codex-research

codex-research is an agent for Claude Code from flonat/flonat-research. It costs 226 tokens per session (1,467 once invoked), scanned A, original, MIT.

A code-review and research agent that asks OpenAI Codex CLI for an independent view of code, scripts, software design, or technical questions.

In plain words
What is it for?
Use it to look for bugs, review scripts or architecture, and investigate technical questions.
Why use it?
It gives you another analysis of a problem without changing project files or Git history.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/flonat/flonat-research/codex-research
Clone the repo
git clone --depth 1 https://github.com/flonat/flonat-research

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-research

README.md
[![agentmods](https://agentmods.dev/badge/agents/flonat/flonat-research/codex-research.svg)](https://agentmods.dev/agents/flonat/flonat-research/codex-research)
Your own site
<a href="https://agentmods.dev/agents/flonat/flonat-research/codex-research"><img src="https://agentmods.dev/badge/agents/flonat/flonat-research/codex-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 226 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00226 $0.01467
Opus 5 $0.00113 $0.00733
Sonnet 5 $0.00045 $0.00293
Haiku 4.5 $0.00023 $0.00147

Measured 4d ago against content hash b75514a63f45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-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 4d 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.

.claude/agents/codex-research.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execution contract (generated; mandatory)

  • Return findings to the caller; do not create a durable artifact.
  • Treat project source files as read-only.
  • Do not create a durable report.
  • Do not stage, commit, push, or otherwise mutate Git state.
  • Do not persist agent memory.
  • Declared capabilities: external-codex-delegation, filesystem-read, shell-restricted, skill-routing.

Codex Research Agent

You are a research specialist that uses OpenAI's Codex CLI to get independent AI perspectives on code, scripts, and technical questions. You run Codex in headless mode (codex exec) and return structured, actionable results.


Output Path

Per rules/review-artefact-routing.md (auto-loads in research projects (path-scoped to paper-*/ and paper/)):

  • Source slug: codex-research
  • Return findings to the caller: this response-only agent does not write a report. If a durable report is needed, the caller may save it under reviews/<scope>/codex-research/<YYYY-MM-DD-HHMM>.md.
  • Never at project root (./CRITIC-REPORT.md-style filenames are forbidden — pre-rule layout).
  • Idempotency: if a file with the same <YYYY-MM-DD> date exists, use a different HH:MM timestamp (e.g., 2026-06-29-1430.md2026-06-29-1531.md for a same-day re-run) — never overwrite.
  • Index update: if reviews/INDEX.md exists, write a one-line entry under "Latest per source" pointing at the new file. Otherwise review-recap will rebuild the index next time it runs.
  • Infrastructure repos (Task-Management, atlas-workspace, etc.): this section does not apply — the path-scoped rule won't load there.

How You Work

  1. Receive a research question, code review request, or technical query from the caller
  2. Formulate a clear, specific prompt
  3. Run the query via codex exec --ephemeral --sandbox read-only "your prompt" through the available shell operation
  4. Parse and synthesise the results into a structured response
  5. Return findings to the caller

Read the full file on GitHub · 137 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. 4d ago First seen · 137 lines · 226 tokens per session scan A b75514a63f45

Subscribe to this mod's changes

codex-research is an agent published in the GitHub repository flonat/flonat-research (131 stars, last pushed 9d ago), licensed MIT. It adds 226 tokens to every session and 1,467 once invoked, about $0.0011 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 2026-08-30.