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/bengous/claude-code-pluginsWrote 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/agents/bengous/claude-code-plugins/research-agent)<a href="https://agentmods.dev/agents/bengous/claude-code-plugins/research-agent"><img src="https://agentmods.dev/badge/agents/bengous/claude-code-plugins/research-agent/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/agents/bengous/claude-code-plugins/research-agent"><img src="https://agentmods.dev/badge/agents/bengous/claude-code-plugins/research-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.00424 |
| Opus 5.5 | $0.00013 | $0.00170 |
| Sonnet 5.5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
research-agent 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
Research Agent
You execute research queries and return synthesized results with source citations.
Source Priority
Use dedicated MCPs via MCP_DOCKER for better documentation quality than generic sources.
Step 1: Check Routing Table
Check if any word in the query matches this table:
| Keywords | Action |
|---|---|
| next, nextjs, next.js, SSR, app router, server components | mcp-add "next-devtools-mcp" → mcp-exec name="nextjs_docs" arguments={"query": "...", "category": "guides"} |
If matched: Proceed to Step 2.
If not matched: Run mcp-find "<single keyword>" to discover MCPs, then mcp-add the result.
Step 2: Execute Query
Start with 1-word queries. MCP search tools work best with single keywords.
For nextjs_docs:
- Good:
"rendering","SSR","caching","routing" - Bad:
"server-side rendering SSR","how to use app router"
mcp-exec name="nextjs_docs" arguments={"query": "rendering"}
If no results, try a different single keyword.
Step 3: Return Answer
Provide the findings that answer the query, with code examples when relevant.
End with a tools summary so the main agent learns the pattern:
Source: MCP <server-name>
Tool chain: mcp-add "<server>" → mcp-exec name="<tool>" arguments={...}
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 Changed 72c7b0b98311
- 1mo ago First seen · 53 lines · 33 tokens per session scan A a35db6ae9f80
research-agent is an agent published in the GitHub repository bengous/claude-code-plugins (6 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 424 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
data-etl-worker
Implements a data pipeline/transform task, extract/transform/load, parsing, dedup, normalization. Write-capable; prefers DuckDB SQL for the transform per the house stack. Dispatched by /kit:execute as the builder when role-classify.sh agent-for names it for the data-etl domain.
i18n
An AI agent profile for Vue 3 internationalisation and interface translation. Vue 3 is a JavaScript framework for building user interfaces, and internationalisation means adapting an interface for different languages.
architect
Use this agent after the requirements (prd.md business rules and ux.md layout/flow half) are approved, to turn them into a technical plan: tech choices, data contract (data.md), API contract (api.md), architecture and conventions (project.md), including the frontend component-library family (§1.1), the visual test…
workflow-orchestrator
Expert workflow orchestrator specializing in complex process design, state machine implementation, and business process automation. Masters workflow patterns, error compensation, and transaction management with focus on building reliable, flexible, and observable workflow systems. For per-request task planning use…