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 mintuz/skillsnpx agentmods add plugins/mintuz/skills/marketplacegit clone --depth 1 https://github.com/mintuz/skillsGrade A, and why
mintuz-claude-plugins 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "mintuz-claude-plugins",
"owner": {
"name": "Adam Bulmer",
"email": "[email protected]",
"url": "https://github.com/mintuz"
},
"plugins": [
{
"name": "core",
"source": "./src/core",
"description": "Core Agents and skills that aid software development workflows",
"skills": [
"./skills/acceptance-review",
"./skills/babysit",
"./skills/commit-messages",
"./skills/expectations",
"./skills/gauntlet-loop",
"./skills/graph-engineering",
"./skills/learn",
"./skills/pr",
"./skills/pseudocode",
"./skills/reducer",
"./skills/ship-pr",
"./skills/writing",
"./skills/wtf",
"./skills/github-monitor"
]
},
{
"name": "typescript",
"source": "./src/typescript",
"description": "Agents and skills that are specialised in writing Web Application TypeScript"
},
{
"name": "system-design",
"source": "./src/system-design",
"description": "Skills for visualising Web Application architecture and relationships",
"skills": ["./skills/mermaid-generator"]
},
{
"name": "product-management",
"source": "./src/product-management",
"description": "Agents and skills that are specialised in Product Management workflows",
"skills": [
"./skills/status-updates",
"./skills/decision-trace",
"./skills/meeting-to-action-brief",
"./skills/story-pr-orchestrator"
]
},
{
"name": "web",
"source": "./src/web",
"description": "Agents and skills that are specialised in building and maintaining web applications",
"skills": [
"./skills/web-design",
"./skills/css",
"./skills/tdd",
"./skills/react",
"./skills/xstate",
"./skills/react-testing",
"./skills/frontend-testing",
"./skills/eyes",
"./skills/chatgpt-app-sdk"
]
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 · 91 lines scan A eff20df6c825
mintuz-claude-plugins is a plugin published in the GitHub repository mintuz/skills (24 stars, last pushed 9d 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
RampStack Claude Skills: the website lifecycle as installable skills.
claude-skills
Full RampStack catalog of website-lifecycle skills across research, brand, build, and audit.
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.
paper-agent
Paper Agent — academic manuscript drafting, review, revision, proofreading, and auditing for quantitative-science journals.
frane-agented
agented (ae) — a text editor for LLMs, not humans.
agented
A text editor for LLMs, not humans.