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 Robot-Inventor/agent-skills --skill web-mastergit clone --depth 1 https://github.com/Robot-Inventor/agent-skillsWrote 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/robot-inventor/agent-skills/web-master)<a href="https://agentmods.dev/skills/robot-inventor/agent-skills/web-master"><img src="https://agentmods.dev/badge/skills/robot-inventor/agent-skills/web-master/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/robot-inventor/agent-skills/web-master"><img src="https://agentmods.dev/badge/skills/robot-inventor/agent-skills/web-master.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 | $0.00046 | $0.02329 |
| Opus 5.5 | $0.00018 | $0.00932 |
| Sonnet 5.5 | $0.00009 | $0.00466 |
| Haiku 4.5 | $0.00005 | $0.00233 |
Grade A, and why
web-master 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 3d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Master
Follow these instructions when writing web-related code.
TypeScript
Do not use type assertions
Do not reach for type assertions unless you need one. Never add a type assertion up front because you think you might need it later. You may use a type assertion only when all of these conditions apply:
- You first write the code without a type assertion and encounter a type error.
- You cannot resolve that type error by improving type definitions elsewhere.
- Adding the type assertion does not compromise type safety.
Do not use ReturnType
Do not use ReturnType unless you need it. Use the following approaches instead.
If you need to use the return type of a specific function defined in the project somewhere other than that function:
- For a simple primitive type such as
booleanorstring, write the type directly. - For a complex type, define a named type, specify it as the function's return type (
(): T => {}), and reuseT.
If you need the return type of a library function:
- Check the function's type definitions first.
- If the library exports that type, use the exported type.
- If you need to pass the return type of another library function as a type argument and the library does not export that function's return type, you may use
ReturnTypeinside the type argument.
- If you need to pass the return type of another library function as a type argument and the library does not export that function's return type, you may use
- If the library does not export the type:
- Write the type directly if it is a simple primitive type.
- Otherwise, you may use
ReturnType.
// Incorrect
import foo from "foo";
const myFunc = (): string => {...};
const myFunc2 = (arg: ReturnType<typeof foo>, arg2: ReturnType<typeof myFunc>): number => {...};
// Correct
import type { FooResult } from "foo";
const myFunc = (): string => {...};
const myFunc2 = (arg: FooResult, arg2: string): number => {...};
Prefer as const satisfies over type annotations
Do not add type annotations unless you need them. Start by writing the code without a type annotation. If that causes a type error, first try to resolve it by improving type definitions elsewhere. Use a type annotation only as a last resort when those changes cannot solve the problem.
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.
- 3d ago Changed · +29 lines d526a82f51cd
- 1mo ago Changed · +59 lines 0e2468f46796
- 1mo ago Changed · +46 lines 69ebb406bb23
- 1mo ago First seen · 110 lines · 46 tokens per session scan A 4ad6ef52077d
web-master is a skill published in the GitHub repository Robot-Inventor/agent-skills (3 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 2,329 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…