delegate-to-agent

delegate-to-agent is a skill for Claude Code, Codex from psychofanPLAYS/gemini4codex-mcp. It costs 26 tokens per session (345 once invoked), scanned A, original, MIT.

A task-delegation skill that sends work to separate coding agents, each working in its own Git worktree—a separate copy of the project files.

In plain words
What is it for?
It helps with parallel coding, code review, security checks, research, and other isolated tasks. It can also resume an existing worker and inspect its status and changes.
Why use it?
It keeps unfinished or experimental changes away from the main branch and lets independent tasks run at the same time. The main agent still checks the results before merging them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Codex.

Good fit It helps with parallel coding, code review, security checks, research, and other isolated tasks. It can also resume an existing worker and inspect its status and changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/psychofanplays/gemini4codex-mcp/delegate-to-gemini
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.

Any agent
npx skills add psychofanPLAYS/gemini4codex-mcp --skill delegate-to-gemini
Clone the repo
git clone --depth 1 https://github.com/psychofanPLAYS/gemini4codex-mcp

Made for: Claude Code, Codex.

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 delegate-to-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/psychofanplays/gemini4codex-mcp/delegate-to-gemini/github.svg)](https://agentmods.dev/skills/psychofanplays/gemini4codex-mcp/delegate-to-gemini)
Your own site
<a href="https://agentmods.dev/skills/psychofanplays/gemini4codex-mcp/delegate-to-gemini"><img src="https://agentmods.dev/badge/skills/psychofanplays/gemini4codex-mcp/delegate-to-gemini/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 delegate-to-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/psychofanplays/gemini4codex-mcp/delegate-to-gemini"><img src="https://agentmods.dev/badge/skills/psychofanplays/gemini4codex-mcp/delegate-to-gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 345 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 $0.00026 $0.00345
Opus 5 $0.00013 $0.00172
Sonnet 5 $0.00005 $0.00069
Haiku 4.5 $0.00003 $0.00034

Measured 9d ago against content hash 519b797ef295, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

delegate-to-agent 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 9d 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.

plugin/skills/delegate-to-gemini/SKILL.md · 29 lines

What it actually says

Delegate to Subagent

You can delegate complex, time-consuming, or isolated tasks to subordinate agents. Tasks run fully isolated in Git Worktrees, keeping your main branch safe. Codex is the final authority and must verify all results before merging them back.

Delegation Policy

  1. Check Existing Workers: ALWAYS call list_agent_runs before delegating to see if an existing worker should resume this workstream.
  2. Reuse When Appropriate: If a worker was doing related work, use continue_agent_run with its worker_id instead of spawning a new one.
  3. Build Bounded Contracts: Use delegate_to_agent with clear constraints. Include the workspace path, success criteria, and a specific objective.
  4. Select Profile:
    • scout: Read-only. Fast research and mapping.
    • reviewer: Read-only. Code review, security analysis, verification.
    • worker: Capable of writing code strictly within its isolated worktree.

After Delegation

  • Use get_agent_run_report to inspect completion status, JSON logs, and the Git Diff.
  • Review the worktree diff provided in the report carefully.
  • If the work is incomplete or flawed, run continue_agent_run to send corrections.
  • If the work is approved, use apply_agent_run to merge the worktree into the main branch.
  • If the work is rejected and not worth saving, use cleanup_agent_run to delete the worktree.
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. 9d ago First seen · 29 lines · 26 tokens per session scan A 519b797ef295

Subscribe to this mod's changes

delegate-to-agent is a skill published in the GitHub repository psychofanPLAYS/gemini4codex-mcp (1 stars, last pushed 28d ago), licensed MIT. It adds 26 tokens to every session and 345 once invoked, about $0.0001 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.