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/futuresearch/futuresearch-pythonWrote 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/futuresearch/futuresearch-python/gemini-extension)<a href="https://agentmods.dev/plugins/futuresearch/futuresearch-python/gemini-extension"><img src="https://agentmods.dev/badge/plugins/futuresearch/futuresearch-python/gemini-extension/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/futuresearch/futuresearch-python/gemini-extension"><img src="https://agentmods.dev/badge/plugins/futuresearch/futuresearch-python/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
futuresearch 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 10d 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": "futuresearch",
"description": "Gemini extension for FutureSearch: forecast questions about the future, including the outcome under each option of a choice you or someone else is weighing. Also runs web research agents.",
"version": "0.27.0",
"mcpServers": {
"futuresearch": {
"command": "uvx",
"args": ["futuresearch-mcp"],
"env": {
"FUTURESEARCH_API_KEY": "$FUTURESEARCH_API_KEY"
}
}
}
}
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.
- 10d ago Changed b6c683b45458
- 15d ago Changed 79085acf3ffa
- 1mo ago First seen · 15 lines scan A 48c6208dada4
futuresearch is a plugin published in the GitHub repository futuresearch/futuresearch-python (57 stars, last pushed 2d 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 2026-09-07.
Other plugins, from other repositories
ci-review
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting via gh api.
relay
Delegate work packets from a lead Claude Code session to executor sessions in their own iTerm tabs, with session reuse instead of always spawning fresh.
agent-harness
Multi-agent harness for Claude Code: Planner→Generator→Evaluator sprints executed as background dynamic workflows (Agent-tool fallback), fable/opus/sonnet/haiku model routing with per-role reasoning effort, harness-engineering framework for design/diagnosis, and Anthropic 2026-04-04 P-G-E pattern.
hato
Carrier-pigeon messaging between Claude Code sessions — send messages and files, and get woken up by other sessions across your machines.
productionos
AI engineering OS for Claude Code and Codex — 80 agents, 41 commands, 18 hooks.
orodruin-labs marketplace
Plugin marketplace listing 1 plugin: nazgul.