Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/docxology/templatenpx agentmods add skills/docxology/template/steganographyWrote 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/docxology/template/steganography)<a href="https://agentmods.dev/skills/docxology/template/steganography"><img src="https://agentmods.dev/badge/skills/docxology/template/steganography/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.
<a href="https://agentmods.dev/skills/docxology/template/steganography"><img src="https://agentmods.dev/badge/skills/docxology/template/steganography.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.01229 |
| Opus 5.5 | $0.00022 | $0.00492 |
| Sonnet 5.5 | $0.00011 | $0.00246 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
infrastructure-steganography 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steganography Infrastructure Module
The steganography module applies cryptographic hash manifests, text overlays, and interactive metadata objects (like mailto QR barcodes) directly to PDF post-rendering.
Core Processor (core.py)
The primary orchestrator of steganography operations. It handles config extraction, hashing, alpha-text watermarking, and barcodes.
from infrastructure.steganography import SteganographyConfig, SteganographyProcessor
from pathlib import Path
processor = SteganographyProcessor(SteganographyConfig(enabled=True, overlay_mode="text"))
final_pdf = processor.process(
Path("output.pdf"),
author_emails=["[email protected]"],
)
Barcodes (barcodes.py)
Responsible for generating dense Error-Correction Q-Level QR codes and Code128 barcode strips.
from infrastructure.steganography.barcodes import create_barcode_strip_overlay
overlay_pdf_bytes = create_barcode_strip_overlay(
page_width=612, page_height=792,
code128_data="paper-id-001",
)
Setup & Hashing (hashing.py)
Provides deterministic SHA-256 and SHA-512 manifest exports alongside standard PDF payloads.
from infrastructure.steganography.hashing import compute_file_hashes, write_hash_manifest
hashes = compute_file_hashes(Path("file.pdf"))
write_hash_manifest(Path("file.pdf"), hashes)
Overlays (overlays.py)
For applying visual steganographic traits like diagonally rendered strings across every page.
from infrastructure.steganography.overlays import create_watermark_overlay
overlay_bytes = create_watermark_overlay(page_width=612, page_height=792, text="CONFIDENTIAL", opacity=0.08)
Kmyth TPM Sealing (kmyth_adapter.py)
Optional TPM-backed sealing of hash manifests and steganography PDFs
into .ski sidecar files using the Kmyth toolkit.
from infrastructure.steganography.kmyth_adapter import (
KmythSealOptions, seal_file_with_kmyth, validate_kmyth_installation,
)
# Validate that kmyth-seal/kmyth-unseal are available
avail = validate_kmyth_installation(binary_dir="infrastructure/steganography/kmyth/bin")
print(avail.summary())
# Seal a file (requires running TPM backend on macOS)
ski_path = seal_file_with_kmyth(
Path("output.pdf"),
options=KmythSealOptions(
binary_dir=Path("infrastructure/steganography/kmyth/bin"),
tcti_config="mssim:host=127.0.0.1,port=2321",
timeout_seconds=15,
),
)
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- __init__.py 1.7 KB runs code
- AGENTS.md 6.6 KB
- barcode_generators.py 3.7 KB runs code
- barcode_payload.py 4.9 KB runs code
- barcodes.py 7.3 KB runs code
- config.py 13 KB runs code
- core.py 19 KB runs code
- encryption.py 6.5 KB runs code
- hashing.py 3.1 KB runs code
- kmyth_adapter.py 11 KB runs code
- metadata.py 7.8 KB runs code
- overlays.py 10 KB runs code
- README.md 7.0 KB
- start_tpm_backend.py 8.2 KB runs code
- swtpm_mssim_proxy.py 14 KB runs code
- THREAT_MODEL.md 8.2 KB
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.
- 1mo ago First seen · 114 lines · 55 tokens per session scan A b7791a8cc058
infrastructure-steganography is a skill published in the GitHub repository docxology/template (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 1,229 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
talisman
Generate a polished, on-brand PDF guide/handbook/whitepaper from a codebase or project using LaTeX (.tex -> .pdf) or Markdown->pandoc->pdf, with a designed cover page, the product's real brand colors and logo, a subtle branded page background, and TikZ diagrams (domain models, flows, state machines). Use for any…
oma-pdf
Extract PDF text, headings, tables, and images into Markdown using opendataloader-pdf. Use for PDF parsing, not PDF layout creation.
liteparse
Parse local document files into LLM-ready content on the daemon itself — PDFs → Markdown / structured JSON (with bounding boxes) / page screenshots via the bundled lit CLI. PDF works out of the box, offline, zero external deps (Tesseract + PDFium are bundled): digital PDFs use a near-instant native text path…
slides
Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding…
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
taxonomy-vto
A reference guide for diagnosing visual problems in LaTeX research papers. It defines categories such as wasted page space, misplaced figures, inconsistent formatting, overflow, alignment, and template-migration issues.