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/kubiyabot/skill/claude-mdgit clone --depth 1 https://github.com/kubiyabot/skillWrote 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/kubiyabot/skill/claude-md)<a href="https://agentmods.dev/instructions/kubiyabot/skill/claude-md"><img src="https://agentmods.dev/badge/instructions/kubiyabot/skill/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 | $0.01633 | $0.01633 |
| Opus 5 | $0.00816 | $0.00816 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
skill 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 4d 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 — 189 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.
Project Overview
Skill is a universal skill runtime for AI agents that executes tools in a sandboxed WASM environment. It provides both CLI commands and MCP (Model Context Protocol) server capabilities for AI agent integration.
Build & Development Commands
# Setup (one-time)
rustup target add wasm32-wasip1 # Required for WASM skill compilation
# Build
cargo build # Debug build
cargo build --release # Release build (optimized for size)
cargo build --profile release-fast # Fast compile with speed optimization
# Test
cargo test --workspace # Run all tests
cargo test -p skill-cli # Test specific crate
cargo test -p skill-cli test_name # Run single test by name
cargo test -p skill-cli --lib -- claude_bridge # Test claude_bridge module
cargo test -p skill-runtime -- --test-threads=1 # Serial execution for flaky tests
./tests/mcp_integration_tests.sh # MCP protocol tests
./tests/run-all-tests.sh # Full test suite
# Snapshot testing (uses insta crate)
cargo insta test # Run snapshot tests
cargo insta review # Review and accept new snapshots
# Benchmarks
cargo bench -p skill-cli # Run benchmarks (claude_bridge_bench)
# Lint & Format
cargo fmt --all # Format code
cargo clippy --all-targets -- -D warnings # Lint
# Coverage
cargo tarpaulin --workspace --out Html # Generate HTML coverage report
# Install locally
cargo install --path crates/skill-cli
# Documentation site (VitePress)
cd docs-site && npm install # One-time setup
cd docs-site && npm run dev # Local dev server
cd docs-site && npm run build # Production build
Architecture
Crate Structure
crates/
├── skill-cli/ # Main binary - CLI commands, Claude bridge, auth
├── skill-runtime/ # Core execution engine - WASM, Docker, native runners
├── skill-mcp/ # MCP server implementation (stdio transport)
├── skill-http/ # HTTP streaming server for web clients
├── skill-web/ # Yew-based WebAssembly UI
└── skill-context/ # Shared types and context
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.
- 4d ago First seen · 189 lines · 1,633 tokens per session scan A ee6b4f78a9f3
skill CLAUDE.md is an instructions file published in the GitHub repository kubiyabot/skill (16 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 1,633 tokens to every session, about $0.0082 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.