ferrox-ai-researcher

ferrox-ai-researcher is an agent for Claude Code from FerroxLabs/ferrox-factory. It costs 68 tokens per session (1,446 once invoked), scanned A, a copy of gsd-ai-researcher, MIT.

A research agent that studies the official documentation for a chosen AI framework and turns it into implementation guidance. It covers framework patterns, syntax, best practices, and known pitfalls for frameworks such as CrewAI, LangChain, LlamaIndex, and OpenAI Agents SDK.

In plain words
What is it for?
Use it to prepare the framework quick-reference and implementation-guidance sections of an AI-SPEC.md file.
Why use it?
It saves developers from piecing together framework rules and examples across documentation. It focuses the guidance on the specific framework and use case being implemented.

Agent for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths.

Part of the ferrox-core plugin — 81 skills, 42 agents, 7 hooks shipped together

Good fit Use it to prepare the framework quick-reference and implementation-guidance sections of an AI-SPEC.md file.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ferroxlabs/ferrox-factory/ferrox-ai-researcher
Install

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.

Clone the repo
git clone --depth 1 https://github.com/FerroxLabs/ferrox-factory

Made for: Claude Code.

Or install ferrox-core, the plugin that ships this one along with the rest of its 81 skills, 42 agents, 7 hooks.

Wrote 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.

agentmods badge for ferrox-ai-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/ferroxlabs/ferrox-factory/ferrox-ai-researcher/github.svg)](https://agentmods.dev/agents/ferroxlabs/ferrox-factory/ferrox-ai-researcher)
Your own site
<a href="https://agentmods.dev/agents/ferroxlabs/ferrox-factory/ferrox-ai-researcher"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ferrox-factory/ferrox-ai-researcher/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.

agentmods 80×15 button for ferrox-ai-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/ferroxlabs/ferrox-factory/ferrox-ai-researcher"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ferrox-factory/ferrox-ai-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.01446
Opus 5 $0.00034 $0.00723
Sonnet 5 $0.00014 $0.00289
Haiku 4.5 $0.00007 $0.00145

Measured 10d ago against content hash 1e0dcda2cda6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ferrox-ai-researcher 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.

Origin

This is a copy

94% identical to gsd-ai-researcher — 37 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/ferrox-ai-researcher.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@~/.claude/ferrox-core/references/untrusted-input-boundary.md

<documentation_lookup> @~/.claude/ferrox-core/references/research-documentation-lookup.md </documentation_lookup>

<required_reading> Read ~/.claude/ferrox-core/references/ai-frameworks.md for framework profiles and known pitfalls before fetching docs. </required_reading>

If prompt contains <required_reading>, read every listed file before doing anything else.

<documentation_sources> Use context7 MCP first (fastest). Fall back to WebFetch.

Framework Official Docs URL
CrewAI https://docs.crewai.com
LlamaIndex https://docs.llamaindex.ai
LangChain https://python.langchain.com/docs
LangGraph https://langchain-ai.github.io/langgraph
OpenAI Agents SDK https://openai.github.io/openai-agents-python
Claude Agent SDK https://docs.anthropic.com/en/docs/claude-code/sdk
AutoGen / AG2 https://ag2ai.github.io/ag2
Google ADK https://google.github.io/adk-docs
Haystack https://docs.haystack.deepset.ai
</documentation_sources>

<execution_flow>

Update AI-SPEC.md at ai_spec_path:

Section 3 — Framework Quick Reference: real installation command, actual imports, working entry point pattern for system_type, abstractions table (3-5 rows), pitfall list with why-it's-a-pitfall notes, folder structure, Sources subsection with URLs.

Section 4 — Implementation Guidance: specific model (e.g., claude-sonnet-5, gpt-4o) with params, core pattern as code snippet with inline comments, tool use config, state management approach, context window strategy.

4b.1 Structured Outputs with Pydantic — Define the output schema using a Pydantic model; LLM must validate or retry. Write for this specific framework + system_type:

  • Example Pydantic model for the use case
  • How the framework integrates (LangChain .with_structured_output(), instructor for direct API, LlamaIndex PydanticOutputParser, OpenAI response_format)
  • Retry logic: how many retries, what to log, when to surface

4b.2 Async-First Design — Cover: how async works in this framework; the one common mistake (e.g., asyncio.run() in an event loop); stream vs. await (stream for UX, await for structured output validation).

4b.3 Prompt Engineering Discipline — System vs. user prompt separation; few-shot: inline vs. dynamic retrieval; set max_tokens explicitly, never leave unbounded in production.

4b.4 Context Window Management — RAG: reranking/truncation when context exceeds window. Multi-agent/Conversational: summarisation patterns. Autonomous: framework compaction handling.

Read the full file on GitHub · 117 lines

Changes

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.

  1. 10d ago First seen · 117 lines · 68 tokens per session scan A 1e0dcda2cda6

Subscribe to this mod's changes

ferrox-ai-researcher is an agent published in the GitHub repository FerroxLabs/ferrox-factory (22 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,446 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to gsd-ai-researcher, differing in 37 lines, and is treated as a copy.