agentmods.dev

codex-delegate

codex-delegate is a skill for Claude Code from smk-labs/claude-plugins. It costs 98 tokens per session (469 once invoked), scanned A, original, MIT.

A delegation tool that sends one self-contained coding or research task to the Codex command-line program using a user's ChatGPT account. The main agent keeps the plan and context while Codex performs the assigned slice and returns an answer.

In plain words
What is it for?
Use it for a bounded coding or research task, choose or inspect an account, run longer work in the background, and review the resulting files.
Why use it?
It lets a task use a separate Codex account allowance instead of the current agent's allowance. Because Codex can edit files directly without approval, its changes still need a diff review.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions subagents; runs codex exec.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cursor-delegate plugin — 4 skills, 1 agent shipped together

not rated 11repo 28d ago A scan 98 tokens original MIT

Good fit Use it for a bounded coding or research task, choose or inspect an account, run longer work in the background, and review the resulting files.

Compare 6 skills from other repositories ↓
View source ↗ smk-labs/claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add smk-labs/claude-plugins
Claude Code
/plugin install cursor-delegate

Made for: Claude Code.

Or install cursor-delegate, the plugin that ships this one along with the rest of its 4 skills, 1 agent.

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-delegate

README.md
[![agentmods](https://agentmods.dev/badge/skills/smk-labs/claude-plugins/codex-delegate/github.svg)](https://agentmods.dev/skills/smk-labs/claude-plugins/codex-delegate)
Your own site
<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/codex-delegate"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/codex-delegate/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-delegate

Your own site · 80×15
<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/codex-delegate"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/codex-delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 469 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 $0.00098 $0.00469
Opus 5.5 $0.00039 $0.00188
Sonnet 5.5 $0.00020 $0.00094
Haiku 4.5 $0.00010 $0.00047

Measured 27d ago against content hash 75f32d9dc4dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-delegate 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 27d 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.

cursor-delegate/skills/codex-delegate/SKILL.md · 28 lines

What it actually says

Delegate to Codex

Hand one self-contained task to codex exec on one of the user's ChatGPT accounts. Claude keeps the plan and the context; Codex does the slice and returns its final answer.

Run it

"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.sh" --cwd "<repo>" "<the whole task, self-contained>"
  • No --account is the normal case: the account with the most weekly room left is picked.
  • --account <label> when the user names one. --list shows every account with what it has left.
  • --model <m> only when the user asks for one.
  • Anything longer than a couple of minutes: run it with the Bash tool's run_in_background, and read the result when it finishes. Only the final answer goes to stdout; progress goes to stderr.

The worker is fully trusted (no approvals, no sandbox) and edits files in --cwd directly, so review its diff the way you would a subagent's before saying the work is done. Say which account ran it.

If it fails

  • "no accounts": the accounts are added once on the Mac with daftar codex add (one browser login each), and daftar codex writes them on every machine.
  • "the login has expired" or a 401: the Mac refreshes the logins daily; ask the user to run daftar codex on the Mac. Never run codex login into ~/.claude-deck/codex/<label>: those copies must not hold a refresh token.
  • Never set OPENAI_API_KEY: that bills the API, not the subscription.
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. 27d ago First seen · 28 lines · 98 tokens per session scan A 75f32d9dc4dc

Subscribe to this mod's changes

codex-delegate is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 28d ago), licensed MIT. It adds 98 tokens to every session and 469 once invoked, about $0.0004 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 2026-09-28.

Building agentsclaudeclaude-code-marketplaceclaude-code-pluginsclaude-skillspersian
Related

Other skills, from other repositories

pmm-resume

Reviews and tailors a PMM resume (IC to VP, including AI PMM roles): dissects the job description, ranks bullets by impact fit and rebuilds the complete resume in one pass. Trigger on: resume + JD paste, "tailor this", "which bullets for this role", "rebuild for [company]", "review my PMM resume", "reframe for…

stefanoskarakasis/Product-Marketing-Skills · 98 tokens

product-marketing-context

Builds and maintains the shared GTM brain (product context, ICP, positioning, voice, market context, proof points, plus optional strategy and execution sections and the deal-reality fields) that every other skill reads before producing output. Works standalone from your own answers, and gets stronger when you connect…

stefanoskarakasis/Product-Marketing-Skills · 139 tokens

competitor-deep-dive

Builds a long-form, fully sourced deep-dive on one competitor for a named decision (strategy call, RFP, pricing change, roadmap bet), with dated reviews, deal evidence, a head-to-head per offering and where they win. Triggers: "deep-dive on [competitor]", "full competitor write-up", "what do users really say about…

stefanoskarakasis/Product-Marketing-Skills · 107 tokens

workflow-orchestrator

Chains positioning, competitive, GTM strategy, campaign briefs, stakeholder maps and retros into one coherent PMM program with a master document and brain updates. Trigger on: "run full GTM workflow", "run a full launch", "launch [product] end to end", "positioning refresh", "quarterly PMM cycle", "competitive…

stefanoskarakasis/Product-Marketing-Skills · 105 tokens

positioning-messaging

Builds or audits positioning statements, messaging hierarchies, homepage copy and persona cards using April Dunford's Obviously Awesome framework, in five modes (build, audit, fletch, sales-enablement, homepage). Refuses to generate without a named primary persona and 3+ alternatives including status quo, and blocks…

stefanoskarakasis/Product-Marketing-Skills · 97 tokens

writing-assistant

Rewrites, sharpens and drafts B2B writing in the writer's real voice: Slack messages, emails, memos, PRDs, decks, plus marketing content (blog posts, landing pages, press releases, case studies, newsletters, social posts). Use whenever someone wants to rewrite, tighten, draft or audit copy, asks why copy isn't landing…

stefanoskarakasis/Product-Marketing-Skills · 117 tokens