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 nortonx/ai-tooling-free --skill framework-upgrade-guidegit clone --depth 1 https://github.com/nortonx/ai-tooling-freeWrote 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/nortonx/ai-tooling-free/framework-upgrade-guide)<a href="https://agentmods.dev/skills/nortonx/ai-tooling-free/framework-upgrade-guide"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/framework-upgrade-guide/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/nortonx/ai-tooling-free/framework-upgrade-guide"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/framework-upgrade-guide.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 | $0.00133 | $0.02386 |
| Opus 5 | $0.00067 | $0.01193 |
| Sonnet 5 | $0.00027 | $0.00477 |
| Haiku 4.5 | $0.00013 | $0.00239 |
Grade A, and why
framework-upgrade-guide 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 8d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
[<path-to-repo-or-package.json>]
- Optional. Path to the target project root or its
package.json. If omitted, use the current working directory. - Examples:
/framework-upgrade-guide,/framework-upgrade-guide ./apps/web,/framework-upgrade-guide ../client/package.json
Copilot CLI note:
$ARGUMENTSdoesn't substitute in skills — include the argument inline in your prompt.
Framework upgrade guide
Analyze a JavaScript/TypeScript front-end project, determine where it stands relative to the latest stable release of its framework, and write a stepwise, minimum-impact upgrade guide to a file in the repo. The guide must walk the project up one major at a time wherever the framework requires it (Angular always; the others when codemods or breaking changes make a single jump unsafe), so the person executing it never has to reverse-engineer the order or guess which packages move together.
The whole point is to remove risk and guesswork from a major upgrade. A guide that lists "upgrade to the latest" without the intermediate hops, the lockstep version matrix, and the breaking changes per hop is worse than useless — it gives false confidence. Be specific and be honest about what will break.
Workflow
1. Detect — read only, never install
Read these from the target path (don't run npm install, builds, or anything that mutates state —
the project may be on someone else's machine and may not have node_modules):
package.json—dependencies,devDependencies,engines,packageManager.- The lockfile (
package-lock.json,yarn.lock, orpnpm-lock.yaml) — this has the exact resolved versions, whichpackage.jsonranges (^,~) do not. The resolved version is what you reason about. If no lockfile exists, say so prominently in the guide header — analysis falls back topackage.jsonranges, which may over- or under-state the installed versions. Ask the user to share the lockfile or paste the output of a read-onlynpm ls --depth=0. - Framework config:
angular.json,vite.config.*,vue.config.*,next.config.*,nuxt.config.*,remix.config.*(orvite.config.*importing@remix-run/*plugins) — these disambiguate the framework and toolchain. tsconfig.json(current TypeScript target/strictness),.nvmrc/.node-version(runtime).
What ships with it
3 files beside SKILL.md 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.
- 8d ago First seen · 189 lines · 133 tokens per session scan A b3864e5cf1c0
framework-upgrade-guide is a skill published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 24d ago), licensed MIT. It adds 133 tokens to every session and 2,386 once invoked, about $0.0007 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
remotion-saas
Building video apps with Remotion - framework, rendering and Player advice.
micro-frontend-architect
Expert guide for designing Micro-Frontend architectures using Webpack Module Federation, Vite Federation, and Single-SPA for large scale Vue and React applications.
web-3d-graphics-expert
Expert guide for WebGL and 3D graphics in the browser using Three.js, Babylon.js, React Three Fiber (R3F), and TresJS. Covers scene optimization, shaders, lighting, 3D model loading (GLTF/GLB), and performance tuning.
component-forge
Build production-grade components for React, Vue 3, and Svelte 5 with all states (loading, empty, error, success, idle), TypeScript strict, WCAG 2.2 accessibility, server components (RSC), and compound component patterns. Includes scaffold script, reference patterns, and template files for React and Vue. Use when user…
react-vitest
Use when adding or improving tests in a React project that uses Vitest — covers component testing with Testing Library, mocking hooks, and coverage configuration.
frontend-ui-design
Use when design and build production-grade UI components using React, Vue, or vanilla HTML/CSS. Create responsive layouts, design systems, and accessible interfaces. Use when designing and build production-grade ui components using react, vue, or.