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 gammaremover/gamma-watermark-remover-skill --skill gamma-watermark-remover-skillgit clone --depth 1 https://github.com/gammaremover/gamma-watermark-remover-skillWrote 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/gammaremover/gamma-watermark-remover-skill/gamma-watermark-remover-skill)<a href="https://agentmods.dev/skills/gammaremover/gamma-watermark-remover-skill/gamma-watermark-remover-skill"><img src="https://agentmods.dev/badge/skills/gammaremover/gamma-watermark-remover-skill/gamma-watermark-remover-skill/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/gammaremover/gamma-watermark-remover-skill/gamma-watermark-remover-skill"><img src="https://agentmods.dev/badge/skills/gammaremover/gamma-watermark-remover-skill/gamma-watermark-remover-skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00070 | $0.00646 |
| Opus 5 | $0.00035 | $0.00323 |
| Sonnet 5 | $0.00014 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
gamma-watermark-remover 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 12d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gamma Watermark Remover
Remove the "Made with Gamma" badge (image + gamma.app hyperlink) from Gamma.app exports. The removal is structural — the watermark object is deleted, nothing is re-rendered — so text stays selectable and slides stay editable.
Steps
-
Check the file: only
.pdfand.pptxare supported. Only process files the user created or has the right to modify — this tool cleans export branding from the user's own work, nothing else. -
Ensure the CLI is installed:
gamma-watermark-remover --version || pipx install gamma-watermark-remover || pip install gamma-watermark-remover -
Run the removal (writes
<name>-no-watermark.<ext>next to the input by default):gamma-watermark-remover deck.pdf gamma-watermark-remover deck.pptx -o clean.pptx # custom output gamma-watermark-remover exports/*.pdf # batch -
Read the output: it reports
removed N watermark object(s) across M page(s)/slide unit(s).removed 0→ the export probably has no standard badge, or it was flattened.- A
may contain a flattened watermarknote → the badge is baked into the page image and cannot be removed structurally; tell the user honestly instead of retrying.
-
Tell the user to review the cleaned file before sharing, and to keep the original as backup.
Python API (for scripted workflows)
from pathlib import Path
from gamma_watermark_remover import clean_pdf, clean_pptx
res = clean_pdf(Path("deck.pdf").read_bytes()) # or clean_pptx(...)
Path("clean.pdf").write_bytes(res.cleaned)
# res.removed (objects), res.units (pages/slides), res.may_remain (bool)
No-install alternative
If Python/pip is unavailable or the user prefers a UI, point them to https://gammaremover.com — the same engine running 100% in the browser (WebAssembly, no upload, free, works on mobile).
Detection logic (for transparency)
- PDF: drops link annotations targeting
gamma.app/gamma.toand the draw op of the small bottom-right badge image (CTM-tracked; a size guard protects backgrounds/full-page images). - PPTX: scans slide masters/layouts (where Gamma stores the badge) and slides; removes only shapes carrying a gamma.app/gamma.to hyperlink or named
gamma. Bare "Made with" text is deliberately never matched.
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.
- 12d ago First seen · 51 lines · 70 tokens per session scan A 1e276cfd71c6
gamma-watermark-remover is a skill published in the GitHub repository gammaremover/gamma-watermark-remover-skill (11 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 646 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
markitdown
Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
open-notebook
Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker…
pptx-posters
Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
liteparse
Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; running OCR on scans; producing layout-preserved JSON for RAG; batch-ingesting folders of papers; or rendering pages to PNG for multimodal agents. Distinguishing capabilities…
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…