agentmods.dev

marketplace-browse

marketplace-browse is a skill for Claude Code from nirholas/nft-marketplace-mcp. It costs 49 tokens per session (489 once invoked), scanned A, original, Apache-2.0.

A read-only skill for searching and paging through the three.ws marketplace and skills catalogue via an MCP server. MCP lets an AI agent call these catalogue-search tools directly.

In plain words
What is it for?
It is for searching listings, filtering or sorting results, opening an agent's details, and reviewing available marketplace categories.
Why use it?
It makes it easier to discover agents and installable skills by query or category without needing a key, signer, payment, or manual browsing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the marketplace-mcp plugin — 1 skill, 1 MCP server shipped together

not rated 9repo today A scan 49 tokens original Apache-2.0

Good fit It is for searching listings, filtering or sorting results, opening an agent's details, and reviewing available marketplace categories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nirholas/nft-marketplace-mcp/marketplace-browse
View source ↗ nirholas/nft-marketplace-mcp nirholas.github.io
Install

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.

Any agent
npx skills add nirholas/nft-marketplace-mcp --skill marketplace-browse
Clone the repo
git clone --depth 1 https://github.com/nirholas/nft-marketplace-mcp

Made for: Claude Code.

Or install marketplace-mcp, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

agentmods badge for marketplace-browse

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirholas/nft-marketplace-mcp/marketplace-browse/github.svg)](https://agentmods.dev/skills/nirholas/nft-marketplace-mcp/marketplace-browse)
Your own site
<a href="https://agentmods.dev/skills/nirholas/nft-marketplace-mcp/marketplace-browse"><img src="https://agentmods.dev/badge/skills/nirholas/nft-marketplace-mcp/marketplace-browse/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.

agentmods 80×15 button for marketplace-browse

Your own site · 80×15
<a href="https://agentmods.dev/skills/nirholas/nft-marketplace-mcp/marketplace-browse"><img src="https://agentmods.dev/badge/skills/nirholas/nft-marketplace-mcp/marketplace-browse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00489
Opus 5.5 $0.00020 $0.00196
Sonnet 5.5 $0.00010 $0.00098
Haiku 4.5 $0.00005 $0.00049

Measured today against content hash f91ef586563e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

marketplace-browse 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 today.

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.

plugins/marketplace-mcp/skills/marketplace-browse/SKILL.md · 36 lines

What it actually says

Browse the three.ws marketplace with marketplace-mcp

The plugin starts @three-ws/marketplace-mcp over stdio (npx -y @three-ws/marketplace-mcp). Tools appear as mcp__marketplace-mcp__<tool>. Everything is a read-only call to the public three.ws API, with no key, signer or payment.

Environment

  • THREE_WS_BASE: API host, default https://three.ws.
  • THREE_WS_TIMEOUT_MS: request timeout, default 20000.

Tools

  • browse_agents (q, category, sort recommended|recent|popular|top_rated, limit 1-48 default 24, cursor): agent cards from GET /api/marketplace/agents.
  • agent_detail (id): one agent by the UUID on a browse_agents card, from GET /api/marketplace/agents/<id>.
  • agent_categories: category slugs for agents, from GET /api/marketplace/categories.
  • browse_skills (q, category, sort popular|new|az, limit 1-50 default 20, cursor): installable skills from GET /api/skills.
  • skill_categories: category slugs for skills, from GET /api/skills/categories.

Paginate by passing the previous response's next_cursor as cursor.

Workflow

  1. Call agent_categories or skill_categories to learn valid category slugs.
  2. Call browse_agents or browse_skills with a query and category.
  3. Call agent_detail on the best card for the full listing.

Example

User: "Find a popular agent for programming help."

Call agent_categories, then browse_agents with category: "programming", sort: "popular", limit: 10, then agent_detail with the chosen card's id, and summarize name, description and rating.

Changes

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.

  1. today First seen · 36 lines · 0 tokens per session scan A f91ef586563e

Subscribe to this mod's changes

marketplace-browse is a skill published in the GitHub repository nirholas/nft-marketplace-mcp (9 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 489 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 2026-11-10.

Building agentsProductivityai-agentsdiscoverymarketplacemcpmcp-serverskills
Related

marketplace-browse compared with skills from other repositories

marketplace-browse next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
marketplace-browsenirholas/nft-marketplace-mcpSkill9todayApache-2.0A49Claude Code
janitor-discoverkhendzel/skills-janitorSkill1251mo agoMITA58Claude Code
find-skillsrohitg00/skillkitSkill1.6k5mo agoApache-2.0A162Claude Code, Codex
acquire-skillsmartineserios/thebranaSkill34d agoMITA45Claude Code
progresstomoking2004/claude-pluginsSkill34d agoMITA113Claude Code
skillsmithsmith-horn/skillsmithSkill78yesterdaynoneA32Claude Code
cleantomoking2004/claude-pluginsSkill34d agoMITB160Claude Code