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.
git clone --depth 1 https://github.com/andreilungeanu/codex-delegate-mcpWrote 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.
[](https://agentmods.dev/plugins/andreilungeanu/codex-delegate-mcp/codex-delegate-mcp)<a href="https://agentmods.dev/plugins/andreilungeanu/codex-delegate-mcp/codex-delegate-mcp"><img src="https://agentmods.dev/badge/plugins/andreilungeanu/codex-delegate-mcp/codex-delegate-mcp/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.
<a href="https://agentmods.dev/plugins/andreilungeanu/codex-delegate-mcp/codex-delegate-mcp"><img src="https://agentmods.dev/badge/plugins/andreilungeanu/codex-delegate-mcp/codex-delegate-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 11d 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "codex-delegate",
"displayName": "Codex Delegate",
"version": "2.5.0",
"description": "Delegate coding tasks to the OpenAI Codex CLI with structured results, plan/ask/review modes, and cancel support.",
"author": {
"name": "Andrei Lungeanu",
"email": "[email protected]"
},
"homepage": "https://github.com/andreilungeanu/codex-delegate-mcp",
"repository": "https://github.com/andreilungeanu/codex-delegate-mcp",
"license": "MIT",
"mcpServers": "./.claude-plugin/mcp.json",
"hooks": "./.claude-plugin/hooks.json",
"keywords": [
"mcp",
"codex",
"openai",
"claude-code",
"delegation"
]
}
What it installs
The manifest is a name and a version. 1 skill, 1 command, 1 MCP server travel with it, and installing the plugin installs all of them — 101 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
4 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago Changed d4aa0a4007f9
- 12d ago Changed 789fc3fc5673
- 23d ago Changed d226fd36040e
- 1mo ago Changed be47e59cf8de
- 1mo ago Changed 90b2a5c5ebbf
- 1mo ago First seen · 24 lines scan A 6e7bd4e6a357
codex-delegate is a plugin published in the GitHub repository andreilungeanu/codex-delegate-mcp (2 stars, last pushed 12d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
orchestkit marketplace
The Complete AI Development Toolkit - 110 skills, 36 agents, 38 commands, 162 hooks for full-stack development.
ork
The Complete AI Development Toolkit — 110 skills, 36 agents, 162 hooks for full-stack development.
lesson-cards
Displays lesson hint cards when tool calls match known patterns. Additive surface during pilot; the classic --strict guard keeps its 12 block-severity denies.
memory-lens
Recalls the few memories related to each prompt: one line for the human, one context entry for the model. Local files only, no network on the hot path.
secrets-veil
Masks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, and high-entropy tokens. No reveal path.
cursor-delegate
Delegate coding tasks to cursor-agent over ACP, with structured results, plan mode, and clarification handling.