codex-swarm

codex-swarm is a skill for Claude Code, Codex from Vallykrie/swarmGPT. It costs 144 tokens per session (2,596 once invoked), scanned B, original, MIT.

A workflow for coordinating multiple Codex command-line sessions to handle larger writing tasks. The main agent plans and reviews while delegated sessions produce the files.

In plain words
What is it for?
Use it for multi-file code, test, documentation, or other content changes that exceed roughly 20 lines.
Why use it?
Large changes can span several files and consume the main agent's context. Delegating the writing divides the work and keeps the main session focused on coordination and checking.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also agents/openai.yaml present. Also seen: mentions subagents; positional $N argument; mentions Codex.

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 swarmgpt plugin — 2 skills, 2 commands, 1 agent shipped together

Good fit Use it for multi-file code, test, documentation, or other content changes that exceed roughly 20 lines.

Compare 6 skills from other repositories ↓
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 Vallykrie/swarmGPT
Claude Code
/plugin install swarmgpt

Made for: Claude Code, Codex.

Or install swarmgpt, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 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-swarm

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/vallykrie/swarmgpt/codex-swarm"><img src="https://agentmods.dev/badge/skills/vallykrie/swarmgpt/codex-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,596 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00144 $0.02596
Opus 5 $0.00072 $0.01298
Sonnet 5 $0.00029 $0.00519
Haiku 4.5 $0.00014 $0.00260

Measured 8d ago against content hash 36044d06e2ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

codex-swarm scanned grade B with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/dispatch.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

once with `codex exec --help` / the user's `~/.codex/config.toml`, then report
skills/codex-swarm/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-swarm

You are the orchestrator: you plan, decompose, route, and review. codex exec sessions running GPT-5.6 do the writing and the token-heavy bulk work. Writing substantial code or content yourself instead of dispatching it is a violation of this workflow — the user installed this skill precisely so that Codex does the writing on their ChatGPT plan instead of burning your context.

Verified against Codex CLI 0.146.0. Re-check codex exec --help if flags seem wrong — this CLI changes fast.

Delegate by default

Before you write anything, apply this rule:

  • Writing work that spans more than one file or more than ~20 lines → dispatch it to Codex via this skill. This holds even when it is a single coherent task: a swarm of one subtask is a normal, valid run. Parallel fan-out is an optimization, not a precondition.
  • Trivial edits (a few lines in one file), pure planning/review, and answers that need no artifacts → do them yourself.
  • You still own everything around the writing: decomposition, prompts, model routing, integration, verification, and the final report.

If you catch yourself mid-task writing a file Codex could have written, stop, turn the remaining work into subtask prompts, and dispatch.

Excuse for writing it yourself Reality
"It's faster if I just write it" Dispatch overhead is seconds; Codex writes while your context stays free for review.
"This task doesn't split into parallel parts" A single-subtask dispatch is a valid swarm. Splitting is optional.
"I need fine control over this code" Put the control in the subtask prompt (exact paths, conventions, constraints), then review the result.
"The user didn't ask for a swarm" The user installed this skill so Codex does the writing by default. Explicit invocation is not required.
"I'm already halfway through writing it" Sunk cost. Dispatch the remaining files.

Step 0 — Preflight

Read the full file on GitHub · 218 lines

Files

What ships with it

2 files beside SKILL.md 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.

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. 8d ago First seen · 218 lines · 144 tokens per session scan B 36044d06e2ef

Subscribe to this mod's changes

codex-swarm is a skill published in the GitHub repository Vallykrie/swarmGPT (2 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 2,596 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

repomix-explorer

Analyze or explore a codebase (remote or local repository) by packing it with the Repomix CLI, then reading and searching the generated output. Use when the user wants a high-level understanding of an unfamiliar or large repo, not a targeted edit. Trigger for: Structure/overview: "analyze this repo", "what's the…

yamadashy/repomix · 227 tokens

agent-carnet

Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.

yamadashy/repomix · 67 tokens

website-maintainer

Use this skill when working on the Repomix documentation website in website/ directory, including VitePress configuration, multi-language content, or translation workflows.

yamadashy/repomix · 37 tokens

browser-extension-developer

Use this skill when developing or maintaining browser extension code in the browser/ directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

yamadashy/repomix · 43 tokens

stss

Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.

lennney/stop-that-shit · 63 tokens

superloopy-loop

Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-backed completion.

beefiker/superloopy · 31 tokens