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 skills/chaxus/ran/ranutsnpx skills add chaxus/ran --skill ranutsgit clone --depth 1 https://github.com/chaxus/ranWhat 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 | $0.00109 | $0.01557 |
| Opus 5 | $0.00055 | $0.00779 |
| Sonnet 5 | $0.00022 | $0.00311 |
| Haiku 4.5 | $0.00011 | $0.00156 |
Grade A, and why
ranuts scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import `ranuts/node` in browser code** — it pulls in `fs`/`http`/`child_process`. How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ranuts — utility library
A broad, tree-shakeable utility toolkit. Four independent entry points; import from the
subpath, never from ranuts/dist/... or the internal @/... alias.
Authoritative reference (read for exact signatures — don't guess)
When ranuts is installed, its docs ship inside the package:
node_modules/ranuts/docs/API.md— the full generated function reference forranuts/utils(signatures + one-line descriptions). This is the source of truth.node_modules/ranuts/CLAUDE.md— usage guide: entry-point map, project layout, thevisual/engine, conventions, and gotchas.
Import map
| Import from | What | Runtime |
|---|---|---|
ranuts |
Root barrel — re-exports utils + visual surface | browser + node |
ranuts/utils |
DOM/BOM, string, object, number, color, time, reactivity | browser + node* |
ranuts/node |
HTTP server, router, ws, fs, streams, middleware | node only |
ranuts/visual |
2D rendering engine (Canvas / WebGL / WebGPU) | browser only |
ranuts/vnode |
Snabbdom-style virtual DOM (h, init, modules) |
browser |
ranuts/stream |
SSE parsing + provider-neutral streamed-response fold | browser + node |
ranuts/conversation |
Event log → renderable conversation nodes | browser + node |
* Most ranuts/utils functions are browser-oriented (touch window/document) but
guard with typeof window/document !== 'undefined'; pure helpers run anywhere. Never
import ranuts/node in browser code — it pulls in fs/http/child_process.
ranuts/utils — frequently used
Reactivity: createSignal(value, opts?) → [getter, setter] (signal primitive).
Timing: throttle, debounce, generateThrottle, durationHandler, getFrame.
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 · 125 lines · 109 tokens per session scan A 3bba81b80df9
ranuts is a skill published in the GitHub repository chaxus/ran (272 stars, last pushed 6d ago), licensed MIT. It adds 109 tokens to every session and 1,557 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
authoring-components
Guide for creating new Elements components with all required files, base classes, metadata patterns, and test boilerplate. Use this skill whenever the user wants to create, scaffold, or set up a new component from scratch, needs to understand the required 10-file structure, asks about base classes and mixins…
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
next-rspack
Maintain @next/rspack-core and @next/rspack-binding packages. Use when editing rspack/package.json, rspack/crates/binding/Cargo.toml, rspack/rust-toolchain.toml, or packages/next-rspack/package.json. Covers upgrading @rspack/core npm version, rspack crate versions, Rust toolchain version, building and linking for…
next-dev-loop
Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app — not just that it compiles or type-checks. Combines /next/mcp (Next.js's view) with agent-browser (the browser's view). Requires a running next dev.
textual-screenshot
Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.
frontend-unit-testing
Write comprehensive, behaviour-driven unit tests for Gradio frontend Svelte components using Vitest browser mode, Playwright, and the @self/tootils test utilities.