huashu-skills is a catalogue of Agent Skills, which are reusable instruction packages that extend coding agents such as Claude Code, Codex, and Kimi Code for particular tasks. It organizes skills for design, research, document conversion, content creation, and other workflows, and includes machine-readable metadata and update checking. The catalogue entries are the skills and related tools that agents install and use.
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.
npx skills add alchaincyf/huashu-skills --skill huashu-agent-swarmgit clone --depth 1 https://github.com/alchaincyf/huashu-skillsWrote 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.
[](https://agentmods.dev/skills/alchaincyf/huashu-skills/huashu-agent-swarm)<a href="https://agentmods.dev/skills/alchaincyf/huashu-skills/huashu-agent-swarm"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-skills/huashu-agent-swarm/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.
<a href="https://agentmods.dev/skills/alchaincyf/huashu-skills/huashu-agent-swarm"><img src="https://agentmods.dev/badge/skills/alchaincyf/huashu-skills/huashu-agent-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00054 | $0.01075 |
| Opus 5.5 | $0.00022 | $0.00430 |
| Sonnet 5.5 | $0.00011 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00108 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infinite Agent Loop - 无限Agent蜂群模式
受Nicholas Carlini用16个Claude实例自主构建C编译器的启发。 没有master agent，纯git自组织，每个agent独立认领任务、写代码、推送。
触发条件
当用户提到「蜂群模式」「多agent并行」「infinite loop」「agent swarm」「启动蜂群」时使用此技能。
前置要求
- tmux（
brew install tmux） - claude CLI（已安装）
- git 仓库（已有或新建）
使用流程
Step 1: 描述项目
用户告诉我：
- 项目目录路径（必须是git仓库）
- 项目目标和总体描述
- 初始任务列表（或让agent自行拆解）
- agent数量（默认8个）
- 代码规范和测试命令
Step 2: 初始化项目
bash SKILL_DIR/scripts/setup_project.sh <项目目录>
这会在项目中创建：
AGENT_PROMPT.md- 从模板生成，需要我根据用户需求定制TASKS.md- 初始任务清单current_tasks/- 任务认领目录agent_logs/- 日志目录
然后我根据 references/agent-prompt-template.md 定制 AGENT_PROMPT.md，填入项目具体信息。
Step 3: 启动蜂群
bash SKILL_DIR/scripts/start_swarm.sh <agent数量> <项目目录>
这会：
- 为每个agent创建 git worktree（共享.git对象库，不浪费磁盘）
- 创建 tmux session，每个pane一个agent
- 每个agent进入无限循环：pull → 认领任务 → 执行 → push → 下一个
Step 4: 打开观测台
python3 SKILL_DIR/scripts/dashboard.py <项目目录> 8420
浏览器打开 http://localhost:8420，可以：
- 实时查看所有agent状态、git log、任务进度
- 查看每个agent的最新日志
- 输入框直接发送指令给agent（写入HUMAN_INPUT.md）
- 一键停止所有agent
也可以用命令行监控：
# 终端状态
bash SKILL_DIR/scripts/status.sh <项目目录>
# 发送指令
bash SKILL_DIR/scripts/send_input.sh <项目目录> "你的指令"
# 直接进入tmux观察
tmux attach -t swarm-<项目名>
Step 5: 停止
bash SKILL_DIR/scripts/stop_swarm.sh <项目目录>
自动停止所有agent + 合并分支 + 清理worktrees。
核心机制
Git自组织协调
- 每个agent通过
current_tasks/*.lock文件认领任务 - 通过
TASKS.md了解全局进度 - 通过
git log了解其他agent的工作 - 冲突由agent自行解决
Git Worktree隔离
- 不用多份clone，用
git worktree实现隔离 - 所有worktree共享同一个
.git对象库 - 每个agent在自己的worktree独立工作
无限循环
- 每个agent完成一个session后自动开始下一个
- 通过
git pull获取其他agent的最新成果 - 通过 sleep 间隔避免API限流
关键配置
| 参数 | 默认值 | 说明 |
|---|---|---|
| agent数量 | 8 | 可在启动时指定 |
| sleep间隔 | 5秒 | agent_loop.sh中可调 |
| 模型 | claude-opus-4-6 | agent_loop.sh中可调 |
风险和应对
| 风险 | 应对 |
|---|---|
| API限流 | sleep间隔 + 可调agent数量 |
| 合并冲突 | AGENT_PROMPT指导小粒度commit |
| 死循环无用功 | 日志监控 + 停止条件 |
| 磁盘空间 | stop_swarm.sh自动清理 |
| 成本失控 | 可在AGENT_PROMPT中限制session数 |
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.
- references/agent-prompt-template.md 4.1 KB
- references/carlini-lessons.md 3.3 KB
- scripts/agent_loop.sh 2.8 KB runs code
- scripts/dashboard.py 21 KB runs code
- scripts/send_input.sh 1.0 KB runs code
- scripts/setup_project.sh 2.7 KB runs code
- scripts/start_swarm.sh 3.3 KB runs code
- scripts/status.sh 2.7 KB runs code
- scripts/stop_swarm.sh 2.3 KB runs code
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.
- 1mo ago First seen · 130 lines · 54 tokens per session scan A 9e8fce92d906
huashu-agent-swarm is a skill published in the GitHub repository alchaincyf/huashu-skills (2,025 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 1,075 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).