What is PixelRAG CLAUDE.md?

A project guide for PixelRAG, a system that turns web pages and PDFs into screenshot images so they can be searched by their visual content.

Use it when working on document rendering, image-based search, embeddings, the web application, model training, or deployment scripts.

It records the repository layout, development conventions, deployment boundaries, and the rule that protected changes go through pull requests.

PixelRAG CLAUDE.md — Instructions file by StarTrail-org

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/startrail-org/pixelrag/claude-md

Clone the repo

git clone --depth 1 https://github.com/StarTrail-org/PixelRAG

Per session 371 This file is loaded in full into every session.

When invoked 371 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.

Model	Per session	Once invoked
Fable 5	$0.00371	$0.00371
Opus 5	$0.00186	$0.00186
Sonnet 5	$0.00074	$0.00074
Haiku 4.5	$0.00037	$0.00037

Measured 3d ago against content hash 945da17ca768, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

PixelRAG 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 · 29 lines

What it actually says

PixelRAG

Visual RAG: render documents (web pages, PDFs) as screenshot tiles and retrieve over the images with a Qwen3-VL embedding model. See README.md for the product overview and deploy/README.md for how it runs in production.

Layout

render/ — pixelshot capture (Playwright/CDP, PDF)
embed/, index/ — tiles → vectors → FAISS index
serve/ — FAISS search API (pixelrag serve)
web/ — Next.js frontend (on Vercel) + agent-server.mjs (the chat agent backend)
train/ — separate uv project (LoRA finetune); install from inside train/, not the root
deploy/ — systemd units, CD workflow, blue-green scripts

Conventions

Python: uv only (uv add, never uv pip install); work in .venv; commit uv.lock.
One distribution (pixelrag) with extras; the CLIs are pixelshot and pixelrag <stage>.
main is branch-protected — land changes via PRs.

Operational context (host-specific, kept out of this public repo)

Deploy/runtime details that are specific to the live host are not committed here. They are imported below; the import is a harmless no-op anywhere the file doesn't exist:

@~/.claude/pixelrag-ops.md

If deploy-host notes appeared from that import, you are on the deploy host — production services run there, so operate carefully. If nothing appeared, you're on a normal dev checkout and can ignore deployment concerns.

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.

3d ago First seen · 29 lines · 371 tokens per session scan A 945da17ca768

Subscribe to this mod's changes

PixelRAG CLAUDE.md is an instructions file published in the GitHub repository StarTrail-org/PixelRAG (9,837 stars, last pushed 4d ago), licensed Apache-2.0. It adds 371 tokens to every session, about $0.0019 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.

Data and AI Documents Multimodal PDF RAG and vectors agent ai search

pdf-inline-image-rag-mcp AGENTS.md

AGENTS.md instructions for Joncallim/pdf-inline-image-rag-mcp, covering pdf inline image rag mcp agent guide, invariants, repository map, focused workflow and validation.

Joncallim/pdf-inline-image-rag-mcp · 551 tokens

pdf-rag CLAUDE.md

Claude Code instructions for abdellahiheiballa/pdf-rag, covering foundational rules, our relationship, proactiveness, designing software and test driven development (tdd).

abdellahiheiballa/pdf-rag · 2,282 tokens

gpt-rag-ingestion azure-boundaries.instructions.md

Instructions for Azure/gpt-rag-ingestion, a project described as: The GPT-RAG Data Ingestion service automates processing of diverse documents—PDFs, images, spreadsheets, transcripts, and SharePoint—readying them for Azure AI Search. It applies smart chunking, generates text and image embeddings, and enables rich…

Azure/gpt-rag-ingestion · 250 tokens

PixelRAG CLAUDE.md