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 uxname/LiteStack --skill new-projectgit clone --depth 1 https://github.com/uxname/LiteStackWrote 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/uxname/litestack/new-project)<a href="https://agentmods.dev/skills/uxname/litestack/new-project"><img src="https://agentmods.dev/badge/skills/uxname/litestack/new-project/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/uxname/litestack/new-project"><img src="https://agentmods.dev/badge/skills/uxname/litestack/new-project.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 | $0.00061 | $0.00769 |
| Opus 5.5 | $0.00024 | $0.00308 |
| Sonnet 5.5 | $0.00012 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade C, and why
new-project 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 11d 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.
then `rm -rf .git && git init` inside it — the project starts its own history. How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The deliverable is a meta-repo with backend/ and frontend/ submodules pointing at the
team's own repos (DERIVED mode), renamed off the template identity and running. The
mechanics are written down already — .agents/DERIVE.md for
repointing and renaming, docs/ENV-CONTRACT.md for the env
pairs. This skill covers only the parts that need a human.
Ask first
- Project name (machine): lowercase
[a-z0-9-], e.g.acme-portal— it becomes npm package names, the docker network and the theme store key. - Display brand (optional; default = Title-Cased name).
- Git host + owner for the three repos, and the target directory.
Then, in order
- Create three empty remote repos (meta, backend, frontend) on the team's host — via
gh/glab, or ask the user for the URLs. Push nothing yet. - Scaffold:
git clone --recurse-submodules https://github.com/uxname/LiteStack <dir>, thenrm -rf .git && git initinside it — the project starts its own history. - Repoint submodules and remotes at the three URLs, per
.agents/DERIVE.md. When.gitmodulesno longer points atuxname/*, the project is in DERIVED mode (.agents/OPERATING-MODE.md) and nothing will ever push to the templates again. Done when both submodule URLs and all threeoriginremotes point at the team's repos — a real product left onuxname/*pushes into the public templates. - Rename:
scripts/rename-project.sh --name <name> --display "<Brand>" --repo-owner <owner>— before installing, because it rewrites the Go module path and package names. - Install and verify:
scripts/setup.sh— one command; it checks the toolchain, writes both.envfiles and runsscripts/doctor.sh. Fix any contract mismatch it reports; these fail silently at runtime otherwise. - Run it:
cd backend && task start:dev,cd frontend && npm run start:dev. It worked whenhttp://localhost:3000andhttp://localhost:4000/readyzboth answer. - Commit and push with the meta
/commitskill. Confirm with the user first — this is the project's first push.
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.
- 11d ago Changed · -3 lines · -49 tokens per session a4d4adec4a97
- 1mo ago Changed · -76 lines 6a9daa05e7be
- 1mo ago Changed f1158383e0a3
- 1mo ago Changed · -1 lines dbecb846cc2d
- 1mo ago First seen · 128 lines · 110 tokens per session scan C 8da7a751a808
new-project is a skill published in the GitHub repository uxname/LiteStack (2 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 769 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…