ShadowAqueduct/watermark-remover
Plugin Claude Code
Agent skills for owned-content hygiene: hidden Unicode, sampling-based text watermarks, and C2PA/EXIF/XMP provenance metadata.
835 8d ago A
tokens not measured
original MIT
ShadowAqueduct/watermark-remover
Plugin Claude Code
Local hygiene for owned content: strip hidden Unicode (Layer A), weaken sampling watermarks via rewrite (Layer B), and drop C2PA/EXIF/XMP provenance from images, documents, and media. Bundles the HTTP-backed remove-ai-marks skill and the self-contained clean-user-facing-text skill.
835 8d ago A
tokens not measured
original MIT
PostToolUse
03ShadowAqueduct/watermark-remover
Hook
Runs after a tool call finishes for Write, Edit, MultiEdit and NotebookEdit tool calls, running python3. From ShadowAqueduct/watermark-remover.
835 8d ago A
tokens not measured
original MIT
ShadowAqueduct/watermark-remover
Cursor rule
Run text hygiene on natural-language content meant for readers.
835 8d ago A 166 tokens
original MIT
ShadowAqueduct/watermark-remover
Skill Claude CodeCodex
Audit and finalize authorized natural-language text meant for readers: strip suspicious invisible Unicode, then rewrite prose while keeping facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI…
835 8d ago A 121 tokens
original MIT
ShadowAqueduct/watermark-remover
Skill Claude CodeCodex
Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…
835 8d ago A 135 tokens
original MIT