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 agentmods add skills/misonl/ling/parallel-agentsnpx skills add MisonL/Ling --skill parallel-agentsgit clone --depth 1 https://github.com/MisonL/LingWhat 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 | $0.00037 | $0.01719 |
| Opus 5 | $0.00018 | $0.00860 |
| Sonnet 5 | $0.00007 | $0.00344 |
| Haiku 4.5 | $0.00004 | $0.00172 |
Grade A, and why
parallel-agents 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 2d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
原生并行智能体
通过 Antigravity 内置的智能体工具实现编排（Orchestration）。
概览（Overview）
本技能旨在通过 Antigravity 的原生智能体系统协调多个专业化 Agent（智能体）。与外部脚本不同，这种方法将所有编排逻辑完全置于 Antigravity 的控制之下。
何时使用编排
[OK] 适用场景：
- 需要跨多个专业领域的复杂任务。
- 从安全、性能和代码质量等多维度进行代码分析。
- 综合评审（架构 + 安全 + 测试）。
- 需要后端 + 前端 + 数据库协同工作的需求实现。
[FAIL] 不适用场景：
- 简单的、仅涉及单一领域的任务。
- 快速修复或细微变动。
- 单个 Agent 即可胜任的任务。
原生 Agent 调用
调用单个 Agent
请使用 security-auditor 智能体来审阅身份认证逻辑。
顺序链式调用
首先，使用 explorer-agent 探索项目结构。
然后，使用 backend-specialist 审阅 API 端点。
最后，使用 test-engineer 识别测试缺口。
带上下文传递的调用
使用 frontend-specialist 分析 React 组件。
基于该分析结果，让 test-engineer 生成对应的组件测试。
恢复先前的工作
恢复智能体 [agentId] 并继续执行其他需求。
编排模式
模式 1：全面分析
智能体流：explorer-agent -> [领域专家级 Agents] -> 综合汇总（Synthesis）
1. explorer-agent：绘制代码库结构图。
2. security-auditor：评估安全态势。
3. backend-specialist：评估 API 质量。
4. frontend-specialist：评估 UI/UX（界面/体验）模式。
5. test-engineer：评估测试覆盖率。
6. 综合汇总所有发现。
模式 2：功能评审
智能体流：[受影响领域的 Agents] -> test-engineer
1. 识别受影响的领域（后端？前端？还是二者兼有？）。
2. 调用相关的领域 Agent。
3. 由 test-engineer 验证变更。
4. 综合汇总改进建议。
模式 3：安全审计
智能体流：security-auditor -> penetration-tester -> 综合汇总
1. security-auditor：进行配置与代码审计。
2. penetration-tester：执行主动漏洞测试。
3. 综合汇总并给出按优先级排列的补救方案。
可用智能体清单
| 智能体（Agent） | 专业领域 | 触发词/场景 |
|---|---|---|
orchestrator |
全局协调 | "全面的", "多维度的", "综合的" |
security-auditor |
安全审计 | "安全", "认证", "漏洞" |
penetration-tester |
渗透测试 | "渗透测试", "红队", "exploit（利用）" |
backend-specialist |
后端开发 | "API（接口）", "服务器", "Node.js", "Express" |
frontend-specialist |
前端开发 | "React", "UI（界面）", "组件", "Next.js" |
test-engineer |
测试工程 | "测试", "覆盖率", "TDD（测试驱动开发）" |
devops-engineer |
运维开发 | "部署", "CI/CD（持续集成/交付）", "基础设施" |
database-architect |
数据库架构 | "模式（Schema）", "Prisma", "迁移" |
mobile-developer |
移动端开发 | "React Native", "Flutter", "移动端" |
debugger |
调试专家 | "Bug（缺陷）", "错误", "不工作" |
explorer-agent |
探索发现 | "探索", "映射", "结构" |
documentation-writer |
文档编写 | "写文档", "创建 README（说明文档）", "生成 API 文档" |
performance-optimizer |
性能优化 | "慢", "优化", "分析（Profiling）" |
project-planner |
项目策划 | "计划", "路线图", "里程碑" |
seo-specialist |
SEO 专家 | "SEO", "Meta（元）标签", "搜索排名" |
game-developer |
游戏开发 | "游戏", "Unity", "Godot", "Phaser" |
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.
- 2d ago First seen · 194 lines · 37 tokens per session scan A cb4e5f9e21a2
parallel-agents is a skill published in the GitHub repository MisonL/Ling (9 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,719 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…