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/curie-eng/curieWrote 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/curie-eng/curie/mean-tester)<a href="https://agentmods.dev/plugins/curie-eng/curie/mean-tester"><img src="https://agentmods.dev/badge/plugins/curie-eng/curie/mean-tester/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/curie-eng/curie/mean-tester"><img src="https://agentmods.dev/badge/plugins/curie-eng/curie/mean-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mean-tester 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 5d 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": "mean-tester",
"version": "0.4.7",
"description": "Mean tests another agent through readonly probes or marked actions on admitted test installations, checks owned approvals and state, and reports a computed ship verdict. It files nothing and fixes nothing.",
"license": "Apache-2.0",
"author": {"name": "CurieTech"},
"keywords": ["testing", "mean-testing", "quality", "slack"],
"secrets": ["MEAN_TESTER_SLACK_BOT_TOKEN", "MEAN_TESTER_SLACK_TEAM_ID"],
"optionalSecrets": ["GITHUB_PERSONAL_ACCESS_TOKEN"],
"starterPrompts": [
"test @asset-search bundle asset-search",
"continue"
],
"toolPolicy": {
"enforcement": "curie/mcp-tool-policy@1",
"allow": [
"slack/slack_post_message",
"slack/slack_get_thread_replies",
"slack/slack_get_channel_history",
"slack/slack_reply_to_thread",
"github/search_code",
"github/get_file_contents",
"github/list_commits"
],
"approvalRequired": [],
"deny": []
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 81 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 5d ago Changed · +1 lines 8cb41fff01c9
- 14d ago Changed · +1 lines 91b78c6f72e5
- 18d ago First seen · 27 lines scan A 4f2637e12fb6
mean-tester is a plugin published in the GitHub repository curie-eng/curie (36 stars, last pushed today), 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 2026-09-26.
Other plugins, from other repositories
han-coding
Coding-facing skills for the Han suite: writing, reviewing, testing, investigating, and standardizing code. Home of the tdd skill, which drives a feature or behavior through a BDD-framed red-green-refactor loop with an enforced observed-failure gate, and the refactor skill, which restructures existing code without…
fuse-react
Expert React 19 with hooks, TanStack Router, TanStack Form, Zustand, Testing Library, shadcn/ui, and SOLID principles.
jig
Spec-driven, review-enforced, hook-gated AI-native development workflow for Claude Code.
testing
Testing toolkit: browser-based end-to-end verification with Playwright and a /write-tests command that generates a suite matching project conventions.
harnessay
Profile Claude Code and Codex transcripts: context budget reports, before/after comparisons, source evidence, and skill regression tests. Local-only, stdlib-only.
branch-recap
Tells you what your branch actually changed — what was done, why, and what deserves a second look, instead of the diff — then files the fixes into the commits they belong to.