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 5.5 | $0.00028 | $0.00258 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (13 stars, last pushed 4mo ago), licensed MIT. It adds 70 tokens to every session and 646 once invoked, about $0.0003 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 2026-08-31.
gamma-watermark-remover compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gamma-watermark-removergammaremover/gamma-watermark-remover-skill | Skill | 13 | 4mo ago | MIT | A | 70 | Claude Code, Codex |
| markitdownK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 62 | Claude Code, Codex |
| pydicomK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 52 | Claude Code, Codex |
| liteparseK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 87 | Claude Code |
| open-notebookK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 96 | Claude Code, Codex |
| pptx-postersK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 59 | Claude Code |
| convert-documents-to-markdownnanocoai/nanoclaw | Skill | 31k | yesterday | MIT | A | 57 | Claude Code |