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.
/plugin marketplace add Rune-kit/runenpx agentmods add plugins/rune-kit/rune/marketplacegit clone --depth 1 https://github.com/Rune-kit/runeGrade A, and why
rune-kit 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "rune-kit",
"description": "Less skills. Deeper connections. A lean, interconnected skill ecosystem for Claude Code — 66 skills, 248 connections, 45 signals, and runtime auto-discipline.",
"owner": {
"name": "Rune Contributors"
},
"plugins": [
{
"name": "rune",
"source": "./",
"description": "66 skills wired into a 5-layer mesh — 248 connections + 45 signals, adaptive routing, mesh analytics, logic preservation, and native lifecycle hooks. The compiler targets 13 runtimes including Claude Code and OpenAI Codex.",
"version": "2.32.0",
"author": {
"name": "Rune Contributors"
},
"homepage": "https://rune-kit.github.io/rune",
"repository": "https://github.com/rune-kit/rune",
"license": "MIT",
"category": "workflow"
},
{
"name": "@rune/ui",
"source": "./extensions/ui",
"description": "Frontend UI patterns — design systems, accessibility, animation",
"category": "frontend"
},
{
"name": "@rune/backend",
"source": "./extensions/backend",
"description": "Backend patterns — API, auth, database, middleware",
"category": "backend"
},
{
"name": "@rune/devops",
"source": "./extensions/devops",
"description": "DevOps — Docker, CI/CD, monitoring, server setup",
"category": "devops"
},
{
"name": "@rune/mobile",
"source": "./extensions/mobile",
"description": "Mobile — React Native, Flutter, app store, native bridge",
"category": "mobile"
},
{
"name": "@rune/security",
"source": "./extensions/security",
"description": "Deep security — OWASP audit, pentest, compliance",
"category": "security"
},
{
"name": "@rune/trading",
"source": "./extensions/trading",
"description": "Fintech — real-time data, charts, indicators, trade logic preservWhat ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 108 lines scan A fc58e52d5705
rune-kit is a plugin published in the GitHub repository Rune-kit/rune (84 stars, last pushed 17d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
paperthin
Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.
jaiskills
Orchestration (insistir, constatar, remoto), prompting (metaprompt), knowledge compounding, file-based TODOs, and OpenAI tooling (askcodex, image-to-frontend) as one Claude Code plugin.
jaiskills
Jairo's agent skills for Claude Code — orchestration, verification, prompting, and OpenAI tooling in one plugin.
missing-codex-manifest
Anti fixture: declares claude+codex agent-targets but ships no .codex-plugin manifest, to trip S6.
agent-skills
Plugin marketplace listing 1 plugin: agent-skills.
claude-wave-plugin
Wave-based engineering execution for Claude Code. Vendors the full v2 framework — 17-phase pipeline plus conditional [DR] (UI waves) and [CR] (opt-in) gates, model-routed across Opus/Sonnet/Haiku, hook-enforced invariants, worktree isolation — plus a polished 5-phase demo subset for live segments and small UI features.