swarm

swarm is a skill for Codex from ZaxbyHub/opencode-swarm. It costs 56 tokens per session (418 once invoked), scanned A, original, MIT.

A higher-rigor workflow posture for coding tasks that adds parallel investigation, planning, review, and final checking.

In plain words
What is it for?
Use it when you ask for swarm mode, maximum quality, parallel investigation, or extra review rigor on code, tests, documentation, metadata, or release work.
Why use it?
It adds structured review and independent criticism for changes where correctness and evidence matter.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions Codex.

Good fit Use it when you ask for swarm mode, maximum quality, parallel investigation, or extra review rigor on code, tests, documentation, metadata, or release work.

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

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/zaxbyhub/opencode-swarm/swarm.svg)](https://agentmods.dev/skills/zaxbyhub/opencode-swarm/swarm)
Your own site
<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/swarm"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/swarm.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 418 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 $0.00056 $0.00418
Opus 5 $0.00028 $0.00209
Sonnet 5 $0.00011 $0.00084
Haiku 4.5 $0.00006 $0.00042

Measured 7d ago against content hash 3e97df6beff3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

.agents/skills/swarm/SKILL.md · 32 lines

What it actually says

Swarm

Read .opencode/skills/swarm/SKILL.md for the source behavior model, then adapt it to Codex.

Codex-specific execution notes:

  • Treat this as a workflow posture, not an instruction to call OpenCode /swarm commands.
  • Use parallel local reads/searches where safe.
  • Use update_plan for visible task tracking on substantial work.
  • Add independent review pressure through $qa-sweep, $swarm-pr-review, or self-critic checks when subagents are unavailable.
  • Keep the user looped in with short progress updates during longer work.
  • For any task that edits code, tests, docs, package metadata, release notes, or skill files, final completion requires:
    1. objective validation evidence,
    2. independent implementation reviewer approval on the actual latest diff,
    3. separate critic approval after reviewer approval,
    4. no unresolved NEEDS_REVISION/BLOCKED items, and
    5. no edits after those approvals.
  • Record reviewer and critic verdicts in durable task artifacts. For issue-tracer work, use 08b-implementation-review.md and 09-final-critic.md; otherwise use task-local review artifacts unless the repo forbids artifacts.
  • Explorer subagents, a plan critic, passing tests, or self-review do not satisfy the final implementation-review gate when subagent delegation is available and swarm work is authorized.

For implementation tasks, prefer $swarm-implement; for fresh PR review, prefer $swarm-pr-review; for known PR feedback closure, prefer $swarm-pr-feedback; for bug tracing, prefer $issue-tracer.

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. 7d ago First seen · 32 lines · 56 tokens per session scan A 3e97df6beff3

Subscribe to this mod's changes

swarm is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (463 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 418 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 2026-08-30.