🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
README badges and charts for shadcn ui
shieldcn turns README metadata into styled badges, charts, headers, sponsor walls, and contributor blocks. It works from hosted image URLs, a GitHub Action, and a skill pack so agents can add the right markdown for you.
Builders who want agent-ready README badges, charts, and header blocks for GitHub projects.
You can add polished README visuals and keep them updated without building the images yourself.
What it does
Hosted badge URLs
Generate badges directly from URLs like `/npm/react.svg` or `/github/vercel/next.js/stars.svg` and paste them into markdown.
Star history charts
Render public repo star history at `/chart/github/stars/{owner}/{repo}.svg`, with SVG, PNG, and JSON outputs.
GitHub Action
Use `jal-co/shieldcn@v1` to commit light and dark star chart SVGs into a repository.
Agent skill pack
Install `skills/shieldcn-badges/SKILL.md` so Claude Code or Cursor can add shieldcn badges and charts from prompts.
Web studio and docs
Use the web app and docs site for badge setup, chart options, and examples.
How to get it
- 1Install the shieldcn-badges skill from skills.sh so your coding agent can add shieldcn…
npx skills add jal-co/shieldcn -a claude-code # installs to Claude Code npx skills add jal-co/shieldcn -a cursor # installs to Cursor
README
Before anyone reaches your docs, they land on your README, the front door of every open-source project. shieldcn makes that first impression count: badges, charts, headers, and sponsor walls, rendered as real shadcn/ui components. A shields.io alternative.
Usage
Drop a badge into any README and it renders as a real shadcn Button.



Agent skill
Install the shieldcn-badges skill from skills.sh so your
coding agent can add shieldcn badges, charts, and headers to READMEs:
npx skills add jal-co/shieldcn -a claude-code # installs to Claude Code
npx skills add jal-co/shieldcn -a cursor # installs to Cursor
See skills/shieldcn-badges/SKILL.md for
prompt examples and options.
Star history
Hosted star charts use GitHub's privacy-safe weekly history API. Embed
https://shieldcn.dev/chart/github/stars/{owner}/{repo}.svg for any public
repository, or use .png and .json at the same path.
To commit a light/dark SVG pair to your repo, use the shieldcn starchart GitHub Action:
- uses: jal-co/shieldcn@v1
with:
theme: violet
pull-request: true
PR mode needs contents: write, pull-requests: write, and permission for
Actions to create pull requests in repository settings.
GitHub Action docs → · action reference
Sponsors
Contributors
MIT · Built by Justin Levine · Contribute
Files in the repo
- .github
- .husky
- .tegami
- packages
- scripts
- skills
- .gitattributes
- .gitignore
- action.yml
- AGENTS.md
- commit-check.toml
- LICENSE
- package.json
- pnpm-lock.yaml
- pnpm-workspace.yaml
- PRODUCT.md
- README.md
- turbo.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More tools
The best-benchmarked open-source AI memory system. And it's free.
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.