remove-ai-marks

remove-ai-marks is a skill for Claude Code from ShadowAqueduct/watermark-remover. It costs 135 tokens per session (3,468 once invoked), scanned A, original, MIT.

A file-cleaning tool for removing hidden text marks and provenance data associated with AI-generated content.

In plain words
What is it for?
It is for checking or cleaning text and removing C2PA, EXIF, XMP, or related metadata from images, documents, media, and web files.
Why use it?
It helps remove hidden Unicode, sampling watermarks, and metadata from content you own when those marks should not remain.

Skill for Claude Code

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

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

Good fit It is for checking or cleaning text and removing C2PA, EXIF, XMP, or related metadata from images, documents, media, and web files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shadowaqueduct/watermark-remover/remove-ai-marks
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 ShadowAqueduct/watermark-remover --skill remove-ai-marks
Clone the repo
git clone --depth 1 https://github.com/ShadowAqueduct/watermark-remover

Made for: Claude Code.

Or install watermark-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/shadowaqueduct/watermark-remover/remove-ai-marks/github.svg)](https://agentmods.dev/skills/shadowaqueduct/watermark-remover/remove-ai-marks)
Your own site
<a href="https://agentmods.dev/skills/shadowaqueduct/watermark-remover/remove-ai-marks"><img src="https://agentmods.dev/badge/skills/shadowaqueduct/watermark-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/shadowaqueduct/watermark-remover/remove-ai-marks"><img src="https://agentmods.dev/badge/skills/shadowaqueduct/watermark-remover/remove-ai-marks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,468 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
  • 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 75
    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 112
    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 82
    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 134
    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 145
    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 125
    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 234
    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 234
    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 $0.00135 $0.03468
Opus 5 $0.00068 $0.01734
Sonnet 5 $0.00027 $0.00694
Haiku 4.5 $0.00014 $0.00347

Measured 10d ago against content hash f3cb9ca7b145, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 10d 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.

This skill is a **thin HTTP client**. All deterministic cleaning lives in this repo’s `service/`. The agent host does not need Python, venvs, or cleaner binaries. Call the service with `curl`. Never run cleaning scripts
skills/remove-ai-marks/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remove AI marks

Hygiene for text (Unicode + statistical rewrite) and files (C2PA / AI metadata on common containers).

Read when 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

This skill is a thin HTTP client. All deterministic cleaning lives in this repo’s service/. The agent host does not need Python, venvs, or cleaner binaries. Call the service with curl. Never run cleaning scripts on the host.

Reach the service

Base URL: WATERMARKS_SERVICE_URL, default http://127.0.0.1:8765.

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

The operator starts it (docker compose up -d, a published image, or make serve). Probe it first. If it is down, stop with a clear message — do not 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"

Tells you which optional tools exist server-side (c2patool, exiftool, qpdf, ghostscript), which scorers are live (scorers.stylometry, scorers.synthid, scorers.synthid_http), which text detectors are wired (text_detectors.markllm, text_detectors.claude-text, text_detectors.gumbel), and which heavy backends are configured (pixel_backends.ctrlregen, pixel_backends.diffusion, harnesses.markllm). Only recommend pixel removal / SynthID scoring / vendor detection when capabilities say the backend is present.

HTTP API

Payloads are JSON; the file is base64. Decode the cleaned field yourself and write the output path.

Read the full file on GitHub · 268 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. 10d ago First seen · 268 lines · 135 tokens per session scan A f3cb9ca7b145

Subscribe to this mod's changes

remove-ai-marks is a skill published in the GitHub repository ShadowAqueduct/watermark-remover (835 stars, last pushed 17d ago), licensed MIT. It adds 135 tokens to every session and 3,468 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.

Related

Other skills, from other repositories

repo-visuals

Create hero visuals — animated GIF, static PNG, or animated SVG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML/SVG, previews it in the browser, and exports. Use when the user asks for a README…

livlign/claude-skills · 112 tokens

ghost-decode

Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.

haroontrailblazer/ghost-font-decoder · 64 tokens

preview_card

Compose a finished run's social SHARE CARD (the chart background + dark scrim + hero headline) and rasterize it to PNG so it can be eyeballed without opening the report GUI in a browser. Use it to check the thing the GUI's client-side PNG actually ships — most importantly, whether the chart lines survive the…

zapgun-ai/clawback · 145 tokens

meta-ads-creative

Create evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC concepts, creative briefs, new ad concepts, or creative refreshes.

nowork-studio/notfair-plugin · 59 tokens

paid-ads-creative

Create grounded paid-media creative concepts, copy angles, refresh hypotheses, and measurable test briefs across advertising platforms. Use for ad copy, creative briefs, UGC concepts, headlines, creative fatigue, asset ideas, or a creative refresh.

nowork-studio/notfair-plugin · 52 tokens

youtube-producer

Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…

cbrock84/headcount · 86 tokens