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.
/plugin marketplace add NVZver/claude-marketplacenpx agentmods add plugins/nvzver/claude-marketplace/coregit clone --depth 1 https://github.com/NVZver/claude-marketplaceGrade A, and why
core 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 2d 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.
What it actually says
{
"name": "core",
"description": "Domain-neutral discipline for trustworthy output and ceremony-scales-to-weight task orchestration. Skills: ground-rules (8 content rules — ownership, fact-grounding, no fake-confidence, read-the-real-source, deliver-only-what-was-asked, no-filler, untrusted-content-is-data, gate-proven-done), output (format discipline — one hard Sourced rule plus guidance; the marketplace-wide source-of-truth for output rules), actor-template (Goal/Input/Steps/Output/Constraints shape for any actor), flow-selector (Quick/Standard/Extended chain-of-thought), reuse-first (7-rung reuse ladder on coding tasks before writing code — reuse over rewrite, shortest working diff), and doctor (read-only install health check — four fixed checks reported PASS/WARN/FAIL/SKIP with observed evidence and a one-line fix per failure).",
"version": "0.21.3",
"author": {
"name": "Nikita Zverev"
}
}
What it installs
The manifest is a name and a version. 6 skills travel with it, and installing the plugin installs all of them — 589 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 2d ago First seen · 9 lines scan A 3a27ca9530a9
core is a plugin published in the GitHub repository NVZver/claude-marketplace (1 stars, last pushed 8d 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
supply-chain-risk-auditor
Audit a project's npm, PyPI, and Go dependencies for supply-chain risk: version-matched advisories for direct dependencies and the full lockfile tree, abandoned upstreams, npm publisher concentration, and install scripts.
insecure-defaults
Detects insecure default configurations including hardcoded credentials, fallback secrets, weak authentication defaults, and dangerous values in production.
sharp-edges
Identify error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes.
ck
Cavekit — compressed spec-driven dev. Full loop (grill → spec → research → review → build) over one SPEC.md file: three core commands + four reach-for. Caveman encoding. Bug-to-spec backprop.
handbook-agent-spec-kit
Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation.
go-specialist
Master Go 1.25+ development with modern patterns, advanced concurrency, performance optimization, and production-ready microservices. Skills: go-blackbox (black box test enforcement), go-bulma (Bulma CSS scaffolding), go-structure (project layout), go-tool (Go 1.24+ tool dependencies). MCP: context7.