New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Swarm

by ZaxbyHub in ZaxbyHub/opencode-swarm

Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode.

MITAuto-check passedAgent Workflows

Install Swarm

skills CLI
$ npx skills add ZaxbyHub/opencode-swarm --skill swarm -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZaxbyHub/opencode-swarm swarm --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/swarm .claude/skills/swarm && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
swarm
GitHub stars
494
Token cost
~3.9k tokens
SKILL.md length
1,813 words
Files
1
Skills in repo
91
Repo updated
First seen
Licence
MIT

At a glance

Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode.

  • The user wants swarm-like behavior
  • Calls bunx
  • Higher review rigor
  • Maximum quality without sacrificing Claude Code speed

What it does

Swarm is an agent skill from ZaxbyHub/opencode-swarm. Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. The repository describes itself as: Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review. The licence is MIT.

When your agent uses it

  • The user wants swarm-like behavior
  • Higher review rigor
  • Maximum quality without sacrificing Claude Code speed

Example prompts

  • “/swarm”

What it can do on your machine

Read from SKILL.md and the folder at commit b63a4bd. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bunx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use bunx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Swarm loads about 3.9k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 1,813 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ZaxbyHub/opencode-swarm at commit b63a4bd, republished under its MIT licence (© ZaxbyHub). 1,813 words, ~3,866 tokens.

Download SKILL.mdSave it as .claude/skills/swarm/SKILL.md (or your agent's skills folder).
name
swarm
description
Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.
audience
swarm-plugin
disable-model-invocation
true
argument-hint
[optional task]

/swarm

Enable swarm mode for the current session. If arguments are provided, enable swarm mode first and then execute that task using the swarm-like implementation workflow.

Argument handling:

  • If no arguments are provided: only enable swarm mode.
  • If the first word of $ARGUMENTS is a known plugin subcommand (see list below): do NOT treat it as a swarm task. Instead, tell the user to run it as a slash command directly (e.g., /swarm close, /swarm handoff). These are OpenCode plugin commands handled by the swarm plugin's command system, not tasks for the swarm workflow. Do NOT try to interpret or execute them yourself.
  • Otherwise: enable swarm mode, then treat $ARGUMENTS as the task to execute immediately.
SWARM-NAMESPACED subcommands — DO NOT confuse with Claude Code built-in commands

These are invoked as /swarm <subcommand>, NOT as bare /subcommand. The list below is generated from the COMMAND_REGISTRY (src/commands/registry.ts) and includes all registered non-deprecated base commands and subcommands:

Core / state

  • /swarm status — show current swarm state
  • /swarm show-plan — show current plan (optionally filter by phase number)
  • /swarm plan — deprecated alias for /swarm show-plan
  • /swarm agents — list registered agents
  • /swarm help — show help for swarm commands (optionally [command])
  • /swarm history — show completed phases summary
  • /swarm config — show current resolved configuration
  • /swarm export — export plan and context as JSON
  • /swarm dataset consent — HUMAN-ONLY: grant or revoke the training-content consent (two-step confirm token; quotas clamp to hard ceilings)
  • /swarm dataset withdraw — HUMAN-ONLY: confirmed destructive withdrawal — purge vault content, write a tombstone, revoke exports
  • /swarm dataset export — HUMAN-ONLY: governed deterministic dataset export (preview + confirm token; manifest with sha256 checksums)
  • /swarm evidence — show evidence bundles [taskId]
  • /swarm evidence summary — generate evidence summary with completion ratio and blockers
  • /swarm evidence-summary — deprecated alias for /swarm evidence summary
  • /swarm handoff — prepare state for clean model switch
  • /swarm archive — archive old evidence bundles [--dry-run]
  • /swarm retrieve — retrieve full output from a summary <id>
  • /swarm rollback — restore swarm state or project files to a checkpoint
  • /swarm reset — clear swarm state files [--confirm]
  • /swarm reset-session — clear session state, preserve plan/evidence/knowledge
  • /swarm recover — settle wedged coder settlements [task_id] [--force] (human-only)
  • /swarm checkpoint — manage project checkpoints [save|restore|delete|list] <label>
  • /swarm finalize — finalize the swarm project and archive evidence
  • /swarm close — deprecated alias for /swarm finalize
  • /swarm auto-proceed — toggle or set auto-proceed override [on|off]
  • /swarm concurrency — manage runtime concurrency override [set|status|reset]

Harness evolution

  • /swarm blueprint validate — validate a declarative harness blueprint or atomic blueprint patch
  • /swarm blueprint current — show the ledger-derived current harness blueprint projection
  • /swarm blueprint history — show bounded hash-verified harness version history
  • /swarm blueprint diff — compare two stored harness blueprint versions
  • /swarm blueprint export — export a canonical stored harness blueprint
  • /swarm harness candidate validate — validate an inert harness candidate manifest
  • /swarm harness candidate show — show bounded harness candidate metadata without raw patch content
  • /swarm harness candidate diff — show candidate file and blueprint-change metadata without raw patch content

