What is huashu-agent-swarm?

A workflow for having multiple coding agents work in parallel on one Git repository, coordinating through shared files and Git.

Use it to set up and run an agent swarm with tmux, a Git repository, a task list, and separate work areas for parallel development.

It organises task claiming, logs, prompts, and code changes when a project is large enough for several agents to work at once.

huashu-agent-swarm — Skill for Claude Code and Codex by Biraj2004

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 Biraj2004/huashu-skills-english --skill huashu-agent-swarm-en

Clone the repo

git clone --depth 1 https://github.com/Biraj2004/huashu-skills-english

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/biraj2004/huashu-skills-english/huashu-agent-swarm-en/github.svg)](https://agentmods.dev/skills/biraj2004/huashu-skills-english/huashu-agent-swarm-en)

Your own site

<a href="https://agentmods.dev/skills/biraj2004/huashu-skills-english/huashu-agent-swarm-en"><img src="https://agentmods.dev/badge/skills/biraj2004/huashu-skills-english/huashu-agent-swarm-en/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/biraj2004/huashu-skills-english/huashu-agent-swarm-en"><img src="https://agentmods.dev/badge/skills/biraj2004/huashu-skills-english/huashu-agent-swarm-en.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,554 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.03554
Opus 5	$0.00024	$0.01777
Sonnet 5	$0.00010	$0.00711
Haiku 4.5	$0.00005	$0.00355

Measured 12d ago against content hash e821fac09b65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

huashu-agent-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 12d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/agent_loop.sh, scripts/dashboard.py, scripts/send_input.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

huashu-agent-swarm-en/SKILL.md · 472 lines

How it starts

The opening of the file, as written. The whole thing — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Infinite Agent Loop — Multi-Agent Swarm Mode

Inspired by Nicholas Carlini's experiment of using 16 Claude instances to autonomously build a C compiler. No master agent. Pure git self-organisation. Each agent independently claims tasks, writes code, and pushes.

Trigger Conditions

Use this skill when the user mentions "swarm mode", "multi-agent parallel", "infinite loop", "agent swarm", or "launch swarm".

Prerequisites

tmux (brew install tmux)
Claude CLI (already installed)
A git repository (existing or new)

Usage Workflow

Step 1: Describe the Project

The user tells me:

Project directory path (must be a git repository)
Project goal and overall description
Initial task list (or let the agents break it down themselves)
Number of agents (default: 8)
Code standards and test commands

Step 2: Initialise the Project

bash SKILL_DIR/scripts/setup_project.sh <project-directory>

This creates the following inside the project:

AGENT_PROMPT.md — Generated from a template; I customise it based on user requirements
TASKS.md — Initial task checklist
current_tasks/ — Task claim directory
agent_logs/ — Logs directory

I then customise AGENT_PROMPT.md using references/agent-prompt-template.md, filling in project-specific details.

Step 3: Launch the Swarm

bash SKILL_DIR/scripts/start_swarm.sh <number-of-agents> <project-directory>

This will:

Create a git worktree for each agent (shared .git object store — no disk waste)
Create a tmux session with one pane per agent
Each agent enters an infinite loop: pull → claim task → execute → push → next task

Step 4: Open the Dashboard

python3 SKILL_DIR/scripts/dashboard.py <project-directory> 8420

Open http://localhost:8420 in your browser to:

View all agent statuses, git log, and task progress in real time
View the latest logs for each agent
Send instructions directly to agents via the input box (written to HUMAN_INPUT.md)
Stop all agents with one click

Read the full file on GitHub · 472 lines

Files

What ships with it

9 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.

12d ago First seen · 472 lines · 49 tokens per session scan A e821fac09b65

Subscribe to this mod's changes

huashu-agent-swarm is a skill published in the GitHub repository Biraj2004/huashu-skills-english (3 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 3,554 once invoked, about $0.0002 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.

Building agents Git and workflow claude claude-skills haushu-design haushu-skills skills

resolve-pr-comments

Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using reasoning recalled from past Claude Code transcripts). Use when the user asks to "resolve PR comments", "fix review comments", "address PR…

tobihagemann/turbo · 95 tokens

create-pr

Create a GitHub pull request with a drafted title and description. Use when the user asks to "create a PR", "create a pull request", "open a PR", or "submit a PR".

tobihagemann/turbo · 44 tokens

update-pr

Update an existing GitHub pull request's title and description to reflect the current state of the branch. Use when the user asks to "update the PR", "update PR description", "update PR title", "refresh PR description", or "sync PR with changes".

tobihagemann/turbo · 56 tokens

changelog-rules

Shared changelog conventions and formatting rules referenced by /create-changelog and /update-changelog. Not typically invoked directly.

tobihagemann/turbo · 29 tokens

fetch-pr-comments

Fetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR conversation comments) without making changes. Use when the user asks to "fetch PR comments", "show PR comments", "check PR for unresolved comments", "list review comments", "what comments are on the…

tobihagemann/turbo · 83 tokens

reply-to-pr-threads

Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".

tobihagemann/turbo · 71 tokens