swarm

swarm is a skill for Codex from dayfinggg/openai-codex-agent-skills. It costs 51 tokens per session (372 once invoked), scanned A, original, MIT.

A method for splitting a question into several independent investigations or solution candidates, then comparing their results and choosing one. Each investigation covers a separate area before the findings are combined.

In plain words
What is it for?
Researching separate evidence areas, comparing designs, evaluating candidate solutions, and reviewing competing approaches.
Why use it?
It helps with broad or uncertain work where one investigation may miss evidence or another approach may be better. It also keeps overlapping work and shared file changes under control.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents.

Good fit Researching separate evidence areas, comparing designs, evaluating candidate solutions, and reviewing competing approaches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dayfinggg/openai-codex-agent-skills/swarm
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 dayfinggg/openai-codex-agent-skills --skill swarm
Clone the repo
git clone --depth 1 https://github.com/dayfinggg/openai-codex-agent-skills

Made for: 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 swarm

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dayfinggg/openai-codex-agent-skills/swarm"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 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 $0.00051 $0.00372
Opus 5 $0.00026 $0.00186
Sonnet 5 $0.00010 $0.00074
Haiku 4.5 $0.00005 $0.00037

Measured 4d ago against content hash e829ae1ba48d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

swarm 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 4d 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.

codex/skills/swarm/SKILL.md · 31 lines

What it actually says

Swarm

Follow the governing instructions and the user's requirements for communication, code style, authorization, and delegation. This skill supplies task-specific guidance, not permission to expand the task. Its workflow and output fields describe internal checks and relevant content, not a mandatory response layout or a progress report. When used within broader authorized work, continue that work through completion rather than stopping to deliver this skill's intermediate result.

Use parallel agents to increase coverage or diversity, not to duplicate the same unbounded request.

Partition

Define the shared question, success criteria, evidence standard, and final decision owner. Divide work into non-overlapping lanes by component, hypothesis, source class, risk category, or candidate approach. Resolve shared contracts before fan-out.

Dispatch

Give each worker a bounded brief with its lane, exclusions, output schema, and stopping condition. Use the smallest number of workers that covers the independent lanes. Do not let multiple workers edit the same files or state.

Drain

Collect all results before synthesis unless one result proves that the remaining work is unnecessary. Track missing or failed lanes. Do not hide disagreement between workers.

Judge

Compare evidence, reconcile duplicates, explain conflicts, and select a conclusion or base candidate. The primary agent remains responsible for integration and final verification.

Boundaries

Use parallel agents only when the user or governing instructions authorize them and collaboration tools are available. This skill does not itself grant that authorization. Respect a request to work personally without subagents. Do not ask again when delegation is already authorized. Otherwise work locally without claiming independent review.

Files

What ships with it

1 file 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. 4d ago Changed · +2 lines · -2 tokens per session e829ae1ba48d
  2. 5d ago Changed · +1 tokens per session 7bf11c399bcb
  3. 10d ago First seen · 29 lines · 52 tokens per session scan A df16f7788c76

Subscribe to this mod's changes

swarm is a skill published in the GitHub repository dayfinggg/openai-codex-agent-skills (4 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 372 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

code-review-excellence

This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.

Galaxy-Dawn/claude-scholar · 43 tokens

git-workflow

This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…

Galaxy-Dawn/claude-scholar · 64 tokens

architecture-design

Use only when creating new registrable ML components that require Factory or Registry patterns.

Galaxy-Dawn/claude-scholar · 19 tokens

results-analysis

This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…

Galaxy-Dawn/claude-scholar · 68 tokens

review-response

Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.

Galaxy-Dawn/claude-scholar · 51 tokens

daily-paper-generator

Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.

Galaxy-Dawn/claude-scholar · 47 tokens