Diagnostics / health

  • /swarm diagnose / /swarm diagnosis — run health check on swarm state (diagnosis is a deprecated alias)
  • /swarm config doctor — run config doctor checks
  • /swarm config-doctor — deprecated alias for /swarm config doctor
  • /swarm doctor — deprecated alias for /swarm config doctor
  • /swarm doctor tools — run tool registration coherence check
  • /swarm doctor-tools — deprecated alias for /swarm doctor tools
  • /swarm preflight — run preflight automation checks
  • /swarm lanes — list active, awaiting-merge, and conflicted worktree lanes
  • /swarm sync-plan — ensure plan.json and plan.md are synced
  • /swarm benchmark — show performance metrics [--cumulative] [--ci-gate] [--max-cost-usd <n>]
  • /swarm review — run the independent review model against a selected Git diff
  • /swarm costs — show per-agent and per-task token/cost telemetry [--json]
  • /swarm learning — show learning metrics and violation trends
  • /swarm guardrail explain — dry-run: show what guardrails would do (executes nothing)
  • /swarm guardrail-explain — deprecated alias for /swarm guardrail explain
  • /swarm guardrail-log — read the guardrail decision log
  • /swarm coupling — measure plan coupling and rank modules driving conflicts
  • /swarm dark-matter — detect hidden file couplings via co-change NPMI analysis
  • /swarm simulate — dry-run hidden coupling analysis with configurable thresholds
  • /swarm ci-simulate — create a temporary merge-result worktree and run CI pre-merge
  • /swarm ci — advisory headless CI: read-only gate/evidence evaluation with machine exit codes (0 = all gates pass; Markdown + [SWARM_CI_JSON] report; bunx opencode-swarm ci outside OpenCode)
  • /swarm qa-gates — view or modify QA gate profile for the current plan
  • /swarm report — query the SQLite observability sink (filters: --task/--session/--trace/--run/--since, --json)
  • /swarm dashboard — show the opt-in local mission-control dashboard URL and status (issue #2509; disabled unless dashboard.port > 0)
  • /swarm acknowledge-spec-drift — acknowledge spec drift and suppress further warnings

Knowledge / memory / curation

  • /swarm knowledge — list knowledge entries
  • /swarm knowledge migrate — migrate knowledge entries to the current format
  • /swarm knowledge quarantine — move a knowledge entry to quarantine
  • /swarm knowledge restore — restore a quarantined or archived knowledge entry
  • /swarm knowledge unactionable — list unactionable knowledge entries pending hardening
  • /swarm knowledge retry-hardening — reset retire candidates for re-hardening
  • /swarm knowledge hive-quarantine — human-only exact-ID quarantine of hive-store entries with backup and rollback (issue #2033)
  • /swarm memory — show Swarm memory commands
  • /swarm memory status — show Swarm memory provider, JSONL, and migration status
  • /swarm memory pending — show pending Swarm memory proposals
  • /swarm memory recall-log — summarize Swarm memory recall usage
  • /swarm memory value-log — show Swarm memory Q-value and reward updates
  • /swarm memory compact — compact deleted/superseded/expired scratch memories
  • /swarm memory stale — list stale and low-utility Swarm memories
  • /swarm memory export — export current Swarm memory to JSONL files
  • /swarm memory evaluate — run golden Swarm memory recall evaluation fixtures
  • /swarm memory audit-verify — verify the memory audit-log hash chain (tamper detection)
  • /swarm memory import — import legacy JSONL memory into SQLite
  • /swarm memory migrate — run the one-time legacy JSONL to SQLite migration
  • /swarm memory consolidation-log — summarize recent memory consolidation passes
  • /swarm memory link — share memory across linked worktrees (requires memory.link.enabled)
  • /swarm memory link status — show whether memory is cohort-linked (distinct from knowledge link)
  • /swarm memory unlink — stop sharing memory; copies cohort family back to local
  • /swarm curate — run knowledge curation and hive promotion review
  • /swarm consolidate — run quota-bounded skill-improver consolidation
  • /swarm promote — manually promote a lesson to hive knowledge
  • /swarm link — tie this worktree to a shared swarm knowledge store
  • /swarm link status — show whether this worktree shares knowledge via a link
  • /swarm unlink — stop sharing swarm knowledge for this worktree
  • /swarm write-retro — write a retrospective evidence bundle for a completed phase
  • /swarm skill-opt — governed single-skill optimizer (plan|run|status|diff|approve|reject|rollback|history); disabled by default (skill_opt.enabled)
  • /swarm skill-opt plan — propose an optimization round (dry-run; no mutation)
  • /swarm skill-opt run — execute the optimization loop (requires skill_opt.enabled=true and --confirm)
  • /swarm skill-opt status — show the current candidate lifecycle state
  • /swarm skill-opt diff — show baseline-vs-candidate diff summary for a candidate
  • /swarm skill-opt approve — activate a pending candidate (human-only; requires --expected-content-hash)
  • /swarm skill-opt reject — record a rejection for a candidate (no active-skill mutation)
  • /swarm skill-opt rollback — restore the pre-activation snapshot (appends a rolled_back event)
  • /swarm skill-opt history — show the append-only lifecycle event log for a candidate
  • /swarm harness-opt — governed HarnessOpt capstone (plan|run|status|stop|history); disabled by default (harness_opt.enabled)
  • /swarm harness-opt plan — freeze the comparative task set and report loop status (dry-run)
  • /swarm harness-opt run — execute one governed optimization round in a disposable worktree (human-only; requires harness_opt.enabled=true and --confirm; a test split consumes the held-out set once)
  • /swarm harness-opt compare — separately executable comparative evaluation: baseline/ablation/simple-agent arms, manifest validation, independent-oracle verdict, retained pilot record (human-only; --confirm)
  • /swarm harness-opt status — show loop status and the latest round lineage summary
  • /swarm harness-opt stop — human-only operator stop with a recorded reason
  • /swarm harness-opt history — list durable round lineage records (bounded)
Show full SKILL.md (607 more words)Show less

