agentmods.dev

codex-executor

codex-executor is an agent for Claude Code from tentenco/skills. It costs 64 tokens per session (375 once invoked), scanned A, original, MIT.

A dispatcher that sends implementation or diagnosis tasks to the OpenAI Codex command-line agent, then checks the repository and reports the result.

In plain words
What is it for?
Use it for repository implementation, alternate diagnoses, and fresh-perspective engineering tasks with a test or other explicit success check.
Why use it?
It can delegate bulk coding or a second opinion while keeping verification separate from the delegated agent’s own report.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; runs codex exec; mentions Codex.

not rated 5repo 1mo ago A scan 64 tokens original MIT

Good fit Use it for repository implementation, alternate diagnoses, and fresh-perspective engineering tasks with a test or other explicit success check.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tentenco/skills/codex-executor
View source ↗ tentenco/skills skills.tenten.co
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/tentenco/skills

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-executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/tentenco/skills/codex-executor/github.svg)](https://agentmods.dev/agents/tentenco/skills/codex-executor)
Your own site
<a href="https://agentmods.dev/agents/tentenco/skills/codex-executor"><img src="https://agentmods.dev/badge/agents/tentenco/skills/codex-executor/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 codex-executor

Your own site · 80×15
<a href="https://agentmods.dev/agents/tentenco/skills/codex-executor"><img src="https://agentmods.dev/badge/agents/tentenco/skills/codex-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 375 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 $0.00064 $0.00375
Opus 5.5 $0.00026 $0.00150
Sonnet 5.5 $0.00013 $0.00075
Haiku 4.5 $0.00006 $0.00038

Measured 2mo ago against content hash e686007eb4af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-executor 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 2mo 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.

skills/engineering/fable-codex-setup/templates/agents/codex-executor.md · 26 lines

What it actually says

You are a thin dispatcher around the Codex CLI. Your only job: hand a task to Codex, verify the result, and report back in as few tokens as possible. You do not write code yourself.

Procedure:

  1. Compose one self-contained prompt for Codex. It must include: the goal, relevant file paths, hard constraints, and a verifiable success criterion (e.g. "npm test passes"). Codex shares no context with this conversation — spell everything out.
  2. Run it from the repository root: 
    codex exec --full-auto "<prompt>"
    Use a generous timeout (10 minutes; longer for big tasks). If codex is not installed, stop and report that the user needs npm i -g @openai/codex + codex login.
  3. Verify — don't trust the transcript: check git diff --stat, and run the success-criterion command yourself.
  4. Report back ONLY:
    • What changed (files + one line each)
    • Verification result (the actual command output tail, not a paraphrase)
    • Codex's key reasoning if it disagrees with the task premise
    • Blockers, if any

Never paste Codex's full session log into your reply. If Codex fails twice on the same task, stop and return its error plus your diagnosis instead of retrying a third time.

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. 2mo ago First seen · 26 lines · 64 tokens per session scan A e686007eb4af

Subscribe to this mod's changes

codex-executor is an agent published in the GitHub repository tentenco/skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 375 once invoked, about $0.0003 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 2026-08-31.

Building agents
Related

codex-executor compared with agents from other repositories

codex-executor next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
codex-executortentenco/skillsAgent51mo agoMITA64Claude Code
playwright-test-generatormicrosoft/playwrightAgent99ktodayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79ktodayMITA33Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
code-revieweranthropics/claude-cookbooksAgent54k3d agoMITA52Claude Code
Pimcore Expertgithub/awesome-copilotAgent41kyesterdayMITA26Claude Code