Borrowing it
Nothing to install: this file belongs to RedactDesk/redactdesk-mac. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RedactDesk/redactdesk-mac/main/CLAUDE.mdgit clone --depth 1 https://github.com/RedactDesk/redactdesk-macWrote 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/instructions/redactdesk/redactdesk-mac/claude-md)<a href="https://agentmods.dev/instructions/redactdesk/redactdesk-mac/claude-md"><img src="https://agentmods.dev/badge/instructions/redactdesk/redactdesk-mac/claude-md.svg" alt="Measured on agentmods" 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 | $0.03284 | $0.03284 |
| Opus 5 | $0.01642 | $0.01642 |
| Sonnet 5 | $0.00657 | $0.00657 |
| Haiku 4.5 | $0.00328 | $0.00328 |
Grade A, and why
redactdesk-mac CLAUDE.md 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 7d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Orientation for Claude Code (and any AI collaborator) working in this repo.
What this project is
RedactDesk is an open-source (MIT) macOS app that redacts PII from PDFs entirely on-device. Text model + PDFKit + SwiftUI. The user name shown in-app and in marketing is "RedactDesk"; the Xcode target + source folders are still named "PII Redactor" from the original template (soft-rename - renaming the folders involves a risky pbxproj shuffle, deferred).
The bundle ID is com.kamban.redactdesk. The display name, bundle ID,
and all user-facing copy were renamed from the previous "SafePaste"
branding; the on-disk Xcode target and folder names were intentionally
left alone.
Distribution: direct download from the team's website, not the Mac App Store. Repo is MIT so anyone can build from source for free; the signed, notarized binary is sold as a separate paid download. Don't propose MAS submission work (StoreKit receipt validation, MAS sandbox quirks, App Store Connect pricing) - it's explicitly off the roadmap.
The underlying ML pipeline is openai/privacy-filter (a token-classification
model) running via ONNX Runtime with the CoreML execution provider. Exported
PDFs use image-rewrite redaction: each page is rasterized, black boxes are
painted over PII rectangles, and the result is a new PDF with no recoverable
text layer for the redacted regions.
Build / run commands
# Debug build on Apple Silicon
xcodebuild -project "PII Redactor.xcodeproj" \
-scheme "PII Redactor" -configuration Debug \
-destination "platform=macOS,arch=arm64" build
# Universal Release (arm64 + x86_64)
xcodebuild -project "PII Redactor.xcodeproj" \
-scheme "PII Redactor" -configuration Release \
-destination "generic/platform=macOS" \
ARCHS="arm64 x86_64" ONLY_ACTIVE_ARCH=NO build
# Resolve SPM deps (fixes "failed downloading" cache errors)
xcodebuild -project "PII Redactor.xcodeproj" -resolvePackageDependencies
The model is not bundled in the repo or the .app. First launch
downloads the ~917 MB ONNX weights from HuggingFace Hub into
~/Library/Containers/com.kamban.redactdesk/Data/Library/Caches/huggingface/
and runs ModelMerger once to produce a self-contained merged .onnx.
Subsequent launches reuse that cached file with no network.
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.
- 7d ago First seen · 229 lines · 3,284 tokens per session scan A 0240e542d2ba
redactdesk-mac CLAUDE.md is an instructions file published in the GitHub repository RedactDesk/redactdesk-mac (53 stars, last pushed 3mo ago), licensed MIT. It adds 3,284 tokens to every session, about $0.0164 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.