Architect MODE workflows

  • /swarm brainstorm — enter architect MODE: BRAINSTORM (seven-phase planning)
  • /swarm loop — enter architect MODE: LOOP (compound-engineering loop)
  • /swarm council — enter architect MODE: COUNCIL (multi-model deliberation)
  • /swarm clarify — clarify and refine an existing feature specification
  • /swarm specify — generate or import a feature specification
  • /swarm analyze — analyze spec.md vs plan.md for requirement coverage gaps
  • /swarm sdd — manage OpenSpec-compatible SDD artifacts
  • /swarm sdd status — show OpenSpec-compatible SDD status
  • /swarm sdd validate — validate OpenSpec-compatible artifacts
  • /swarm sdd project — materialize the effective spec into .swarm/spec.md
  • /swarm epic — toggle Epic Mode (autonomous coupling-aware parallel activation)
  • /swarm turbo — toggle Turbo Mode strategy [on|off|lean|standard|epic|status]
  • /swarm full-auto — toggle Full-Auto Mode; accepts on [mode], off, or status
  • /swarm guardrail reset — reset an action-local guardrail circuit after external repair
  • /swarm post-mortem — run the post-mortem agent (project-end synthesis)

Read-only audits / research

  • /swarm deep-dive / /swarm deep dive — launch deep codebase audit (parallel explorers, dual reviewers, critic)
  • /swarm deep-research / /swarm deep research — launch cited multi-source deep research pass
  • /swarm codebase-review / /swarm codebase review — run codebase-review-swarm
  • /swarm design-docs / /swarm design docs — generate or sync language-agnostic design docs

PR / issue workflows

  • /swarm issue — ingest a GitHub issue (intake → localization → resolution spec) [--plan] [--trace] [--no-repro]
  • /swarm pr-review — launch deep PR review with multi-lane analysis
  • /swarm pr-feedback — ingest and close known PR feedback (review comments, CI failures, conflicts)
  • /swarm abort-pr-workflow — clear a stuck PR_REVIEW/PR_FEEDBACK mechanical gate and stop the auto-resume loop (human-only escape hatch)
  • /swarm pr-feedback-loop — stop the autonomous PR babysitting settling loop for this session (stop <reason...>; cancels any armed publication via the #2584 route, records a terminal cancelled state with the operator reason, clears unsettled monitor events, and writes a cleanup receipt; human-only)
  • /swarm approve-plan-critic — record a MANUAL plan-critic approval to unblock the ratchet-tighter critic_pre_plan execution gate when the critic already returned APPROVED but the snapshot was not recorded (human-only escape hatch)
  • /swarm approve-write — issue one exact, session-bound, one-shot write approval for a candidate action and content hash (human-only)
  • /swarm ci-monitor — drive an already-reviewed, approved PR to green and merged (monitor CI, fix, merge; max 5 fix cycles)
  • /swarm pr subscribe / /swarm pr-subscribe — subscribe session to PR state-change notifications
  • /swarm pr unsubscribe / /swarm pr-unsubscribe — unsubscribe session from PR notifications
  • /swarm pr status / /swarm pr-status — show PR monitor subscription status
CRITICAL NAMING CONFLICTS

These swarm subcommands share exact names with CC built-in commands. Invoking the bare form instead of /swarm <name> causes irreversible damage:

Swarm CommandCC Built-inDamage
/swarm planCC /planEnters CC plan mode — blocks execution
/swarm resetCC /resetWipes entire conversation context
/swarm checkpointCC /checkpointReverts conversation history
/swarm historyCC /historyShows CC conversation history instead of swarm phase history

All swarm commands: /swarm <subcommand>. Never the bare name.

