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/waynesutton/markdown-site/claude-mdgit clone --depth 1 https://github.com/waynesutton/markdown-siteWhat 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 | $0.01605 | $0.01605 |
| Opus 5 | $0.00803 | $0.00803 |
| Sonnet 5 | $0.00321 | $0.00321 |
| Haiku 4.5 | $0.00161 | $0.00161 |
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.
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:
workosauth +netlifyhosting
Workflows
Adding a blog post
- Create
content/blog/my-post.mdwith frontmatter (see.claude/skills/frontmatter.md) - Run
npm run sync - Content appears at localhost:5173/my-post
Adding a page
- Create
content/pages/my-page.mdwith frontmatter - Run
npm run sync - Page appears at localhost:5173/my-page
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 · 178 lines · 1,605 tokens per session scan A 779fdc2acac0
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.
Other instructions, from other repositories
shieldcn AGENTS.md
Instructions for jal-co/shieldcn, covering agents.md — shieldcn, what this is, monorepo structure, packages/core (@shieldcn/core) and packages/web (@shieldcn/web).
flowwink CLAUDE.md
Instructions for magnusfroste/flowwink, covering claude.md, commands, development (auto-runs migrations before starting), production build and lint.
reboot-cms AGENTS.md
Instructions for shaack/reboot-cms, covering agents.md, what this is, project layout, routing: file = url and pages.
mainbranch AGENTS.md
Instructions for noontide-co/mainbranch, covering agent instructions, product shape, daily operating loop, quick start and repository layout.
mainbranch CLAUDE.md
Instructions for noontide-co/mainbranch, covering claude code instructions, repository role, product loop to preserve, how to work here and engine vs business repo.
context CLAUDE.md
Claude Code instructions for Supa-Media/context, covering agent instructions — context, non-negotiables, 1. the customer owns the storage, 2. tenancy is bucket-level, never prefix-level and 3. plain files stay canonical.