Borrowing it
Nothing to install: this file belongs to BND-1/horseMD. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/BND-1/horseMD/main/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/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/instructions/bnd-1/horsemd/claude-md"><img src="https://agentmods.dev/badge/instructions/bnd-1/horsemd/claude-md.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 | $0.27286 | $0.27286 |
| Opus 5.5 | $0.10914 | $0.10914 |
| Sonnet 5.5 | $0.05457 | $0.05457 |
| Haiku 4.5 | $0.02729 | $0.02729 |
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 — 1,432 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 + Arch pacman
(.pkg.tar.xz) 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 (or, on Arch, the .pkg.tar.xz) from the official
GitHub Release. Its postinst is our
build/linux/after-install.tpl (deb.afterInstall), which always installs
chrome-sandbox as root:root 4755 — electron-builder's default probes
unshare as root and leaves it 0755, which crashes on launch under Ubuntu
24.04+'s AppArmor userns restriction (#143). release.yml asserts this. Packaging runs with USE_HARD_LINKS=false
(#157): on CI electron-builder hard-links copies of one source file, so
resources/icons/32x32.png became a hard link to the hicolor icon and dpkg
failed with "Invalid cross-device link" where /opt is its own mount
(deepin 25); release.yml rejects any hard link in the .deb / pacman
package. The Arch package (#153) reuses the same template
(pacman.afterInstall) and overrides pacman.depends: electron-builder's
default list names packages Arch no longer ships (http-parser,
libappindicator-gtk3), so pacman -U would fail. Keep the list to the
libraries the binary actually links. release.yml installs and launches it in
an archlinux container (scripts/ci/verify-arch-package.sh).
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 Changed · +48 lines · +895 tokens per session 3eaf931a0114
- 7d ago Changed · +143 lines · +2,813 tokens per session 75e39de09223
- 9d ago Changed · +117 lines · +2,341 tokens per session 83bc2e51afe5
- 11d ago Changed · +119 lines · +2,225 tokens per session b666b66aba14
- 12d ago Changed · +41 lines · +751 tokens per session 082c9c4a76e3
- 13d ago Changed · +198 lines · +3,739 tokens per session b086a20d8a94
- 15d ago Changed · +16 lines · +305 tokens per session 87fc36c9fef3
- 16d ago Changed · +57 lines · +1,115 tokens per session 99c9d129de82
- 19d ago Changed · +9 lines · +188 tokens per session e47061aafcdd
- 20d ago First seen · 684 lines · 12,914 tokens per session scan A a707a3eb5675
horseMD CLAUDE.md is an instructions file published in the GitHub repository BND-1/horseMD (588 stars, last pushed 6d ago), licensed MIT. It adds 27,286 tokens to every session, about $0.1091 per session on Opus 5.5. 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.
horseMD CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| horseMD CLAUDE.mdBND-1/horseMD | Instructions file | 588 | 6d ago | MIT | A | 27,286 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |