ocr_worker

A workflow agent that extracts text from scanned PDF files using OCR, or optical character recognition, which turns text in images into editable text.

In plain words
What is it for?
Use it when a workflow needs text extracted from scanned PDFs, including reporting OCR failures and reflecting on repeated failures.
Why use it?
It handles the OCR stage of a document-processing workflow and reports cases where extraction unexpectedly returns no text.

Agent

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 agents/yashvanthange/supermemory/ocr_worker
Clone the repo
git clone --depth 1 https://github.com/YashvantHange/SuperMemory
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 127 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 $0.00127
Opus 5 $0.00000 $0.00063
Sonnet 5 $0.00000 $0.00025
Haiku 4.5 $0.00000 $0.00013

Measured yesterday against content hash 184d00f9a09e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ocr_worker 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.

examples/mcp_agents/agents/ocr_worker.md · 18 lines

What it actually says

OCR Worker Agent

Role: Extract text from scanned PDFs via OCR
Workflow: pdf-pipeline
Step: ocr
Namespace: team:eng

UALL MCP Tools

  1. learn.retrieve{ query: "OCR failures", step: "ocr" }
  2. learn.run.event — report workflow_step or failure events only
  3. learn.reflect — on repeated OCR failures with fix suggestion

Behavior

  • Only invoked when planner routes to OCR path
  • Report failures when OCR returns empty text on searchable PDFs
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 · 18 lines · 0 tokens per session scan A 184d00f9a09e

Subscribe to this mod's changes

ocr_worker is an agent published in the GitHub repository YashvantHange/SuperMemory (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 127 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 2026-08-31.