markdown-site CLAUDE.md

Project instructions for a Markdown publishing framework that syncs files from a content folder into Convex, a real-time database. They document local setup and commands for content, wiki, and discovery files.

In plain words
What is it for?
Installing and running the site locally, syncing Markdown content, updating wiki pages and AI-discovery files, targeting a knowledge base, and publishing all content to production.
Why use it?
They show how to make written content appear in the application and how to sync it to development or production environments.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/waynesutton/markdown-site/claude-md
Clone the repo
git clone --depth 1 https://github.com/waynesutton/markdown-site
Per session 1,605 This file is loaded in full into every session.
When invoked 1,605 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01605 $0.01605
Opus 5 $0.00803 $0.00803
Sonnet 5 $0.00321 $0.00321
Haiku 4.5 $0.00161 $0.00161

Measured 3d ago against content hash 779fdc2acac0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

markdown-site 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.

CLAUDE.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project instructions for Claude Code.

Project context

Markdown sync framework. Write markdown in content/, run sync commands, content appears instantly via Convex real-time database. Built for developers and AI agents.

Quick start

npm install                    # Install dependencies
npx convex dev                 # Start Convex (creates .env.local)
npm run dev                    # Dev server at localhost:5173
npm run sync                   # Sync markdown to Convex

Commands

Command Purpose
npm run sync Sync markdown to dev Convex
npm run sync:prod Sync markdown to prod Convex
npm run sync:discovery Update AGENTS.md, CLAUDE.md, llms.txt (includes wiki pages)
npm run sync:discovery:prod Update discovery files for production
npm run sync:wiki Sync wiki from content/blog and content/pages
npm run sync:wiki:prod Sync wiki to production
npm run sync:wiki -- --kb=<id> Sync wiki into a specific knowledge base
npm run sync:all Sync content + wiki + discovery files
npm run sync:all:prod Sync all to production
npm run dev Start Vite dev server
npm run build Production build
npx convex dev Start Convex dev watcher
npx convex deploy Deploy Convex to production
npm run deploy Deploy static app with Convex self-hosting
npm run import <url> Import external URL as post

Default and legacy modes

  • Default auth mode: convex-auth
  • Default hosting mode: convex-self-hosted
  • Legacy compatibility mode: workos auth + netlify hosting

Workflows

Adding a blog post

  1. Create content/blog/my-post.md with frontmatter (see .claude/skills/frontmatter.md)
  2. Run npm run sync
  3. Content appears at localhost:5173/my-post

Adding a page

  1. Create content/pages/my-page.md with frontmatter
  2. Run npm run sync
  3. Page appears at localhost:5173/my-page

Read the full file on GitHub · 178 lines

Changes

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.

  1. 3d ago First seen · 178 lines · 1,605 tokens per session scan A 779fdc2acac0

Subscribe to this mod's changes

markdown-site CLAUDE.md is an instructions file published in the GitHub repository waynesutton/markdown-site (631 stars, last pushed 3mo ago), licensed MIT. It adds 1,605 tokens to every session, about $0.0080 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 2026-08-30.