gemini-watermark-and-synthid-remover: Instructions file for Claude Code

CLAUDE.md

gemini-watermark-and-synthid-remover CLAUDE.md is an instructions file for Claude Code from froggeric/gemini-watermark-and-synthid-remover. It costs 25,625 tokens per session, scanned D, original, MIT.

A project guidance file for a C++ tool that detects and removes watermarks and SynthID markers from images, then optionally fills the affected areas and denoises the result.

In plain words
What is it for?
Use it to build the watermark-removal program, run its tests, configure OpenCV and FFmpeg dependencies, and choose whether optional denoising is enabled.
Why use it?
It records the supported build methods, dependencies, and pipeline settings so the tool can be compiled and tested reliably on macOS.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is froggeric/gemini-watermark-and-synthid-remover's own configuration. It tells Claude Code how to work on gemini-watermark-and-synthid-remover itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gemini-watermark-and-synthid-remover configures →

Reuse

Borrowing it

Nothing to install: this file belongs to froggeric/gemini-watermark-and-synthid-remover. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/froggeric/gemini-watermark-and-synthid-remover/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/froggeric/gemini-watermark-and-synthid-remover

Made for: Claude Code.

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 gemini-watermark-and-synthid-remover CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/froggeric/gemini-watermark-and-synthid-remover/claude-md/github.svg)](https://agentmods.dev/instructions/froggeric/gemini-watermark-and-synthid-remover/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/froggeric/gemini-watermark-and-synthid-remover/claude-md"><img src="https://agentmods.dev/badge/instructions/froggeric/gemini-watermark-and-synthid-remover/claude-md/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 gemini-watermark-and-synthid-remover CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/froggeric/gemini-watermark-and-synthid-remover/claude-md"><img src="https://agentmods.dev/badge/instructions/froggeric/gemini-watermark-and-synthid-remover/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25,625 This file is loaded in full into every session.
When invoked 25,625 The same file — it is already loaded in full.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.25625 $0.25625
Opus 5.5 $0.10250 $0.10250
Sonnet 5.5 $0.05125 $0.05125
Haiku 4.5 $0.02562 $0.02562

Measured 1mo ago against content hash db83316e4fd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

gemini-watermark-and-synthid-remover CLAUDE.md scanned grade D with 3 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 1mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **Broken CommandLineTools SDK (link fails with `tapi error: malformed file` / `unknown architecture arm64e.x1-macos`):** xcode-select points at CLT whose SDK tbds the current linker cannot parse. Build via Xcode's SDK

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **HF model uploads (`froggeric/wmr`):** use `hf upload froggeric/wmr <local> <path-in-repo>` (NOT `huggingface-cli`, which is deprecated and no-ops); it auto-uses the cached `~/.cache/huggingface/token` and auto-tracks

Makes network callslowCapability

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

- **Download progress + leftover cleanup (1.16.11):** an HF fetch is 302 -> CDN and curl fires the xferinfo cb during the redirect body too, reporting the ~1 KB redirect page's Content-Length as the total; `download_pinn
CLAUDE.md · 651 lines

How it starts

The opening of the file, as written. The whole thing — 651 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build Commands

Recommended (macOS/Homebrew), resilient to brew upgrade:

scripts/build.sh                 # Release build + tests; self-heals a stale cache
BUILD_TYPE=Debug scripts/build.sh
RUN_TESTS=0 scripts/build.sh     # build only

scripts/build.sh verifies the required Homebrew formulas, auto-wipes + reconfigures when a cached dependency path has vanished after an upgrade, and configures against the stable /opt/homebrew/opt/… symlinks. Binaries: build/wmr, build/tests/wmr_tests. Test suite needs Catch2 (brew install catch2).

Or, arm64 preset: cmake --preset mac-homebrew-Release && cmake --build --preset mac-homebrew-Release.

System libs (macOS/Homebrew), manual, no vcpkg:

cmake -B build -S . -GNinja \
  -DCMAKE_PREFIX_PATH="$(brew --prefix opencv);$(brew --prefix ffmpeg);$(brew --prefix catch2);$(brew --prefix fmt);$(brew --prefix spdlog);$(brew --prefix cli11)" \
  -DOpenCV_DIR=$(brew --prefix opencv)/lib/cmake/opencv4 \
  -DFFMPEG_ROOT=$(brew --prefix ffmpeg) \
  -DWMR_BUILD_TESTS=ON
cmake --build build

vcpkg (all platforms):

cmake -B build -S . -GNinja
cmake --build build

Tests:

ctest --test-dir build --output-on-failure
./build/tests/wmr_tests "[v2]"          # single tag (path: tests/wmr_tests)

Integration tests need project root as CWD (they look for test-images/ relative to CWD). Tests use SKIP macro if test data is absent, so they don't fail without it.

Architecture

Single-pass C++20 CLI tool. No libraries, everything compiles into one wmr executable.

Pipeline: Detect → Remove → Inpaint

WatermarkEngine (src/core/) orchestrates the image pipeline:

  1. NccDetector (detection/), 3-stage NCC: spatial template match (cv::matchTemplate), gradient match (Sobel magnitudes), variance analysis. Fusion: spatial×0.50 + gradient×0.30 + variance×0.20. Threshold: 0.35.
  2. Reverse alpha blend (core/blend_modes), original = (watermarked - alpha*255) / (1-alpha). Alpha maps decoded from embedded PNGs (assets/embedded_assets.hpp).
  3. Inpaint (core/inpaint) — OFF by default since 1.14.0: the default is the pure reverse-alpha-blend (the exact inversion). The opt-in --denoise ns|telea cleanup is residual-only (predicts clean content with cv::inpaint and blends it in only where the reverse-blend left a real residual, never blurring a clean removal).

Read the full file on GitHub · 651 lines

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. 1mo ago Changed · +9 lines · +676 tokens per session scan C → D db83316e4fd3
  2. 1mo ago Changed · +15 lines · +304 tokens per session f3d4fb90bf0c
  3. 1mo ago Changed · +51 lines · +895 tokens per session 72d9db2d2489
  4. 1mo ago Changed · +155 lines · +3,394 tokens per session 954d528421b6
  5. 2mo ago Changed · +8 lines · +822 tokens per session a04a29dfcbc5
  6. 2mo ago First seen · 413 lines · 19,534 tokens per session scan C 007283a21a2c

Subscribe to this mod's changes

gemini-watermark-and-synthid-remover CLAUDE.md is an instructions file published in the GitHub repository froggeric/gemini-watermark-and-synthid-remover (122 stars, last pushed 1mo ago), licensed MIT. It adds 25,625 tokens to every session, about $0.1025 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

gemini-watermark-and-synthid-remover CLAUDE.md compared with instructions from other repositories

gemini-watermark-and-synthid-remover CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gemini-watermark-and-synthid-remover CLAUDE.mdfroggeric/gemini-watermark-and-synthid-removerInstructions file1221mo agoMITD25,625Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot