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/richer-richard/cc-researchWrote 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/richer-richard/cc-research/plugin)<a href="https://agentmods.dev/plugins/richer-richard/cc-research/plugin"><img src="https://agentmods.dev/badge/plugins/richer-richard/cc-research/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/richer-richard/cc-research/plugin"><img src="https://agentmods.dev/badge/plugins/richer-richard/cc-research/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cc-research 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "cc-research",
"version": "1.1.3",
"description": "Multi-agent deep research on Claude models: orchestrator -> parallel researcher subagents -> triangulate -> synthesize -> cite -> report. Built-in tools only (WebSearch, WebFetch, Read, Grep, Glob, Write, Task); no external research APIs or MCP servers.",
"author": {
"name": "Richard Huang"
},
"homepage": "https://github.com/richer-richard/cc-research",
"repository": "https://github.com/richer-richard/cc-research",
"license": "MIT",
"keywords": ["research", "deep-research", "multi-agent", "subagents", "citations"]
}
What it installs
The manifest is a name and a version. 1 skill, 1 command, 3 agents travel with it, and installing the plugin installs all of them — 340 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.
- 1mo ago First seen · 14 lines scan A b7f20eb72b84
cc-research is a plugin published in the GitHub repository richer-richard/cc-research (1 stars, last pushed 4mo 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
scout
Autonomous knowledge management and daily briefing system. Monitors your work tools (Slack, Calendar, Linear, GitHub, etc.), synthesizes findings into a persistent knowledge base with a formal ontology, and delivers daily action items — all running unattended via scheduled Claude Code sessions. Six session types…
scout-plugin marketplace
Marketplace for the Scout autonomous knowledge management plugin.
scout
Autonomous knowledge management and daily briefing system. Monitors your work tools (Slack, Calendar, Linear, GitHub, etc.), synthesizes findings into a persistent knowledge base with a formal ontology, and delivers daily action items — all running unattended via scheduled Claude Code sessions. Six session types…
visionclaw-agent
VisionClaw Agent — multi-tenant agentic AI platform exposing 243 production tools, 16 specialist personas, hybrid-search Skill-RAG, and a self-improving skill registry over MCP. One-click access to project management, Drive/email/calendar, web research, code execution, multi-channel messaging, schema-aware databases…
fabrik
Ambient awareness of Fabrik (the GitHub-Project-driven SDLC pipeline orchestrator) for the human's interactive Claude Code session. Turns Claude into a product-management buddy and supervisor for projects that use Fabrik to automate issue processing.
consilium-principis
A personal board of directors made of AI personas of real thinkers, grounded in public-domain texts, with a fidelity contour: quotes checked word-for-word by code, fail-closed abstention when there are no grounds.