remove-ai-marks

remove-ai-marks is a skill for Claude Code from guillaumemeyer/watermarks-remover. It costs 138 tokens per session (4,908 once invoked), scanned A, original, MIT.

A skill for removing selected AI-related marks from text and supported files, including invisible Unicode, statistical text patterns, and provenance metadata.

In plain words
What is it for?
Use it with supported PNG, JPEG, WebP, SVG, PDF, DOCX, ODT, HTML, and Markdown files, or with reader-facing text.
Why use it?
It helps produce cleaned copies when such marks or embedded file information should be removed, while noting that statistical cleanup is only best-effort.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the watermarks-remover plugin — 2 skills, 1 hook shipped together

Good fit Use it with supported PNG, JPEG, WebP, SVG, PDF, DOCX, ODT, HTML, and Markdown files, or with reader-facing text.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guillaumemeyer/watermarks-remover/remove-ai-marks
About the project

watermarks-remover is a privacy-focused application that removes AI provenance marks from text and files owned by the user, including hidden text markers and metadata in many document, image, audio, and video formats. Its agent skill sends requests to a separate Python service, allowing supported coding agents to use the removal tools without installing Python on the agent host.

guillaumemeyer/watermarks-remover · 21,743 stars · on GitHub

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.

Any agent
npx skills add guillaumemeyer/watermarks-remover --skill remove-ai-marks
Clone the repo
git clone --depth 1 https://github.com/guillaumemeyer/watermarks-remover

Made for: Claude Code.

Or install watermarks-remover, the plugin that ships this one along with the rest of its 2 skills, 1 hook.

Wrote 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.

agentmods badge for remove-ai-marks

README.md
[![agentmods](https://agentmods.dev/badge/skills/guillaumemeyer/watermarks-remover/remove-ai-marks/github.svg)](https://agentmods.dev/skills/guillaumemeyer/watermarks-remover/remove-ai-marks)
Your own site
<a href="https://agentmods.dev/skills/guillaumemeyer/watermarks-remover/remove-ai-marks"><img src="https://agentmods.dev/badge/skills/guillaumemeyer/watermarks-remover/remove-ai-marks/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.

agentmods 80×15 button for remove-ai-marks

Your own site · 80×15
<a href="https://agentmods.dev/skills/guillaumemeyer/watermarks-remover/remove-ai-marks"><img src="https://agentmods.dev/badge/skills/guillaumemeyer/watermarks-remover/remove-ai-marks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,908 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket warn 4 Sept 2026
  • Snyk pass 4 Sept 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 8 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 104
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 144
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 111
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 180
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 194
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 164
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium MCP Rug Pull · line 298
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • low Tool Misuse · line 298
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
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 5.1 $0.00138 $0.04908
Opus 5 $0.00069 $0.02454
Sonnet 5 $0.00028 $0.00982
Haiku 4.5 $0.00014 $0.00491

Measured 2d ago against content hash bef308cdeffc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

remove-ai-marks scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Python, venvs, or cleaning tools. Call the service with `curl`; never run
skills/remove-ai-marks/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remove AI marks

Multi-vendor anti-detection hygiene for text (Unicode + statistical rewrite) and files (C2PA / AI metadata across common containers).

Read if needed:

  • references/mark-classes.md — Unicode / sampling / C2PA / containers
  • references/vendor-notes.md — Claude, Gemini/SynthID, OpenAI, open-LLM
  • references/removal-matrix.md — which layer when
  • references/ethics.md — intended use
  • references/how-claude-marks.md — Anthropic-specific detail
  • references/markdiffusion.md — optional MarkDiffusion image harness (schemes, honesty caveats)

This skill is a thin client. All deterministic cleaning machinery runs in a separate HTTP service (this repo's service/), so the agent host needs no Python, venvs, or cleaning tools. Call the service with curl; never run cleaning scripts directly.

Service access

Base URL comes from WATERMARKS_SERVICE_URL, default http://127.0.0.1:8765:

WM="${WATERMARKS_SERVICE_URL:-http://127.0.0.1:8765}"

The service is started either by the operator (docker compose up -d, or a published GHCR image) or locally (make serve). Always check it first, and stop with a clear message if it is unreachable — never fall back to local cleaning:

curl -sf "$WM/health"
# {"ok": true, "version": "..."}

If WATERMARKS_SERVER_API_KEY is set on the service, every request needs -H "Authorization: Bearer $WATERMARKS_SERVICE_API_KEY".

Capabilities

curl -s "$WM/capabilities"

Reports which optional tools are available server-side (c2patool, exiftool, qpdf, ghostscript), scorers present (scorers.stylometry, scorers.synthid, scorers.synthid_http), text-watermark detectors (text_detectors.markllm, text_detectors.claude-text), and which heavy backends are configured (pixel_backends.ctrlregen, pixel_backends.diffusion, harnesses.markllm). Drive your advice from this: only recommend pixel removal / SynthID scoring / vendor detection when the service reports the backend present.

Read the full file on GitHub · 373 lines

Files

What ships with it

6 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.

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. 2d ago Changed · +23 lines · +2 tokens per session bef308cdeffc
  2. 6d ago Changed · +11 lines bce434da0080
  3. 12d ago First seen · 339 lines · 136 tokens per session scan A daf1a6034f56

Subscribe to this mod's changes

remove-ai-marks is a skill published in the GitHub repository guillaumemeyer/watermarks-remover (21,743 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 4,908 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.