markdown-site AGENTS.md

Repository instructions for coding agents working on a Markdown publishing site built with Convex, a real-time database platform. They describe the project, its modes, and its content, search, knowledge-base, and API setup.

In plain words
What is it for?
Understanding the site's architecture, technology choices, content workflow, search and wiki features, authentication, hosting, and available HTTP interfaces.
Why use it?
They give an agent the project context needed to make changes that fit the existing application and its supported operating modes.

Instructions file for CodexOpenCode

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/agents-md
Clone the repo
git clone --depth 1 https://github.com/waynesutton/markdown-site

Made for: Codex, OpenCode.

Per session 5,876 This file is loaded in full into every session.
When invoked 5,876 The same file — it is already loaded in full.
Security scan C 3 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 $0.05876 $0.05876
Opus 5 $0.02938 $0.02938
Sonnet 5 $0.01175 $0.01175
Haiku 4.5 $0.00588 $0.00588

Measured 2d ago against content hash a8027fcf9f05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

markdown-site AGENTS.md scanned grade C with 3 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

3. Internal action `compileWiki` sends context to GPT-4.1 mini with structured output instructions

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST https://yoursite.example.com/vfs/exec -H "Content-Type: application/json" -d '{"command": "ls /wiki"}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://yoursite.example.com/vfs/tree
AGENTS.md · 682 lines

How it starts

The opening of the file, as written. The whole thing — 682 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents working on this codebase.

Project overview

Your content is instantly available to browsers, LLMs, and AI agents.. Write markdown, sync from the terminal. Your content is instantly available to browsers, LLMs, and AI agents. Built on Convex.

Default and legacy modes

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

Key features:

  • Markdown posts with frontmatter
  • Four themes (dark, light, tan, cloud)
  • Full text search with Command+K
  • Semantic search with OpenAI embeddings and Ask AI (Cmd+J)
  • Real-time analytics at /stats
  • RSS feeds and sitemap for SEO
  • API endpoints for AI/LLM access
  • Virtual filesystem HTTP interface (/vfs/tree, /vfs/exec) with no auth required
  • Source ingest pipeline with Firecrawl scraping and OpenAI embeddings
  • LLM wiki compilation with GPT-4.1 mini driven synthesis and daily cron
  • Knowledge bases with Obsidian vault uploads, per-KB API access, and visibility controls
  • Interactive knowledge graph visualization per wiki and KB
  • Anonymous demo mode at /dashboard with 30-minute auto-cleanup
  • Admin dashboard with content management, config editor, sync buttons, and KB management
  • Newsletter automation with AgentMail integration

Current Status

  • Site Name: markdown sync
  • Site Title: markdown sync framework
  • Site URL: https://yoursite.example.com
  • Total Posts: 24
  • Total Pages: 4
  • Wiki Pages: 49
  • Latest Post: 2026-04-14
  • Last Updated: 2026-04-27T06:32:41.458Z

Tech stack

Layer Technology
Frontend React 18, TypeScript, Vite
Backend Convex (real-time serverless database)
Styling CSS variables, no preprocessor
Hosting Convex self-hosting (default) or Netlify (legacy)
Auth @robelest/convex-auth (default) or WorkOS (legacy)
Content Markdown with gray-matter frontmatter

Setup commands

Read the full file on GitHub · 682 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. 2d ago First seen · 682 lines · 5,876 tokens per session scan C a8027fcf9f05

Subscribe to this mod's changes

markdown-site AGENTS.md is an instructions file published in the GitHub repository waynesutton/markdown-site (631 stars, last pushed 3mo ago), licensed MIT. It adds 5,876 tokens to every session, about $0.0294 per session on Opus 5. A static security scan graded it C with 3 findings (asks the agent to reveal its instructions, sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.