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 skills add alejandro-ventures/llm-agnostic-icm-framework --skill ocr-foldergit clone --depth 1 https://github.com/alejandro-ventures/llm-agnostic-icm-frameworkWrote 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.
[](https://agentmods.dev/skills/alejandro-ventures/llm-agnostic-icm-framework/ocr-folder)<a href="https://agentmods.dev/skills/alejandro-ventures/llm-agnostic-icm-framework/ocr-folder"><img src="https://agentmods.dev/badge/skills/alejandro-ventures/llm-agnostic-icm-framework/ocr-folder.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00052 | $0.00512 |
| Opus 5 | $0.00026 | $0.00256 |
| Sonnet 5 | $0.00010 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
ocr-folder 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 6d 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.
What it actually says
ocr-folder
Environment
Runs in its own venv at .venv/ (gitignored). From this workflow folder:
- Windows PowerShell:
python -m venv .venv; .\.venv\Scripts\Activate.ps1; pip install -r requirements.txt - macOS/Linux:
python3 -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt
A venv isolates dependencies, not the system (see _core/SANDBOXING.md).
Inputs
| Source | Location | Why |
|---|---|---|
| PDFs to OCR | input/ |
source documents (gitignored) |
Process
- List PDFs in the input folder; report count and total size to the user.
- For each file, compute a content-hash cache token; skip if already in
output/.ocr_cache. - Per page: keep a sufficient native text layer as-is; render and OCR image-only pages.
- Gate: if any file would overwrite an existing output, stop and ask for explicit "yes".
- Writes go through
_core/scripts/sandbox.py(guard_write) — they cannot leave the workspace. - Append a run-log line and a token-tracker entry.
Outputs
| Artifact | Location | Format |
|---|---|---|
| Searchable text | output/<name>.txt |
UTF-8 |
| Cache | output/.ocr_cache |
hash list |
Gates
- Overwriting any existing output requires an explicit user "yes".
Run log
Append timestamp,ocr-folder,ocr,<n_processed> to output/run-log.csv, then log the run:
python _core/token-tracker/tracker.py log --workflow ocr-folder --action ocr --source local.
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.
- 6d ago First seen · 48 lines · 52 tokens per session scan A a77d295eb384
ocr-folder is a skill published in the GitHub repository alejandro-ventures/llm-agnostic-icm-framework (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 512 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
analyzing-malicious-pdf-with-peepdf
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
pdf-processing
Extract text from PDFs, fill forms, and merge documents.
azure-ai-document-intelligence-ts
Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building custom document models.
pdf-processing
Process and extract information from PDF documents. Use this skill when the user asks to read, analyze, or extract data from PDF files.
pandoc
Convert documents between formats (Markdown, DOCX, HTML, PDF, RST, EPUB, LaTeX) via the pandoc CLI. Use to transform a document from one format to another.