swarm-wave

swarm-wave is a skill for Claude Code from voxpelli/claude-beads. It costs 176 tokens per session (4,827 once invoked), scanned A, original, MIT.

A method for running development work with multiple agents in parallel waves. Each agent receives separate files to reduce conflicts when changes are combined.

In plain words
What is it for?
Use it to split a sprint into file-separated tasks, run research or coding waves, apply backpressure when needed, and review each wave before committing.
Why use it?
It organizes parallel work while adding a quality check before changes are committed, and records the temporary sprint state in SWARM files.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Part of the vp-beads plugin — 8 skills, 1 agent, 3 hooks shipped together

Good fit Use it to split a sprint into file-separated tasks, run research or coding waves, apply backpressure when needed, and review each wave before committing.

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

Made for: Claude Code.

Or install vp-beads, the plugin that ships this one along with the rest of its 8 skills, 1 agent, 3 hooks.

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-wave

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/voxpelli/claude-beads/swarm-wave"><img src="https://agentmods.dev/badge/skills/voxpelli/claude-beads/swarm-wave.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,827 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 $0.00176 $0.04827
Opus 5 $0.00088 $0.02413
Sonnet 5 $0.00035 $0.00965
Haiku 4.5 $0.00018 $0.00483

Measured 9d ago against content hash 2d6041426045, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

swarm-wave 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.

skills/swarm-wave/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swarm Wave

Orchestrate multi-agent development sprints using the swarm wave pattern: group file-disjoint work into waves, launch parallel task agents per wave, enforce a blocking quality gate before committing, and track sprint state in SWARM-NN.md files.

File isolation is the primary safety mechanism — agents within a wave each own distinct files, preventing merge conflicts without relying on worktrees.

This skill does not create beads issues (use /backlog-groomer), write retrospectives (use /retrospective), or gate sprint closure (the sprint-review agent handles that). It orchestrates the execution phase between backlog grooming and sprint close.

SWARM Files

Sprint state is tracked in SWARM-NN.md files in the project root (NN = sprint number). These are gitignored — they are ephemeral working documents, not committed artifacts.

Structure:

# SWARM-NN — Sprint Theme

Waves: N | Issues: N | Started: YYYY-MM-DD

## Wave 1 — [Theme]

Status: pending | running | gate-pending | gate-passed | committed
Issues: id1, id2, id3

### Agent Assignments

- Agent A: [file1, file2] -> issue-id
- Agent B: [file3] -> issue-id
- Research: [topic]

### Item Status

| Item        | State                              |
| ----------- | ---------------------------------- |
| id1         | pending / claimed / done / carried |
| id2         | pending / claimed / done / carried |

## Wave 2 — [Theme]
...

Item Status is the run-state table. When beads is available, bd is the source of truth (claim/close) and this table mirrors it for at-a-glance status. When beads is unavailable (ROADMAP or manual source), this table is the source of truth: the orchestrator owns all writes to it — pending at plan time, claimed when an agent launches, done when the agent reports complete, carried when an item is deferred to a later wave. Item is a beads id when beads is used, otherwise a short slug for the work item.

Workflows

Determine which workflow the user needs based on their request. If ambiguous, default to workflow 1 (Plan a swarm sprint) when the user mentions planning or starting a sprint, workflow 2 (Execute a wave) when a SWARM plan already exists, and workflow 3 (Post-wave gate) when a wave has completed and needs review.

Read the full file on GitHub · 382 lines

Files

What ships with it

6 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. 9d ago First seen · 382 lines · 176 tokens per session scan A 2d6041426045

Subscribe to this mod's changes

swarm-wave is a skill published in the GitHub repository voxpelli/claude-beads (2 stars, last pushed 25d ago), licensed MIT. It adds 176 tokens to every session and 4,827 once invoked, about $0.0009 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

schema-evolve

This skill should be used when the user asks about 'schema drift', 'schema evolution', 'evolve schema', 'schema sync', 'sync schemas', 'update schema fields', 'schema field frequency', 'missing schema fields', 'unused schema fields', 'schema proposal', 'schema cardinality', 'check schema', 'schema audit', 'schema…

voxpelli/vp-claude · 139 tokens

knowledge-garden

This skill should be used when the user asks to audit, health-check, or structurally validate one or more SPECIFIC named notes or a bounded topic cluster — 'audit these notes', 'check this note for orphans or broken links', 'fourth-wall check on [note]', 'validate the structure of [note]', 'spot-check [note]'. Runs a…

voxpelli/vp-claude · 152 tokens

knowledge-maintain

This skill should be used when the user asks to fix, repair, or tidy one or more SPECIFIC named notes — 'fix these notes', 'fix the issues in [note]', 'add the missing relations to [note]', 'tidy up [note]', 'fix orphan [note]', 'apply the gardener findings for [note]'. Applies structural fixes (missing sections…

voxpelli/vp-claude · 183 tokens

raindrop-triage

This skill should be used when the user asks to 'triage unsorted bookmarks', 'clean up raindrop inbox', 'sort unsorted', 'organize bookmarks', 'raindrop triage', 'process bookmark backlog', 'promote triaged bookmarks', 'classify triaged', 'raindrop cleanup', 'deduplicate bookmarks', 'find duplicate bookmarks', 'tag…

voxpelli/vp-claude · 181 tokens

session-bookmarks

This skill should be used to save URLs or links found this session as Raindrop bookmarks — triggers: 'bookmark URLs from this session', 'save links we found', 'save notable URLs to Raindrop', 'save session URLs', 'raindrop bookmarks from session'. Scans the current conversation for high-signal URLs discovered during…

voxpelli/vp-claude · 129 tokens

session-reflect

This skill should be used when the user asks to 'reflect on this session', 'save insights to memory', 'capture what we learned', 'commit this to memory', 'save decisions to Basic Memory', 'write up what we did', 'preserve what we found', 'save insights from this conversation', 'save what was discovered', 'capture…

voxpelli/vp-claude · 147 tokens