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/akougkas/helios-mcpWrote 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/akougkas/helios-mcp/helios-plugin)<a href="https://agentmods.dev/plugins/akougkas/helios-mcp/helios-plugin"><img src="https://agentmods.dev/badge/plugins/akougkas/helios-mcp/helios-plugin/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/akougkas/helios-mcp/helios-plugin"><img src="https://agentmods.dev/badge/plugins/akougkas/helios-mcp/helios-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
helios 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 yesterday.
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": "helios",
"version": "0.5.0-beta.1",
"description": "Learns your working style and negotiates an update with you when what it actually does drifts from what you've declared.",
"author": {"name": "Helios Contributors"},
"homepage": "https://github.com/akougkas/helios-mcp",
"repository": "https://github.com/akougkas/helios-mcp",
"license": "MIT",
"keywords": ["behavioral", "personality", "drift", "personalization", "preferences"]
}
What it installs
The manifest is a name and a version. 1 skill, 1 agent, 9 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 98 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill helios A 35 tokens
- Agent helios-observer A 63 tokens
- Hook SessionStart A not measured
- Hook PostToolUse A not measured
- Hook PostToolUseFailure A not measured
- Hook SessionEnd A not measured
- Hook SubagentStart A not measured
- Hook SubagentStop A not measured
- Hook UserPromptSubmit A not measured
- Hook Notification A not measured
- Hook Stop A not measured
- MCP server helios A not measured
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.
- yesterday First seen · 11 lines scan A ef5dd7c2abaa
helios is a plugin published in the GitHub repository akougkas/helios-mcp (2 stars, last pushed yesterday), 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 2026-09-19.
Other plugins, from other repositories
notion-mcp-server
Token-auth Notion MCP server: pages, databases, blocks, comments, files and templates behind three context-efficient tools (read, write, describe), with batched writes and markdown round-trip.
mcptoon
Zero-dependency CLI to discover and call MCP servers with compact manifests and TOON-compressed results; doubles as a single stdio bridge.
openclaw
OpenClaw AI assistant integration. Chat, manage sessions, access memory, and run async tasks through your OpenClaw instance.
prism-coder
Your coding agent forgets everything between sessions. Prism gives it a memory that sticks: your decisions, open TODOs, and changed files, restored the moment you return. It goes past a notes store — associative recall surfaces related past work, drift detection catches a long session wandering off-goal, and an…
joplin-mcp
Claude Code plugin for Joplin MCP server — orchestration guidance for 26 note-management tools.
anytype-toolbox-skills
Agent Skills for Anytype setup, including a dedicated headless account for one LLM-sharing space, plus anyr and any-mcp workflows.