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 meteor/agent-skills --skill meteor-community-packagesgit clone --depth 1 https://github.com/meteor/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/meteor/agent-skills/meteor-community-packages)<a href="https://agentmods.dev/skills/meteor/agent-skills/meteor-community-packages"><img src="https://agentmods.dev/badge/skills/meteor/agent-skills/meteor-community-packages/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/meteor/agent-skills/meteor-community-packages"><img src="https://agentmods.dev/badge/skills/meteor/agent-skills/meteor-community-packages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 135 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00128 | $0.01503 |
| Opus 5 | $0.00064 | $0.00751 |
| Sonnet 5 | $0.00026 | $0.00301 |
| Haiku 4.5 | $0.00013 | $0.00150 |
Grade A, and why
meteor-community-packages 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 10d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meteor community packages
Use Meteor's community package pages as a curated discovery catalog. A listing does not make a package part of Meteor core, transfer its maintenance to the Meteor organization, or guarantee compatibility with every Meteor 3 release. Select a package only after checking its ownership, current release, supported Meteor range, and changes to application behavior.
This skill owns package discovery, comparison, first adoption, and the package-specific integration documented in Meteor core. It does not replace the core skill for methods, publications, Mongo, accounts, security, testing, builds, or deployment.
Decision flow
- Define the missing capability and the behavior that must remain unchanged.
Distinguish a new adoption from a package that stopped resolving during a
Meteor upgrade. Route the latter to
migrate-to-meteor-3. - Inspect
.meteor/release,.meteor/packages,.meteor/versions,package.json, and the npm lockfile. Package APIs follow the resolved package version, not only the Meteor release. - Read
references/package-catalog.mdwhen the request matches the documented catalog or a promoted package. Open only the selected package's local guide and read its baseline, selection rules, and required checks before responding. Then consult its linked upstream repository for APIs or versions beyond Meteor's maintained guidance. - Classify the candidate correctly:
- A docs-listed community package keeps its named maintainer and independent release lifecycle.
- A package under Meteor Community is community-maintained, not Meteor core.
- A promoted core package, such as
rolesin Meteor 3.1+, uses the core package name and Meteor documentation.
- Compare behavior, not feature labels. Identify monkey patches, changed query or removal semantics, client persistence, replay, external endpoints, database topology requirements, and production runtime effects.
- Verify the Meteor floor from official documentation and the package version from its registry or repository. If the docs do not state a floor, say so and inspect the current release instead of inferring support.
- Install through the package's documented ecosystem. Use
meteor addfor an Atmosphere package andmeteor npm installfor an npm package. Do not invent a version constraint. After installation, confirm the resolved version in.meteor/versionsor the npm lockfile. - Apply every relevant required check from the selected package guide. Do not stop after asking for a project path. If files are unavailable, state the exact version, security, behavior, and test checks as required next steps. For an option not covered there, verify the resolved version against the upstream repository instead of extrapolating from another release.
- Add the smallest representative integration and test its package-specific behavior plus the underlying Meteor invariants. Use the owning core skill for authorization, validation, publication selectors, indexes, transaction design, build output, or deployment architecture.
What ships with it
13 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.
- references/archive.md 1.8 KB
- references/cluster.md 1.7 KB
- references/eval-cases.md 6.7 KB
- references/jam-method.md 3.2 KB
- references/jam-pub-sub.md 2.5 KB
- references/mail-preview.md 1.8 KB
- references/meteor-rpc.md 2.0 KB
- references/mongo-transactions.md 2.0 KB
- references/offline.md 2.7 KB
- references/package-catalog.md 4.8 KB
- references/roles.md 2.4 KB
- references/soft-delete.md 1.8 KB
- references/wormhole.md 2.5 KB
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.
- 10d ago First seen · 146 lines · 128 tokens per session scan A 8e7cd67f402a
meteor-community-packages is a skill published in the GitHub repository meteor/agent-skills (8 stars, last pushed today), licensed MIT. It adds 128 tokens to every session and 1,503 once invoked, about $0.0006 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
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…