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/CrestApps/CrestApps.AgentSkillsWrote 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/crestapps/crestapps.agentskills/crestapps-core)<a href="https://agentmods.dev/plugins/crestapps/crestapps.agentskills/crestapps-core"><img src="https://agentmods.dev/badge/plugins/crestapps/crestapps.agentskills/crestapps-core/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/crestapps/crestapps.agentskills/crestapps-core"><img src="https://agentmods.dev/badge/plugins/crestapps/crestapps.agentskills/crestapps-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
crestapps-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 yesterday.
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": "crestapps-core",
"source": "./plugins/crestapps-core",
"description": "CrestApps.Core skills for GitHub Copilot CLI backed by CrestApps.AgentSkills.",
"version": "1.0.4",
"homepage": "https://github.com/CrestApps/CrestApps.AgentSkills/tree/main/plugins/crestapps-core",
"repository": "https://github.com/CrestApps/CrestApps.AgentSkills",
"license": "MIT",
"keywords": [
"crestapps",
"copilot-cli",
"skills",
"dotnet"
],
"category": "library",
"tags": [
"crestapps",
"core",
"agentskills"
],
"skills": [
"./skills"
]
}What it installs
The manifest is a name and a version. 47 skills travel with it, and installing the plugin installs all of them — 8,046 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill crestapps-core-realtime-voice A 201 tokens
- Skill crestapps-core-ai-model-capabilities A 210 tokens
- Skill crestapps-core-chat-interactions A 202 tokens
- Skill crestapps-core-openai A 184 tokens
- Skill crestapps-core-overview A 179 tokens
- Skill crestapps-core-yessql-stores A 171 tokens
- Skill crestapps-core-ai-profiles A 191 tokens
- Skill crestapps-core-ai-runtime A 175 tokens
- Skill crestapps-core-ai-usage-metering A 194 tokens
- Skill crestapps-core-aspnet-hosting A 178 tokens
- Skill crestapps-core-azure-openai A 201 tokens
- Skill crestapps-core-chat A 188 tokens
- Skill crestapps-core-custom-tools A 184 tokens
- Skill crestapps-core-data-sources A 159 tokens
- Skill crestapps-core-document-agents A 161 tokens
- Skill crestapps-core-document-processing A 153 tokens
- Skill crestapps-core-file-sources A 178 tokens
- Skill crestapps-core-foundations A 178 tokens
- Skill crestapps-core-orchestration A 186 tokens
- Skill crestapps-core-prompt-security A 196 tokens
- Skill crestapps-core-tool-instances A 201 tokens
- Skill crestapps-core-web-crawlers A 153 tokens
- Skill crestapps-core-a2a A 182 tokens
- Skill crestapps-core-ai-agents A 181 tokens
- Skill crestapps-core-ai-personas A 196 tokens
- Skill crestapps-core-ai-templates A 154 tokens
- Skill crestapps-core-azure-ai-inference A 173 tokens
- Skill crestapps-core-context-builders A 175 tokens
- Skill crestapps-core-copilot-orchestrator A 205 tokens
- Skill crestapps-core-data-storage A 168 tokens
- Skill crestapps-core-entitycore-stores A 167 tokens
- Skill crestapps-core-mcp A 162 tokens
- Skill crestapps-core-resilience A 145 tokens
- Skill crestapps-core-sample-hosts A 164 tokens
- Skill crestapps-core-signalr A 205 tokens
- Skill crestapps-core-templates A 170 tokens
- Skill crestapps-core-ai-markdown A 179 tokens
- Skill crestapps-core-elasticsearch A 125 tokens
- Skill crestapps-core-extensible-entities A 145 tokens
- Skill crestapps-core-ollama A 148 tokens
- Skill crestapps-core-ai-memory A 140 tokens
- Skill crestapps-core-azure-ai-search A 141 tokens
- Skill crestapps-core-claude-orchestrator A 177 tokens
- Skill crestapps-core-mcp-file-resources A 144 tokens
- Skill crestapps-core-postgresql A 129 tokens
- Skill crestapps-core-response-handlers A 145 tokens
- Skill crestapps-core-external-relays A 103 tokens
What ships with it
1 file beside marketplace.json#crestapps-core 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.
- yesterday Changed fa914d10fce1
- 2d ago First seen · 24 lines scan A b868a450926a
crestapps-core is a plugin published in the GitHub repository CrestApps/CrestApps.AgentSkills (13 stars, last pushed yesterday), 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 2026-10-21.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.