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/mostlyharmless-ai/watercoolerWrote 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/mostlyharmless-ai/watercooler/marketplace)<a href="https://agentmods.dev/plugins/mostlyharmless-ai/watercooler/marketplace"><img src="https://agentmods.dev/badge/plugins/mostlyharmless-ai/watercooler/marketplace/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/mostlyharmless-ai/watercooler/marketplace"><img src="https://agentmods.dev/badge/plugins/mostlyharmless-ai/watercooler/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
watercooler marketplace 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": "watercooler",
"description": "Official Watercooler plugin marketplace \u2014 open-core skills + MCP server.",
"owner": {
"name": "Watercooler",
"url": "https://github.com/mostlyharmless-ai/watercooler"
},
"plugins": [
{
"name": "watercooler",
"source": {
"source": "git-subdir",
"url": "https://github.com/mostlyharmless-ai/watercooler.git",
"path": "plugins/claude/watercooler",
"sha": "e4264a123c9c4c6c9a141833211828b1388b501c",
"ref": "v0.5.6"
},
"description": "Watercooler \u2014 graph-first threaded memory for agentic coding teams."
}
]
}
The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
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 First seen · 22 lines scan A 8ee25c77fa45
watercooler marketplace is a plugin published in the GitHub repository mostlyharmless-ai/watercooler (14 stars, last pushed 2mo ago), licensed Apache-2.0. 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
agentrq-workspace
Workspace agent that executes tasks assigned by humans or supervisors, communicates progress via reply, and manages task lifecycle within a specific AgentRQ workspace.
greatpractice
A practice for capturing useful ways of working and gradually turning them into shared, repeatable procedures. It is designed to help teams preserve and improve recurring practices over time.
giovanni
AI Chief of Staff runtime: 4-layer memory with hard limits, daily digest with drift detection, stakeholder trajectories, invisible shadow hypotheses, adversarial-default review, and a governance lint that fails the build on contradictions. State lives in your repo; the mechanism lives here.
marrow
Shared memory and collision-avoidance for parallel Claude Code sessions. Warm-starts each session with what earlier ones learned, records what every agent does, and blocks two sessions editing the same file.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.