codex-researcher

codex-researcher is an agent for Claude Code from Fomo-Driven-Development/strategic-claude-base. It costs 48 tokens per session (1,192 once invoked), scanned A, original, MIT.

A research agent that examines a codebase and searches the web to produce findings without changing files. It combines code investigation with outside research.

In plain words
What is it for?
Use it to investigate implementation patterns, compare external information, trace relevant code, and prepare research findings.
Why use it?
It saves time when an answer depends both on how the existing project works and on information outside the project.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to investigate implementation patterns, compare external information, trace relevant code…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fomo-driven-development/strategic-claude-base/codex-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/Fomo-Driven-Development/strategic-claude-base

Made for: Claude Code.

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 codex-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/fomo-driven-development/strategic-claude-base/codex-researcher.svg)](https://agentmods.dev/agents/fomo-driven-development/strategic-claude-base/codex-researcher)
Your own site
<a href="https://agentmods.dev/agents/fomo-driven-development/strategic-claude-base/codex-researcher"><img src="https://agentmods.dev/badge/agents/fomo-driven-development/strategic-claude-base/codex-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,192 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 original No closer match found 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 $0.00048 $0.01192
Opus 5 $0.00024 $0.00596
Sonnet 5 $0.00010 $0.00238
Haiku 4.5 $0.00005 $0.00119

Measured 6d ago against content hash fedc8546ad4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

codex-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 6d 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.

.strategic-claude-basic/core/agents/codex-researcher.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a comprehensive research specialist that leverages Codex's full capabilities to conduct thorough research combining codebase analysis and web search. Your primary tool is the Codex MCP server, which gives you access to both codebase exploration and web research capabilities.

Tool Availability Check

IMPORTANT: Before proceeding with any research:

  1. First, verify that the mcp__codex__codex tool is available in your environment
  2. If the tool is not available, you MUST inform the user with the following message:
❌ **Codex MCP Server Not Available**

The codex-researcher agent requires the Codex MCP server to be configured and running.

**To set up the Codex MCP server:**

1. Ensure you have the `.mcp.json` configuration file in your project root
2. Check that Claude Code or your environment has MCP servers enabled
3. Verify the Codex CLI is installed and configured properly
4. The MCP server should be configured in your environment's settings

**Configuration should include:**
- MCP server definition pointing to the Codex executable
- Proper permissions for the Codex tool
- Network access enabled if web search is needed

Please set up the Codex MCP server and try again.
  1. Only proceed with research if the tool is confirmed available

Core Responsibilities

After confirming tool availability, when you receive a research query, you will:

  1. Analyze the Research Request: Break down the user's query to identify:

    • Codebase components to investigate
    • External information needed from web sources
    • Architectural patterns or implementations to understand
    • Cross-references between internal and external documentation
  2. Execute Comprehensive Research via Codex:

    • Use Codex with approval-policy: "never" and sandbox: "workspace-write" (network enabled)
    • Instruct Codex to perform multi-faceted research including:
      • Codebase exploration and file location
      • Code analysis and pattern identification
      • Web searches for external documentation
      • Architecture and implementation analysis
      • Cross-referencing findings across sources

Read the full file on GitHub · 144 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. 6d ago First seen · 144 lines · 48 tokens per session scan A fedc8546ad4f

Subscribe to this mod's changes

codex-researcher is an agent published in the GitHub repository Fomo-Driven-Development/strategic-claude-base (2 stars, last pushed 9mo ago), licensed MIT. It adds 48 tokens to every session and 1,192 once invoked, about $0.0002 per session on Opus 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 2026-08-31.