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.
npx agentmods add instructions/crossoverjie/skilldeck/claude-mdgit clone --depth 1 https://github.com/crossoverJie/SkillDeckWhat 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 | $0.01986 | $0.01986 |
| Opus 5 | $0.00993 | $0.00993 |
| Sonnet 5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
SkillDeck 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 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.
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 — 131 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.
Code Style: Comments Required
The author has extensive Java/Golang/Python experience but is new to Swift and macOS app development. All generated code must include detailed comments in English explaining:
- Swift-specific syntax and language features (e.g.,
@Observable,actor,some View, property wrappers) - SwiftUI concepts and view lifecycle (e.g.,
.task,.environment(),NavigationSplitView) - macOS/Apple platform APIs (e.g.,
NSWorkspace,DispatchSource,FileManager) - Why a particular Swift pattern is used when it differs from the Java/Go/Python equivalent
Build & Run Commands
swift build # Development build
swift build -c release # Optimized release build
swift run SkillDeck # Build and launch the app
open Package.swift # Open in Xcode (Cmd+R to run)
swift test # Run all tests
swift test --filter SkillMDParserTests # Run one test class
swift test --filter SkillMDParserTests/testParseStandardSkillMD # Run one test method
swift package clean # Clean build artifacts
First build downloads dependencies (Yams, swift-markdown, swift-collections).
Architecture
MVVM with @Observable (macOS 14+). The filesystem is the database — skills are directories containing SKILL.md files.
Views → ViewModels (@Observable) → SkillManager (@Observable) → Services (actor)
SkillManager (Services/SkillManager.swift) is the central orchestrator — injected into the view tree via .environment(). It coordinates all sub-services and exposes the public API that ViewModels call.
Services use Swift actor for thread-safe file system access:
- SkillScanner — scans
~/.agents/skills/and per-agent directories, deduplicates via symlink resolution - LockFileManager — reads/writes
~/.agents/.skill-lock.jsonwith atomic writes and caching - AgentDetector — detects installed agents by checking CLI binaries (
which) and config directories - SymlinkManager — static methods for creating/removing symlinks between canonical and agent directories
- FileSystemWatcher — DispatchSource/FSEvents monitoring with 0.5s debounce, publishes via Combine
- GitService — executes git CLI operations (clone, pull, fetch) for GitHub-based skill installs
- UpdateChecker — compares local vs remote commit hashes to detect skill updates
- SkillRegistryService — fetches skills from skills.sh registry API
- ClawHubService — fetches skills from ClawHub catalog for OpenClaw
- TranslationService — inline Chinese translation of skill docs (macOS 26+ Translation framework)
- KeychainService — stores/retrieves proxy credentials from macOS Keychain
- NetworkSessionProvider — provides URLSession instances with proxy configuration applied
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.
- 2d ago First seen · 131 lines · 1,986 tokens per session scan A a810c92bbf1e
SkillDeck CLAUDE.md is an instructions file published in the GitHub repository crossoverJie/SkillDeck (552 stars, last pushed 1mo ago), licensed MIT. It adds 1,986 tokens to every session, about $0.0099 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
Applite CLAUDE.md
Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.
scarf AGENTS.md
Instructions for awizemann/scarf: This repo carries its own agent memory — plain files in git, served by the in-repo memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the memophant markers…
scarf copilot-instructions.md
Instructions for awizemann/scarf: File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass sourcepaths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be kept…
skills-manager CLAUDE.md
Instructions for yibie/skills-manager, covering skills manager - development guide, tui engine: blessed, 核心原则, 参考文档 and 正确的 list 用法.
mectrics AGENTS.md
Instructions for farukkamcici/mectrics, covering agents.md — working agreement for mectrics, 0. golden rule: english-only repository, 1. project shape, 2. internationalization (i18n) and 3. menu bar rendering rules.
skills-manager AGENTS.md
Instructions for yibie/skills-manager, covering repository agent instructions and ui and interaction work.