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/rune-kit/rune/claude-mdgit clone --depth 1 https://github.com/Rune-kit/runeWrote 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/rune-kit/rune/claude-md)<a href="https://agentmods.dev/instructions/rune-kit/rune/claude-md"><img src="https://agentmods.dev/badge/instructions/rune-kit/rune/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 | $0.03005 | $0.03005 |
| Opus 5 | $0.01503 | $0.01503 |
| Sonnet 5 | $0.00601 | $0.00601 |
| Haiku 4.5 | $0.00300 | $0.00300 |
Grade B, and why
rune CLAUDE.md scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
**Native skills (v2.23.0)**: 7 adapters emit to each platform's native Agent Skills dir — codex/antigravity `.agents/skills/`, cursor `.cursor/skills/`, windsurf `.windsurf/skills/`, copilot `.github/skills/`, gemini `.g How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rune — Project Configuration
Overview
Rune is an interconnected skill ecosystem for AI coding assistants. 67 core skills | 5-layer mesh architecture | 209 connections + 45 signals | Multi-platform. Philosophy: "Less skills. Deeper connections."
Works on: Claude Code (native plugin) · Cursor · Windsurf · Google Antigravity · OpenAI Codex · OpenCode · Aider · GitHub Copilot CLI · Gemini CLI · Qoder · Qwen Coder · any AI IDE.
Tech Stack
- Claude Code Plugin System (native)
- Multi-platform compiler (Node.js) — 13 adapters: Cursor, Windsurf, Antigravity, Codex, OpenCode, OpenClaw, Aider, GitHub Copilot CLI, Gemini CLI, Qoder, Qwen Coder, generic
- Agent Skills SKILL.md format
- Git for version control
- Markdown + JSON for configuration
- JavaScript for hooks/scripts
Directory Structure
rune/
├── .claude-plugin/ # Plugin manifest (Claude Code native)
│ ├── plugin.json # Plugin metadata
│ └── marketplace.json # Marketplace catalog
├── skills/ # Core skills — SINGLE SOURCE OF TRUTH
├── extensions/ # L4 extension packs (one dir per pack)
├── compiler/ # Multi-platform compiler
│ ├── bin/rune.js # CLI (init, build, doctor)
│ ├── parser.js # SKILL.md → IR
│ ├── transformer.js # Transform pipeline
│ ├── emitter.js # IR → platform files
│ ├── adapters/ # Platform adapters (claude, cursor, windsurf, antigravity, codex, openclaw, opencode, generic, aider, copilot, gemini, qoder, qwen)
│ └── transforms/ # Cross-refs, tool-names, frontmatter, subagents, hooks, branding
├── commands/ # Slash command definitions
├── agents/ # Subagent definitions
├── contexts/ # Behavioral mode injection (dev, research, review)
├── hooks/ # Event hooks (session-start, pre-compact, etc.)
├── scripts/ # Executable scripts for skills
└── docs/ # Documentation, templates, and plans
Mandatory Skill Routing
ALWAYS invoke skills via the Skill tool. NEVER "mentally apply" a skill or do the work casually.
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 · 158 lines · 3,005 tokens per session scan B d4a9bbae8309
rune CLAUDE.md is an instructions file published in the GitHub repository Rune-kit/rune (84 stars, last pushed 18d ago), licensed MIT. It adds 3,005 tokens to every session, about $0.0150 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
agent-orchestrator AGENTS.md
AGENTS.md instructions for Untrivial-ai/agent-orchestrator, covering agents.md, repo layout, commands, where to look first and distribution.
agent-orchestrator CLAUDE.md
Claude Code instructions for Untrivial-ai/agent-orchestrator, covering claude.md, app state lives under /.ao only and design system.
paperthin CLAUDE.md
Instructions for LilMGenius/paperthin, covering paperthin, philosophy, layout, skill.md format and disable-model-invocation: true ← user-invoked skills only.
maestro CLAUDE.md
Instructions for ReinaMacCredy/maestro: Read the local agent instructions in @AGENTS.md.
gossipcat-ai CLAUDE.md
Instructions for gossipcat-ai/gossipcat-ai, covering claude.md, gossipcat — multi-agent orchestration, your role, agent accuracy — skill development and scoped agent contract.
agent-skills-toolkit AGENTS.md
Instructions for product-on-purpose/agent-skills-toolkit, covering agents.md - agent-skills-toolkit, what this project is, current state (read before assuming capabilities), conventions and build / test / lint.