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/urbanmorph/mdshare/claude-mdgit clone --depth 1 https://github.com/urbanmorph/mdshareWhat 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 | $0.00756 | $0.00756 |
| Opus 5 | $0.00378 | $0.00378 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
mdshare 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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
mdshare
Project Philosophy
mdshare is deliberately minimal. The core value is: upload markdown, get a link, share it. That's it.
Design principles:
- Simple over powerful — if a feature needs explanation, it's too complex
- Zero friction — no login, no setup, no configuration. Paste and go.
- Invisible infrastructure — users shouldn't know or care about the tech stack
- Features earn their place — every feature must make the core flow faster or clearer. If it adds a button, menu, or step, it needs strong justification.
- Don't build what users haven't asked for — resist speculative features
What mdshare is NOT:
- Not a Google Docs competitor (no real-time cursors, no track changes)
- Not a CMS or wiki
- Not a note-taking app
- Not a collaboration platform with user accounts
When evaluating new features, ask:
- Does this make upload → share → collaborate faster?
- Can a first-time user figure it out without instructions?
- Does it add UI clutter?
- Could this be solved by the user's existing tools instead?
Tech Stack
- Astro 5 on Cloudflare Workers (native, via
@astrojs/cloudflareadapter) - React 19 as Astro islands (
client:load,client:only="react") - Cloudflare D1 (SQLite), Durable Objects (WebSocket)
- Tiptap editor with tiptap-markdown
- Tailwind CSS v4
- CI/CD: GitHub Actions →
astro build && wrangler deployon push to main
Key Files
lib/sanitize.ts— content sanitization pipeline (security-critical)lib/tokens.ts— token generation and verificationlib/permissions.ts— permission resolution from tokenslib/db.ts— D1 access viacloudflare:workersenvlib/db-types.ts— D1 row types (separated so client code can import without runtime)lib/broadcast.ts— DO broadcast helper called from PUT/PATCHsrc/pages/— Astro pages (file-based routing)src/pages/api/— all REST API routes (Astro endpoints)src/pages/d/[id].astro— document SSR page (dynamic OG tags from D1)src/components/DocumentView.tsx— main editor component (React island, largest)src/worker.ts— custom worker entry with WebSocket bypass + DO export + cronsrc/layouts/Layout.astro— HTML shell, meta tags, JSON-LD, fontsworker/document-ws.ts— Durable Object class for WebSocket synccomponents/editor/— Tiptap editor, toolbar, comments, highlightspublic/.assetsignore— prevents wrangler from uploading_worker.jsas an asset
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.
- 2d ago First seen · 64 lines · 756 tokens per session scan A fa45cf9f9338
mdshare CLAUDE.md is an instructions file published in the GitHub repository urbanmorph/mdshare (8 stars, last pushed 23d ago), licensed MIT. It adds 756 tokens to every session, about $0.0038 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
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.
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 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).
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.