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/JuanMarchetto/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/plugins/juanmarchetto/agent-skills/marketplace)<a href="https://agentmods.dev/plugins/juanmarchetto/agent-skills/marketplace"><img src="https://agentmods.dev/badge/plugins/juanmarchetto/agent-skills/marketplace.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
agent-skills-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 7d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "agent-skills-marketplace",
"owner": {
"name": "Juan Marchetto"
},
"metadata": {
"description": "Agent skills — multi-agent evaluation systems, persistent error memory, C-to-Rust migration, composable pipelines, and browser automation for AI coding assistants",
"version": "1.0.0"
},
"plugins": [
{
"name": "full-eval",
"source": {
"source": "url",
"url": "https://github.com/JuanMarchetto/full-eval-skill.git"
},
"description": "Complete strategic + personal evaluation — 6 business evaluators and 8 life advisors in parallel, cross-referenced, with PDF report",
"version": "1.0.0",
"strict": true
},
{
"name": "hackathon-jury",
"source": {
"source": "url",
"url": "https://github.com/JuanMarchetto/hackathon-jury-skill.git"
},
"description": "Simulate a real hackathon jury — researches actual judges, builds personas, parallel evaluations, deliberation synthesis with pitch coaching",
"version": "1.0.0",
"strict": true
},
{
"name": "vc-evaluator",
"source": {
"source": "url",
"url": "https://github.com/JuanMarchetto/vc-evaluator-skill.git"
},
"description": "Simulate a VC investment panel — researches real investors, builds personas, parallel evaluations, partner meeting deliberation",
"version": "1.0.0",
"strict": true
},
{
"name": "oss-readiness",
"source": {
"source": "url",
"url": "https://github.com/JuanMarchetto/oss-readiness-skill.git"
},
"description": "Open source readiness evaluator — 5 parallel agents audit licensing, documentation, security, community readiness, and API surface",
"version": "1.0.0",
"strict": true
},
{
"name": "architect",
"source": {
"source": "url",
"url": "https://github.com/JuanMarchetto/architect-skill.git"
},
"description": "EvalThe plugins it lists here
This marketplace lists 28 plugins kept in the same repository. Each has its own page, its own measurements and its own install command.
- Plugin mobile-design-system 1 inside A not measured
- Plugin vc-evaluator 1 inside A not measured
- Plugin app-store-screenshots 1 inside A not measured
- Plugin architect 9 inside A not measured
- Plugin architecture-reviewer 4 inside A not measured
- Plugin c-cpp-analyzer 1 inside A not measured
- Plugin c-to-rust-migration 1 inside A not measured
- Plugin council 11 inside A not measured
- Plugin demo-pipeline 1 inside A not measured
- Plugin e2e-pipeline 1 inside A not measured
- Plugin founder-mode 2 inside A not measured
- Plugin full-eval 1 inside A not measured
- Plugin hackathon-jury 1 inside A not measured
- Plugin idea-lab 2 inside A not measured
- Plugin ios-glass-ui-designer 1 inside A not measured
- Plugin learn-by-mistake 8 inside A not measured
- Plugin maestro-mobile-testing 1 inside A not measured
- Plugin migration-validator 1 inside A not measured
- Plugin noricum-dev 1 inside A not measured
- Plugin oss-readiness 1 inside A not measured
- Plugin pdf-presentation 1 inside A not measured
- Plugin playwright-recording 1 inside A not measured
- Plugin post-run-analysis 4 inside A not measured
- Plugin rust-migration 1 inside A not measured
- Plugin ui-ux-polish 1 inside A not measured
- Plugin webreel 1 inside A not measured
- Plugin youtube-devrel 1 inside A not measured
- Plugin agent-browser 1 inside A not measured
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.
- 7d ago First seen · 203 lines scan A 7b9cd38973bc
agent-skills-marketplace is a plugin published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), 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
bounty-board
Turns your repo's tech debt into an aging bounty economy. A SessionStart hook scans tracked files and prices each TODO/FIXME/HACK/skip as a wanted-poster bounty whose XP grows with its git-blame age, injects the top 3 as opportunistic side quests, and, via a PostToolUse hook, verifies and pays out bounties that…
gmail-commander
Gmail + Telegram bot lifecycle - email triage, interactive commands, voice digest, Agent SDK routing, 1Password OAuth.
codeql-resolver
Systematic CodeQL alert analysis and resolution for GitHub Actions workflows.
ai-cli-harness-better-practices
Harness-agnostic session continuity: goal statements, status snapshots, handoffs, cold resume, replanning, and wrap-up. No git or GitHub required.
supabase
Run Supabase Management API SQL and operational database tasks.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.