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 skills add KiWi233333/JiwuChat --skill docsgit clone --depth 1 https://github.com/KiWi233333/JiwuChatWrote 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/skills/kiwi233333/jiwuchat/docs)<a href="https://agentmods.dev/skills/kiwi233333/jiwuchat/docs"><img src="https://agentmods.dev/badge/skills/kiwi233333/jiwuchat/docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kiwi233333/jiwuchat/docs"><img src="https://agentmods.dev/badge/skills/kiwi233333/jiwuchat/docs.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00041 | $0.04488 |
| Opus 5.5 | $0.00016 | $0.01795 |
| Sonnet 5.5 | $0.00008 | $0.00898 |
| Haiku 4.5 | $0.00004 | $0.00449 |
Grade C, and why
jiwuchat-quickstart scanned grade C 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules pnpm-lock.yaml && pnpm install The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 1mo ago First seen · 462 lines · 41 tokens per session scan C c17870c04da7
jiwuchat-quickstart is a skill published in the GitHub repository KiWi233333/JiwuChat (751 stars, last pushed 13d ago), licensed AGPL-3.0. It adds 41 tokens to every session and 4,488 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
slidev
Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.
Cypress v14 Component Testing
Component testing patterns with Cypress v14 including React, Vue, and Angular component mounting, custom mount commands, interaction testing, visual snapshots, and integration with Vite and Webpack bundlers.
chags
Use when building or extending CHAGS (Chinese Historical Anecdotes Game Series): each Chinese historical anecdote is one small kids game built with Phaser 4.2 inside a Vue 3.5 + Pinia shell (TypeScript 5.9.3, Vite 8, pnpm workspace, zh/en bilingual). Covers the GameModule/GameContext contract, gameplay template…
ai-water-front
Use when building a Vue 3 smart-water map dashboard demo that pairs OpenLayers with a Dify AI chat assistant — natural-language queries rendered as GeoJSON highlights, GeoServer REST layer management, streaming SSE replies, and resizable panels. Stack: Vue 3.3 + Vite 4 + ol 8 + axios, dev proxy carrying Basic auth to…
map-360-demo
Use when exploring, running or extending map-360-demo — a Vue 3 + Vite + TypeScript frontend demo that bidirectionally links Photo Sphere Viewer v5 panoramas (equirectangular and cubemap) with a Leaflet plan map. Covers virtual tour arrows, marker CRUD with search and JSON import/export, panorama-yaw to GPS coordinate…
openlayers-vue3-demo
Use when building OpenLayers maps with Vue 3 declarative components (vue3-openlayers) — WMS tile layers, dynamic layer trees loaded from the GeoServer REST API, layer-switcher/zoom/scale-line/context-menu controls, and a Vite dev proxy injecting Basic auth. Bilibili livestream demo for a one-map GIS dashboard on…