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/lightpaperorg/lightpaper/agents-mdgit clone --depth 1 https://github.com/lightpaperorg/lightpaperWhat 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 | $0.00873 | $0.00873 |
| Opus 5 | $0.00436 | $0.00436 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
lightpaper AGENTS.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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://lightpaper.org/v1/auth/email \ How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — lightpaper.org
API-first publishing platform for AI agents and humans. One HTTP call, one permanent URL.
What is lightpaper.org?
lightpaper.org publishes markdown documents as permanent, discoverable web pages with quality scoring, author gravity (trust system), and full-text search. Designed for AI agents — publish via API, MCP, or direct HTTP.
Quick Start
MCP Server (recommended for agents)
pip install lightpaper-mcp
Or connect to the remote endpoint (no install): https://lightpaper.org/mcp
Direct API
# Sign up (30 seconds)
curl -X POST https://lightpaper.org/v1/auth/email \
-H "Content-Type: application/json" \
-d '{"email": "[email protected]", "display_name": "Your Name", "handle": "yourhandle"}'
# Verify code from email
curl -X POST https://lightpaper.org/v1/auth/verify \
-H "Content-Type: application/json" \
-d '{"session_id": "...", "code": "123456"}'
# Publish
curl -X POST https://lightpaper.org/v1/publish \
-H "Authorization: Bearer lp_free_your_key" \
-H "Content-Type: application/json" \
-d '{"title": "My Article", "content": "# Heading\n\nYour markdown here (300+ words)..."}'
Project Structure
| Path | Purpose |
|---|---|
app/ |
FastAPI application (routes, services, models) |
mcp/server.py |
MCP server (25 tools, 3 prompts) — stdio transport |
lightpaper_mcp/ |
Standalone MCP package for PyPI distribution |
app/routes/mcp_http.py |
Remote MCP endpoint (Streamable HTTP transport) |
tests/ |
Pytest test suite |
migrations/ |
Idempotent SQL migrations |
CLAUDE.md |
Detailed development instructions |
Development
docker compose up -d db # PostgreSQL on port 5433
cp .env.example .env
pip install -r requirements-dev.txt
uvicorn app.main:app --port 8001 --reload
Tests
python3 -m pytest tests/ -v
~58 tests pass without a database. ~7 integration tests need PostgreSQL on port 5433.
Key Conventions
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.
- yesterday First seen · 88 lines · 873 tokens per session scan A d95adda69216
lightpaper AGENTS.md is an instructions file published in the GitHub repository lightpaperorg/lightpaper (0 stars, last pushed 2mo ago), licensed MIT. It adds 873 tokens to every session, about $0.0044 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
data-olympus AGENTS.md
Instructions for knaisoma/data-olympus, covering data olympus, project overview, architecture, development workflow and code standards.
obsidian-mcp-server CLAUDE.md
Instructions for smith-and-web/obsidian-mcp-server, covering obsidian mcp server — project conventions, stack, commands, layout and adding a new tool (the common change).
data-olympus copilot-instructions.md
Instructions for knaisoma/data-olympus: Read and follow all instructions in AGENTS.md. Read and follow all rules in .rules/. Read and follow the global Codex and Claude Code collaboration rule in /kn-projects/company-knowledge/tooling/codex-claude-collaboration.md.
data-olympus CLAUDE.md
Instructions for knaisoma/data-olympus: Read and follow all instructions in AGENTS.md. Read and follow all rules in .rules/. Read and follow the global Codex and Claude Code collaboration rule in /kn-projects/company-knowledge/tooling/codex-claude-collaboration.md.
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.