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 brentspine/brents-toasts --skill docsgit clone --depth 1 https://github.com/brentspine/brents-toastsWrote 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/brentspine/brents-toasts/docs)<a href="https://agentmods.dev/skills/brentspine/brents-toasts/docs"><img src="https://agentmods.dev/badge/skills/brentspine/brents-toasts/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/brentspine/brents-toasts/docs"><img src="https://agentmods.dev/badge/skills/brentspine/brents-toasts/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00127 | $0.03510 |
| Opus 5.5 | $0.00051 | $0.01404 |
| Sonnet 5.5 | $0.00025 | $0.00702 |
| Haiku 4.5 | $0.00013 | $0.00351 |
Grade A, and why
brents-toasts 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 2mo 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brents-toasts
Distributed as a Claude Code plugin: /plugin marketplace add brentspine/brents-toasts then
/plugin install brents-toasts@brents-toasts. To install by hand instead, copy this whole
docs/ directory (not just this file) to a project's .claude/skills/brents-toasts/ - the
links below are relative to files that travel with it either way, so both installs stay useful.
Zero-dependency, framework-agnostic toast/snackbar library. Works as an ESM/CJS import or a
plain <script> tag (UMD, global BrentsToasts). No CSS to link: the stylesheet is bundled
into the JS.
Install
npm install brents-toasts
import { toasts, ToastColor, ToastSeverity, ToastBuilder, Toasts } from 'brents-toasts';
No-build-step alternative, served via jsDelivr (unpkg also works, drop-in):
<script src="https://cdn.jsdelivr.net/npm/brents-toasts/dist/index.umd.min.js"></script>
<script>BrentsToasts.toasts.showToast('Hello, toast.');</script>
BrentsToasts mirrors the npm named exports 1:1. Full walkthrough:
guide/getting-started.md.
The core decision: which call shape
toasts is a ready-to-use singleton. Three equivalent, permanently supported call shapes for
showToast; pick whichever reads best, don't mix conventions within one codebase without reason:
// Options object: default choice once you need more than a bare message
toasts.showToast('Saved!', { severity: ToastSeverity.SUCCESS, duration: 5000, title: 'Done' });
// Legacy positional: message, color, duration(ms), closable, allowHtml (5 args, all after message
// optional) - no severity param, so role/aria-live stay at the default (see Config below)
toasts.showToast('Saved!', ToastColor.SUCCESS, 5000, false, false);
// Fluent builder: chainable, same options object under the hood
new ToastBuilder('Saved!').asSuccess().withDuration(5000).withTitle('Done').show();
showToast() returns the toast's id (string); save it if you'll removeToast/updateToast/
control its timer later, or pass your own via id in options to choose it up front instead - see
guide/lifecycle.md. Defaults: severity ToastSeverity.INFO (which also picks the default
color, ToastColor.INFO - see Config below), duration 3000ms, closable
true, allowHtml false, allowLineBreaks true (all overridable via configure(), see
guide/config.md). Builder method reference:
guide/builder-reference.md.
What ships with it
60 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.
- .claude-plugin/plugin.json 505 B
- changelogs/2.0.1.md 726 B
- changelogs/2.0.10.md 997 B
- changelogs/2.0.11.md 58 B
- changelogs/2.0.12.md 361 B
- changelogs/2.0.13.md 711 B
- changelogs/2.0.14.md 259 B
- changelogs/2.0.15.md 349 B
- changelogs/2.0.16.md 440 B
- changelogs/2.0.2.md 149 B
- changelogs/2.0.3.md 107 B
- changelogs/2.0.4.md 985 B
- changelogs/2.0.5.md 162 B
- changelogs/2.0.6.md 104 B
- changelogs/2.0.7.md 626 B
- changelogs/2.0.8.md 712 B
- changelogs/2.0.9.md 733 B
- changelogs/2.1.0.md 563 B
- changelogs/2.1.1.md 523 B
- changelogs/2.1.10.md 751 B
- changelogs/2.1.2.md 1.8 KB
- changelogs/2.1.3.md 988 B
- changelogs/2.1.4.md 684 B
- changelogs/2.1.5.md 1.1 KB
- changelogs/2.1.6.md 935 B
- changelogs/2.1.7.md 327 B
- changelogs/2.1.8.md 529 B
- changelogs/2.1.9.md 150 B
- changelogs/2.2.0.md 3.1 KB
- changelogs/2.2.1.md 354 B
- changelogs/2.2.10.md 946 B
- changelogs/2.2.11.md 179 B
- changelogs/2.2.12.md 149 B
- changelogs/2.2.13.md 130 B
- changelogs/2.2.14.md 789 B
- changelogs/2.2.2.md 469 B
- changelogs/2.2.3.md 233 B
- changelogs/2.2.4.md 760 B
- changelogs/2.2.5.md 334 B
- changelogs/2.2.6.md 267 B
- changelogs/2.2.7.md 488 B
- changelogs/2.2.8.md 1.8 KB
- changelogs/2.2.9.md 867 B
- changelogs/2.3.0.md 841 B
- changelogs/2.3.1.md 168 B
- changelogs/2.3.2.md 329 B
- changelogs/2.3.3.md 142 B
- changelogs/2.3.4.md 223 B
- changelogs/2.3.5.md 318 B
- changelogs/2.3.6.md 1.0 KB
- changelogs/2.3.7.md 1.1 KB
- changelogs/2.3.8.md 468 B
- changelogs/2.3.9.md 151 B
- changelogs/2.4.0.md 646 B
- changelogs/2.4.1.md 1.1 KB
- changelogs/2.4.10.md 1.9 KB
- changelogs/2.4.2.md 217 B
- changelogs/2.4.3.md 304 B
- changelogs/2.4.4.md 457 B
- changelogs/2.4.5.md 998 B
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.
- 2mo ago First seen · 187 lines · 127 tokens per session scan A df7ffb4e471f
brents-toasts is a skill published in the GitHub repository brentspine/brents-toasts (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 127 tokens to every session and 3,510 once invoked, about $0.0005 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 2026-08-30.
brents-toasts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| brents-toastsbrentspine/brents-toasts | Skill | 8 | 7d ago | Apache-2.0 | A | 127 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |