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 viktorbezdek/skillstacknpx agentmods add plugins/viktorbezdek/skillstack/marketplacegit clone --depth 1 https://github.com/viktorbezdek/skillstackGrade A, and why
skillstack 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.
How it starts
The opening of the file, as written. The whole thing — 938 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "skillstack",
"owner": {
"name": "Viktor Bezdek",
"url": "https://github.com/viktorbezdek"
},
"metadata": {
"description": "Battle-tested Claude Code plugins spanning Engineering, Meta-Infra, Managerial-Product, and Marketing-Comms.",
"version": "3.0.0"
},
"plugins": [
{
"name": "agent-evaluation",
"source": "./agent-evaluation",
"description": "Comprehensive evaluation framework for LLM agent systems. Multi-dimensional rubrics, LLM-as-judge with bias mitigation, pairwise comparison, direct scoring, confidence calibration, and continuous monitoring.",
"version": "1.0.5",
"category": "Meta-Infra",
"tags": [
"evaluation",
"llm-as-judge",
"bias-mitigation",
"rubrics",
"pairwise-comparison"
]
},
{
"name": "agent-project-development",
"source": "./agent-project-development",
"description": "Methodology for LLM-powered project development. Task-model fit analysis, pipeline architecture (acquire-prepare-process-parse-render), file system state machines, cost estimation, and architectural reduction.",
"version": "1.0.5",
"category": "Engineering",
"tags": [
"project-development",
"pipeline",
"task-model-fit",
"cost-estimation"
]
},
{
"name": "api-design",
"source": "./api-design",
"description": "Comprehensive API design skill for REST, GraphQL, gRPC, and Python library architectures. Design endpoints, schemas, authentication, pagination, error handling, and federation.",
"version": "1.2.24",
"category": "Engineering",
"tags": [
"api",
"rest",
"graphql",
"grpc",
"openapi"
]
},
{
"name": "bdi-mental-states",
"source": "./bdi-mental-states",
"description": "Belief-Desire-Intention cognitive architecture for LLM agents. Formal BDI ontology, T2B2T paradigm, RDF What ships with it
1 file beside marketplace.json 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.
- 2d ago First seen · 938 lines scan A b89d35219bc7
skillstack is a plugin published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo 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 2026-08-30.
Other plugins, from other repositories
google-plugins
Plugin marketplace listing 17 plugins: alloydb, alloydb-omni, bigtable, cloud-sql-mysql, cloud-sql-postgresql.
discover
Discover which AI agent to build — map automation outcomes to solvable opportunities, validate assumptions, and decide build vs buy. Use when exploring agent ideas, analyzing automation opportunities, running build-or-buy analysis, or estimating agent development costs.
vibe-plugins
Plugin marketplace listing 1 plugin: vibe-engineering.
supabase
Supabase MCP integration for database operations, authentication, storage, and real-time subscriptions. Manage your Supabase projects, run SQL queries, and interact with your backend directly.
fmh66
Plugin marketplace listing 1 plugin: kernel-opt-agent.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.