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 fmind/agent-supagentsnpx agentmods add plugins/fmind/agent-supagents/marketplacegit clone --depth 1 https://github.com/fmind/agent-supagentsGrade A, and why
agent-supagents 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agent-supagents — 89% identical, 46 lines differ
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-marketplace.json",
"name": "agent-supagents",
"description": "Compile a single AI supagent into multiple AI subagents.",
"owner": {
"name": "Médéric Hurier",
"email": "[email protected]"
},
"plugins": [
{
"name": "agent-supagents",
"source": "./",
"description": "Compile a single AI supagent into multiple AI subagents.",
"author": {
"name": "Médéric Hurier",
"email": "[email protected]",
"url": "https://fmind.dev"
},
"homepage": "https://github.com/fmind/agent-supagents",
"repository": "https://github.com/fmind/agent-supagents",
"license": "MIT",
"keywords": [
"agent-skills",
"agentic-coding",
"claude-code",
"cursor",
"gemini-cli",
"github-copilot",
"kilo-code",
"opencode",
"subagent"
],
"category": "workflow"
}
]
}
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 · 37 lines scan A bdeb26a5a029
agent-supagents is a plugin published in the GitHub repository fmind/agent-supagents (5 stars, last pushed 3mo 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
claude-settings
Plugin marketplace listing 36 plugins: simplify, humanize, fable-advisor, codex-advisor, adhd-output-style.
fable-advisor
Get a second opinion from Claude Fable 5 before big decisions.
gcloud-tools
Google Cloud Observability MCP for logs, metrics, and traces, plus best practices.
humanize
Block a curated list of AI buzzwords on every write with a hook.
intelligent-compact
Keep file paths, root causes, and open questions through auto-summaries.
anthropic-office-skills
Official Anthropic skills for PDF, Word, PowerPoint, and Excel files.