), licensed MIT. It adds 1,401 tokens to every session, about $0.0070 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
markstream-vue AGENTS.md
Instructions for Simon-He95/markstream-vue, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
MarkCardStudio AGENTS.md
AGENTS.md instructions for pangxiaobin/MarkCardStudio, covering repository guide for coding agents, product scope, stack and commands, architecture and important invariants.
markview CLAUDE.md
Instructions for paulhkang94/markview, covering markview — ai development guide, quick reference, architecture, mcp tools (for ai integration) and safety rules.
Knote AGENTS.md
Instructions for 1661169091kiwi/Knote, covering agents.md, 构建与验证约定（用户明确要求，所有会话必须遵守） and 测试说明.
mdread CLAUDE.md
Instructions for techjewel/mdread, covering claude.md, what this is, commands, architecture and styles (scss).
hanji AGENTS.md
Instructions for kokodak/hanji, covering agents.md, project overview, product north star, project structure and engineering guidelines.