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/mintuz/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/mintuz/skills/core)<a href="https://agentmods.dev/plugins/mintuz/skills/core"><img src="https://agentmods.dev/badge/plugins/mintuz/skills/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/mintuz/skills/core"><img src="https://agentmods.dev/badge/plugins/mintuz/skills/core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade 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 1mo 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",
"version": "2.0.3",
"description": "Core Agents and skills that aid software development workflows",
"author": {
"name": "Adam Bulmer",
"email": "[email protected]"
},
"repository": "https://github.com/mintuz/claude-plugins",
"license": "MIT",
"keywords": ["core", "software", "development", "workflows"]
}
What it installs
The manifest is a name and a version. 14 skills travel with it, and installing the plugin installs all of them — 926 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill graph-engineering A 66 tokens
- Skill github-monitor A 85 tokens
- Skill pseudocode A 60 tokens
- Skill commit-messages A 29 tokens
- Skill babysit A 171 tokens
- Skill gauntlet-loop A 50 tokens
- Skill reducer A 53 tokens
- Skill ship-pr A 75 tokens
- Skill yagni A 61 tokens
- Skill acceptance-review A 56 tokens
- Skill learn A 56 tokens
- Skill wtf A 61 tokens
- Skill writing A 60 tokens
- Skill pr C 43 tokens
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.
- 1mo ago Changed a7c1cae0dc49
- 1mo ago First seen · 13 lines scan A 99f020d7c66b
core is a plugin published in the GitHub repository mintuz/skills (29 stars, last pushed 2d 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
rampstack marketplace
RampStack Claude Skills: the website lifecycle as installable skills.
plugmem-coding-claude-code
PlugMem cross-session memory for Claude Code — a self-writing CLAUDE.md that learns project conventions and debugging recipes from your sessions.
agented
A text editor for LLMs, not humans.
rampstack-starter
Curated starter subset of the RampStack catalog: a general-purpose skill set for the website lifecycle.
agented
MCP configuration declaring 1 server: agented.
papermate
Human-in-the-loop thesis writing copilot for Chinese university students. Search literature, organize evidence, draft sections, and prepare for defense — with you, not instead of you.