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/maxvaega/skillkit/claude-mdgit clone --depth 1 https://github.com/maxvaega/skillkitWhat 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 | $0.04749 | $0.04749 |
| Opus 5 | $0.02374 | $0.02374 |
| Sonnet 5 | $0.00950 | $0.00950 |
| Haiku 4.5 | $0.00475 | $0.00475 |
Grade A, and why
skillkit 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skillkit
skillkit is a Python library that implements Anthropic's Agent Skills functionality, enabling LLM-powered agents to autonomously discover and utilize packaged expertise. The library provides:
- Multi-source skill discovery from personal directories, project directories, and plugins
- SKILL.md parsing with YAML frontmatter validation
- Progressive disclosure pattern (metadata loading → on-demand content)
- Framework integrations (LangChain, LlamaIndex, CrewAI, Haystack, Google ADK)
- Security features (path traversal prevention, permission checks)
- Model-agnostic design supporting Claude, GPT, Gemini, and open-source LLMs
Development Approach
This project follows a Vertical Slice MVP strategy to deliver working functionality quickly:
- v0.1 (Released): Core functionality + LangChain integration (sync only)
- v0.2 (Released): Async support + multi-source discovery + plugin integration
- v0.3 (Released): Script execution with security controls
- v1.0 (Planned): Additional framework integrations + production polish + comprehensive documentation + 90% test coverage
Current Focus (v0.4)
The v0.4 release implements advanced progressive disclosure with intelligent caching:
- LRU Content Cache: In-memory cache with configurable size (default: 100 entries)
- Mtime-based Invalidation: Automatic cache invalidation when SKILL.md files are modified
- Argument Normalization: Whitespace variations map to same cache entry for maximum efficiency
- Thread-Safe Concurrency: Per-skill asyncio locks enable safe parallel invocations
- Cache Management API: get_cache_stats(), clear_cache() for monitoring and control
- Performance: <1ms cache hits vs 10-25ms first invocation (up to 25x faster)
- Memory Efficient: ~2.1KB per cached entry, ~5MB cache overhead
- High Hit Rate: 80%+ cache hit rate achievable with typical usage patterns
- Script Integration: Script detection integrates with Level 2 caching lifecycle
- Backward Compatible: 100% compatible with v0.1/v0.2/v0.3 APIs
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 · 329 lines · 4,749 tokens per session scan A 3e68a30bb715
skillkit CLAUDE.md is an instructions file published in the GitHub repository maxvaega/skillkit (147 stars, last pushed 7mo ago), licensed MIT. It adds 4,749 tokens to every session, about $0.0237 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
swarms CLAUDE.md
Claude Code instructions for kyegomez/swarms, covering claude.md — swarms framework guide, installation & setup, any provider supported by litellm works, project layout and core primitive: agent.
opik python_sdk.instructions.md
Instructions for comet-ml/opik, covering opik python sdk code review guidelines, 🔧 core architecture principles, three-layer architecture, execution paths and 📋 api design standards.
opik copilot-instructions.md
Instructions for comet-ml/opik, covering copilot code review instructions, project overview, 1. git workflow & branch management, branch naming convention and commit message standards.
opik AGENTS.md
Instructions for comet-ml/opik, covering repository guidelines, scope & inheritance, project structure & module organization, build, test, and development commands and coding style & naming conventions.
dawnai AGENTS.md
Instructions for cacheplane/dawnai, covering agents.md, what this is (and isn't), workspace map, definition of done and conventions.
agent-operating-protocol AGENTS.md
Instructions for ryu-tada/agent-operating-protocol, covering agents.md - agent operating protocol, 0. instruction priority and trust boundaries, 1. core operating stance, 2. why high-agency agents feel strong and 3. default work loop.