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/bnd-1/horsemd/claude-mdgit clone --depth 1 https://github.com/BND-1/horseMDWrote 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/bnd-1/horsemd/claude-md)<a href="https://agentmods.dev/instructions/bnd-1/horsemd/claude-md"><img src="https://agentmods.dev/badge/instructions/bnd-1/horsemd/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 | $0.10927 | $0.10927 |
| Opus 5 | $0.05463 | $0.05463 |
| Sonnet 5 | $0.02185 | $0.02185 |
| Haiku 4.5 | $0.01093 | $0.01093 |
Grade A, and why
horseMD CLAUDE.md scanned grade A with 1 finding 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 6d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
src/main/subprocess.js no-shell subprocess: timeout→kill→SIGKILL, 64 KiB stderr cap How it starts
The opening of the file, as written. The whole thing — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude / AI agents (and new devs) working in this repo. Keep it
short; deep detail lives in docs/.
New AI handoff: read
docs/ai-handoff.mdfirst. It captures the current project state, user working style, risk map, website/guide ownership, verification matrix, and recent stable baseline. This file remains the detailed historical convention book.
What this is
HorseMD — a warm, Typora-style Markdown editor. Electron shell + Vite + React, with Milkdown Crepe (ProseMirror-based WYSIWYG) as the editor engine. Core idea: every file opens as a tab in one window, not a new process. The shell (tabs, file tree, command palette, outline, themes, i18n, welcome screen) is all hand-written.
Commands
npm install # if Electron download is slow: ELECTRON_MIRROR=https://npmmirror.com/mirrors/electron/
npm run dev # electron-vite dev (HMR)
npm run build # build main + preload + renderer → out/
npm start # run the built app
npm run dist # build + electron-builder package for the HOST platform
npm run dist:dir # unpacked build (no installer)
npm run guide:dev # user tutorial site
npm run guide:check # tutorial content checks + static build
npm run dist packages for whatever OS you run it on — Windows NSIS on
Windows, macOS dmg + zip on macOS, and Linux amd64 deb on Linux. Installers
must be built and validated on their target OS; a dmg must be built on macOS and
a deb must pass dpkg-deb --info on Linux. If the
electron-builder binaries download slowly:
ELECTRON_BUILDER_BINARIES_MIRROR=https://npmmirror.com/mirrors/electron-builder-binaries/.
Builds are unsigned: Windows shows SmartScreen ("更多信息 → 仍要运行");
macOS Gatekeeper blocks first launch (right-click → Open, or
xattr -dr com.apple.quarantine /Applications/HorseMD.app). Linux users should
install only the .deb from the official GitHub Release.
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.
- 6d ago First seen · 574 lines · 10,927 tokens per session scan A 7523b82f7e56
horseMD CLAUDE.md is an instructions file published in the GitHub repository BND-1/horseMD (425 stars, last pushed 5d ago), licensed MIT. It adds 10,927 tokens to every session, about $0.0546 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.