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 agentmods add skills/arenukvern/mcp_flutter/plugin-marketplace-setupnpx skills add Arenukvern/mcp_flutter --skill plugin-marketplace-setupgit clone --depth 1 https://github.com/Arenukvern/mcp_flutterWrote 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/arenukvern/mcp_flutter/plugin-marketplace-setup)<a href="https://agentmods.dev/skills/arenukvern/mcp_flutter/plugin-marketplace-setup"><img src="https://agentmods.dev/badge/skills/arenukvern/mcp_flutter/plugin-marketplace-setup.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.02839 |
| Opus 5 | $0.00044 | $0.01419 |
| Sonnet 5 | $0.00018 | $0.00568 |
| Haiku 4.5 | $0.00009 | $0.00284 |
Grade A, and why
plugin-marketplace-setup 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- plugin-marketplace-setup — 86% identical, 38 lines differ
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin & skill marketplace setup
Ship skills (portable instructions), plugins (runtime wiring), and marketplaces (catalogs) without mixing them up.
Three layers (normative)
| Layer | What it is | Install unit | Skill Steward home |
|---|---|---|---|
| Skill | SKILL.md per agentskills.io |
npx skills add owner/repo --skill name |
skills/{name}/ |
| Plugin | Open Plugin or vendor manifest + hooks/MCP/rules/commands | Per-agent (see matrix) | plugins/{id}/ (ADR 0004) |
| Marketplace | Catalog of plugins/skills | Add marketplace, then install plugin | Product repos; Skill Steward uses public Git + skills.sh |
Rule: Instructions only → skill. Event hooks or multi-file wiring → plugin (references skills by id, do not fork SKILL.md).
Skill Steward meta-plugin means: a declarative manifest, referenced skill IDs, hook/rule snippets, and validated wiring artifacts. It does not mean a host marketplace submission has happened, and it must not silently mutate Cursor/Codex/Claude configuration. Host-specific install steps remain explicit in README/docs.
Public vs private (decision)
| Goal | Recommended channel | Notes |
|---|---|---|
| Public discovery | GitHub public repo + skills.sh | npx skills add owner/repo; index needs valid skills/*/SKILL.md |
| Team-only skills (any agent) | Private GitHub/GitLab repo | Same npx skills add org/private-repo if agents can clone; use deploy keys / SSO |
| Cursor team plugins | Team marketplace — Dashboard → Settings → Plugins → Import repo | Teams/Enterprise; private GitHub repo with .cursor-plugin/marketplace.json |
| Claude Code team | Private git marketplace | /plugin marketplace add with token env for auto-update (Claude docs) |
| Codex team | $REPO_ROOT/.agents/plugins/marketplace.json or ~/.agents/plugins/marketplace.json |
Repo/personal marketplace; install from app or CLI |
| Zed skills | .agents/skills/ or ~/.agents/skills/ |
Skills only; Zed has no remote skill registry or custom search paths |
| npm-private skills packages | Claude marketplace source.type: npm |
For npm-hosted plugin bundles; uncommon for plain SKILL.md trees |
What ships with it
6 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.
- 6d ago First seen · 202 lines · 88 tokens per session scan A a27832227346
plugin-marketplace-setup is a skill published in the GitHub repository Arenukvern/mcp_flutter (373 stars, last pushed 10d ago), licensed MIT. It adds 88 tokens to every session and 2,839 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
at_client_skills-sdk
Use this skill when a developer is building a Dart or Flutter app that depends on atclient or atclientflutter from pub.dev, stores or shares data via the Atsign Protocol, needs onboarding (CRAM new-atsign, atKeys file, keychain, APKAM) or APKAM enrollment, or asks about AtCollection , CItem , Query , sub-collections…
flutter-pre-caching
Use when preloading fonts, asset/network images, Lottie/Rive animations, local JSON/config, warming initial API data, or optimizing Flutter Web startup.
firebase-auth
Use when setting up auth, managing auth state, implementing email/password or social sign-in, handling auth errors, or managing users.
architecture-feature-first
Use when creating a feature, designing folder structure, adding repositories/services/view models, wiring dependency injection, or deciding which layer owns logic.
code-review
Use when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.
effective-dart
Use when writing Dart code, reviewing for style, refactoring naming, adding doc comments, structuring imports, or enforcing type annotations.