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.
git clone --depth 1 https://github.com/avivsinai/skills-marketplaceWrote 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/plugins/avivsinai/skills-marketplace/marketplace)<a href="https://agentmods.dev/plugins/avivsinai/skills-marketplace/marketplace"><img src="https://agentmods.dev/badge/plugins/avivsinai/skills-marketplace/marketplace/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/plugins/avivsinai/skills-marketplace/marketplace"><img src="https://agentmods.dev/badge/plugins/avivsinai/skills-marketplace/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
avivsinai-marketplace 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "avivsinai-marketplace",
"owner": {
"name": "Aviv Sinai"
},
"metadata": {
"description": "Skills and plugins for AI coding assistants",
"version": "1.0.0"
},
"plugins": [
{
"name": "amq-cli",
"source": {
"source": "url",
"url": "https://github.com/avivsinai/agent-message-queue.git",
"ref": "main",
"sha": "fddce853890a475d77e440d1b46d12e3a7ca138a"
},
"description": "Agent Message Queue - file-based inter-agent messaging with co-op mode, cross-project federation, and orchestrator integrations (Symphony, Kanban).",
"version": "fddce853890a",
"repository": "https://github.com/avivsinai/agent-message-queue",
"keywords": ["messaging", "agents", "maildir", "queue", "inter-agent", "coordination", "coop", "federation", "integration", "symphony", "kanban"]
},
{
"name": "amq-spec",
"source": {
"source": "url",
"url": "https://github.com/avivsinai/agent-message-queue.git",
"ref": "main",
"sha": "fddce853890a475d77e440d1b46d12e3a7ca138a"
},
"description": "Parallel-research-then-converge design workflow between two agents. Structured phase-by-phase guidance for collaborative spec/design work via AMQ.",
"version": "fddce853890a",
"repository": "https://github.com/avivsinai/agent-message-queue",
"keywords": ["spec", "design", "collaborative", "agents", "parallel-research", "amq", "coordination"]
},
{
"name": "langfuse",
"source": {
"source": "url",
"url": "https://github.com/avivsinai/langfuse-mcp.git",
"ref": "main",
"sha": "2abb3fb68e1dcd19f05b3176ae1f4f89d6a80d2c"
},
"description": "Langfuse observability - query traces, debug exceptions, analyze sessions, manage prompts and datasets via MCP tools. First LLM observability skill for Claude Code and Codex.",
"version": "2abb3fb68e1d",
"repository": "https://github.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.
- today Changed 3718c38c5860
- yesterday Changed a108979c632a
- 2d ago Changed 16bf174b58e6
- 3d ago Changed 820f6977ef3f
- 4d ago Changed a30fd30789cd
- 5d ago Changed 8a363830ee1a
- 7d ago Changed 4d930ce519f2
- 8d ago Changed 8e4e2271b592
- 9d ago Changed 256e8fb328a7
- 12d ago First seen · 169 lines scan A 93ebafae3170
avivsinai-marketplace is a plugin published in the GitHub repository avivsinai/skills-marketplace (2 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
dev-workflow-forge
A generator kit for Claude Code dev tooling. Three generators read your codebase and write a project-specific review skill, a rules set, and a self-learning feedback loop tuned to your stack, instead of handing you tooling written for someone else's project. The review skill they write is an overlay on a shared engine.
search-visibility
Two halves of getting found: a-seo-gsc pulls your Google Search Console data over the API (or reads a manual export) and turns it into a prioritized action plan backed by your own numbers, and a-geo-optimizer checks whether AI assistants can fetch, parse, and cite a site, then recommends the technical and content…
unslop
Three anti-slop scanners in one bundle: a-unslop-text catches AI-diction and cadence tells in prose, a-unslop-code catches bugs and tutorial-shaped patterns in source, a-unslop-ui catches stock-default looks in web UI. Each ships a deterministic scanner plus a Build mode that heads off the tell before it ships. The…
dev-loop
The everyday dev loop as three stack-neutral commands: fix debugs a bug or batch-applies a review report by severity, commit runs pre-flight checks and drafts a conventional message behind a sensitive-file gate, ship chains review, fix, and commit with a gate between each phase.
role-lenses
Six senior-review lenses as slash commands. Each drops Claude into a specific principal-level seat (architect, critic, design, ops, pm, staff) with its own refusals and output contract, so you get a pointed second opinion instead of agreement.
sanitize-public
Pre-publish leak scanner. Scans a skill, plugin, repo, or bundle for secrets, internal hostnames, private paths, and other identifiers before it ships publicly, then walks a manual-review checklist for the contextual leaks a regex can't see.