COMMAND INVOCATION RULE

All commands in this list are invoked as /swarm <subcommand>. Never invoke the bare subcommand as a standalone slash command. /plan, /status, /reset, /checkpoint, /agents, /config, /export, /doctor are Claude Code built-in commands with completely different behaviors. The /swarm prefix is mandatory, not optional.

Examples:

  • /swarm — enable swarm mode only
  • /swarm implement OAuth login without breaking existing session handling — enable swarm mode, then execute the task
  • /swarm fix the failing auth refresh tests and verify the session flow — enable swarm mode, then execute the task
  • /swarm close — this is a plugin subcommand; tell the user it will be handled by the plugin command system
  • /swarm handoff — this is a plugin subcommand; tell the user it will be handled by the plugin command system

Behavior model

The canonical swarm behavior model (goal, workflow posture, quality/speed policy, default triage model, and the mandatory implementation closeout gate) lives at .opencode/skills/swarm/SKILL.md. This file holds only the Claude Code /swarm command wiring above; the cross-agent contract is canonical.

© ZaxbyHub, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/swarm of ZaxbyHub/opencode-swarm.

Open the folder on GitHubat commit b63a4bd

Compare with similar skills

Swarm next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Swarm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Swarm this skillZaxbyHub/opencode-swarm494—~3.9kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k10 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k36 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT
Skill CreatorAzure/azqr79689 repos~8.2kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 10 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes

  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 36 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    796 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

More from ZaxbyHub/opencode-swarm

All 91 skills in this repo

  • Codebase Review Swarm

    ZaxbyHub/opencode-swarm

    Runs an evidence-gated, quote-grounded audit of a codebase for security, QA, accessibility, performance and more, and writes a verified report without changing source files.

    496 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Issue Tracer

    ZaxbyHub/opencode-swarm

    Drives a bug report from validation and root-cause tracing through a critic-reviewed plan, an approved minimal fix and a PR-ready closure, never merging without recorded human approval.

    496 GitHub stars~4.4k tokensUpdated today
    Auto-check passed

  • Commit and PR Publishing for Codex

    ZaxbyHub/opencode-swarm

    Codex adapter for opencode-swarm that governs commits, pushes, draft PRs, PR body updates and CI closeout, deferring to the repo's canonical commit-pr protocol.

    496 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Durable Session State

    ZaxbyHub/opencode-swarm

    Keeps plans, decisions, evidence and reviewer verdicts in small files so long multi-phase tasks survive context compaction and session resumes.

    496 GitHub stars~896 tokensUpdated today
    Auto-check passed

  • Swarm PR Feedback Closer

    ZaxbyHub/opencode-swarm

    Ingests existing pull request feedback such as review comments and CI failures, verifies each claim, fixes confirmed issues and reports closure status for every item.

    496 GitHub stars~14k tokensUpdated today
    Auto-check passed

  • Swarm PR Subscribe

    ZaxbyHub/opencode-swarm

    Monitor a pull request after creation and act autonomously on pushed PR activity.

    496 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Swarm

What does Swarm do?

Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Swarm is an agent skill from ZaxbyHub/opencode-swarm. Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode.

When should I use Swarm?

Swarm fits situations like: the user wants swarm-like behavior; higher review rigor; maximum quality without sacrificing Claude Code speed.

How do I install Swarm in Claude Code?

Run `npx skills add ZaxbyHub/opencode-swarm --skill swarm -a claude-code`. Or copy the skill folder (.claude/skills/swarm in ZaxbyHub/opencode-swarm) into .claude/skills/swarm in your project. Claude Code loads it when a task matches its description.

How do I install Swarm in Codex?

Run `npx skills add ZaxbyHub/opencode-swarm --skill swarm -a codex`. Or copy the skill folder (.claude/skills/swarm in ZaxbyHub/opencode-swarm) into .agents/skills/swarm in your project. Codex loads it when a task matches its description.

Can I use Swarm in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZaxbyHub/opencode-swarm --skill swarm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/swarm, .gemini/skills/swarm, .github/skills/swarm and .opencode/skills/swarm in your project.

What does Swarm need to run?

Going by SKILL.md and its folder, Swarm needs the command-line tools its instructions call (bunx).

Does Swarm access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Swarm safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Swarm use?

Swarm is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Swarm use?

About 3.9k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Swarm?

Skills that share tags, products or a category with Swarm: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Swarm?

ZaxbyHub (a GitHub organization) maintains it in ZaxbyHub/opencode-swarm, which has 494 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on October 10, 2026.

Source: ZaxbyHub/opencode-swarm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.