Spawns isolated Claude agents to run tasks in parallel, each with fresh context so they don't trip over each other's assumptions. The mayor (your session) plans the work, identifies which tasks can run concurrently based on dependencies, then dispatches workers that write results to disk as JSON. Uses runtime-native backends (Claude teams, Codex sub-agents, or gc pool) and falls back to sequential execution if multi-agent isn't available. Best for when you have independent tasks that don't share files or need to wait on each other. Integrates with the crank skill for autonomous epic execution, but you can also use it directly with TaskList commands if you just want parallelism without the full beads workflow.

skills.sh installs
1.5K
GitHub stars
454
last updated
Aug 21, 2026

Install

$ npx -y skills add boshu2/agentops --skill swarm --agent claude-code

Installs into .claude/skills of the current project.

Files

Spawns isolated Claude agents to run tasks in parallel, each with fresh context so they don't trip over each other's assumptions. The mayor (your session) plans the work, identifies which tasks can run concurrently based on dependencies, then dispatches workers that write results to disk as JSON. Uses runtime-native backends (Claude teams, Codex sub-agents, or gc pool) and falls back to sequential execution if multi-agent isn't available. Best for when you have independent tasks that don't share files or need to wait on each other. Integrates with the crank skill for autonomous epic execution, but you can also use it directly with TaskList commands if you just want parallelism without the full beads workflow.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/boshu2/agentops
First seen
May 16, 2026

More from boshu2/agentops

All 54

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs