citra

A local tool for reading PDF files with structure, tables, page references, search, rendering, cropping, and OCR. OCR reads text from scanned pages or images.

In plain words
What is it for?
Use it to read documents, search for exact text, inspect tables, render pages, crop areas, and extract text from scans.
Why use it?
It helps an agent find and verify information in PDFs while preserving evidence about where the information came from.

Skill for Claude CodeCodex

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 skills/sylphxai/pdf-reader-mcp/citra
Any agent
npx skills add SylphxAI/pdf-reader-mcp --skill citra
Clone the repo
git clone --depth 1 https://github.com/SylphxAI/pdf-reader-mcp

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 200 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00200
Opus 5 $0.00000 $0.00100
Sonnet 5 $0.00000 $0.00040
Haiku 4.5 $0.00000 $0.00020

Measured yesterday against content hash 2eaf2e5f0a70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

citra 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 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.

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.

skills/citra/SKILL.md · 33 lines

What it actually says

Citra — PDF evidence for agents

Install

npm i -g @sylphx/citra
# or
npx @sylphx/citra

Tools

Tool Job
read_pdf Agent Document Twin (structure, tables, citations)
search_pdf Literal search with page/bbox evidence
pdf_evidence inspect / render / crop / OCR follow-ups

SDK

import { Citra } from '@sylphx/citra/sdk'
const citra = Citra.create()
const result = await citra.read({ path: '/abs/doc.pdf' })

Rules

  • Local-first; no API key required for default path
  • Missing native binary → fail closed
  • Evidence on results (envelope v1); no evidence_first tool
  • Do not install Prism for PDF routing
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. yesterday First seen · 33 lines · 0 tokens per session scan A 2eaf2e5f0a70

Subscribe to this mod's changes

citra is a skill published in the GitHub repository SylphxAI/pdf-reader-mcp (909 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 200 tokens. 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.