What is pdf-inline-image-rag-mcp AGENTS.md?

Repository instructions for a PDF search server that indexes text and actual inline images in a local SQLite database.

Building and searching PDF indexes, retrieving pages and images, storing captions, and validating changes to the package.

They define how to preserve page positions and image details while avoiding invented captions and unnecessary exposure of sensitive files.

How Joncallim/pdf-inline-image-rag-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Joncallim/pdf-inline-image-rag-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Joncallim/pdf-inline-image-rag-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Joncallim/pdf-inline-image-rag-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/joncallim/pdf-inline-image-rag-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/joncallim/pdf-inline-image-rag-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/joncallim/pdf-inline-image-rag-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/joncallim/pdf-inline-image-rag-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/joncallim/pdf-inline-image-rag-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/joncallim/pdf-inline-image-rag-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 551 This file is loaded in full into every session.

When invoked 551 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00551	$0.00551
Opus 5.5	$0.00220	$0.00220
Sonnet 5.5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash 6846bf7c210b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pdf-inline-image-rag-mcp AGENTS.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 2mo 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.

AGENTS.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PDF Inline Image RAG MCP Agent Guide

This Python package provides an MCP server and CLI that builds local SQLite full-text indexes from PDF text and actual inline image blocks while retaining exact page-flow placeholders and bounding boxes.

Invariants

Extract actual PDF image blocks, not whole-page screenshots by default. Preserve page number, image index, dimensions, file path, and exact PDF bounding box in the stored record and text placeholder.
Keep extraction factual: the package does not invent OCR or captions. Save externally produced captions only through the existing caption path so full-text search stays synchronized.
Keep CLI and MCP behavior aligned for their shared operations: build, search, page retrieval, and database inspection. Direct image retrieval, uncaptioned- image listing, and caption persistence are MCP-only operations; do not expand the CLI to match them unless the user explicitly requests that product change.
Treat PDFs, extracted images, SQLite databases, captions, and output paths as potentially sensitive user data. Do not commit them, log their contents unnecessarily, or expose files outside the requested output/database scope.
Validate paths and replacement behavior before filesystem writes. Do not weaken explicit --replace semantics or allow a request to escape the intended output/database roots.

Repository Map

src/pdf_inline_image_rag_mcp/extractor.py: PDF extraction, image placement, SQLite schema/indexing, and retrieval behavior.
src/pdf_inline_image_rag_mcp/server.py: MCP tools and input/output contracts.
src/pdf_inline_image_rag_mcp/cli.py: command-line surface.
tests/test_extractor.py: focused extraction and persistence coverage.
pyproject.toml: Python, dependency, entry-point, and pytest configuration.

Focused Workflow

Keep one writer per implementation or test file. For substantive work, separate core extraction/database changes from a read-only MCP/CLI contract review.
Add a focused regression test for changes to coordinates, placeholder ordering, page selection, FTS updates, replacement, or path handling.
Filesystem scope, replacement/deletion, untrusted PDFs, SQL/FTS construction, MCP exposure, or sensitive output changes require an independent security review.

Read the full file on GitHub · 37 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.

2mo ago First seen · 37 lines · 551 tokens per session scan A 6846bf7c210b

Subscribe to this mod's changes

pdf-inline-image-rag-mcp AGENTS.md is an instructions file published in the GitHub repository Joncallim/pdf-inline-image-rag-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 551 tokens to every session, about $0.0022 per session on Opus 5.5. 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 2026-08-31.

Data and AI Documents PDF RAG and vectors

pdf-inline-image-rag-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pdf-inline-image-rag-mcp AGENTS.mdJoncallim/pdf-inline-image-rag-mcp	Instructions file	1	2mo ago	MIT	A	551	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

pdf-inline-image-rag-mcp: Instructions file for Codex