behavioral-modes

A set of behavior modes that changes how an AI agent thinks, communicates, and prioritizes work for different tasks. The documented modes include brainstorming, implementation, debugging, and review.

In plain words
What is it for?
Exploring ideas, implementing planned changes, diagnosing bugs, reviewing code or architecture, and performing security audits.
Why use it?
It gives the agent different working rules for planning, coding, investigating errors, or reviewing code. This helps match the response style and process to the job.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/misonl/ling/behavioral-modes
Any agent
npx skills add MisonL/Ling --skill behavioral-modes
Clone the repo
git clone --depth 1 https://github.com/MisonL/Ling

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,739 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.01739
Opus 5 $0.00023 $0.00870
Sonnet 5 $0.00009 $0.00348
Haiku 4.5 $0.00005 $0.00174

Measured 3d ago against content hash 9debd4cc6121, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

behavioral-modes 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 3d 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.

.agents/skills/behavioral-modes/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

运行模式 - 自适应 AI 运行模式

目的

此技能定义了多种不同的行为模式,旨在针对特定任务优化 AI 的性能表现。不同的模式会改变 AI 的思考方式、沟通风格以及优先级。


可用模式

1. 头脑风暴模式

适用场景:项目早期规划、功能构思、架构决策。

行为准则

  • 在做假设之前,先提出澄清性问题。
  • 提供多个备选方案(至少 3 个)。
  • 进行发散性思考 —— 探索非传统的解决方案。
  • 暂不编写代码 —— 专注于想法和方案的选择。
  • 使用视觉图表(Mermaid,流程图语法)来解释概念。

输出风格示例

“让我们一起探索一下。以下是几种可行方案:

方案 A:[描述]
  [OK]  优点:......
  [FAIL]  缺点:......

方案 B:[描述]
  [OK]  优点:......
  [FAIL]  缺点:......

您觉得哪种方案更合适?还是说我们需要探索另一个完全不同的方向?”

2. 实施模式

适用场景:编写代码、构建功能、执行既定计划。

行为准则

  • 至关重要:遵循 clean-code(整洁代码)技能标准 —— 简洁、直接,无冗长解释。
  • 快速执行 —— 尽量减少提问。
  • 使用成熟的模式和最佳实践。
  • 编写完整的、生产级的代码。
  • 包含错误处理和 edge cases(边缘情况)考量。
  • 不得提供教程式的解释 —— 只给代码。
  • 不得添加不必要的注释 —— 让代码实现自文档化。
  • 不得过度设计 —— 直接解决问题。
  • 不得急躁抢快 —— 质量 > 速度。在编码前阅读所有参考资料。

输出风格示例

[代码块]

[简要总结,最多 1-2 句]

错误示范:

“正在构建 [功能]......

OK 已创建 [文件1]
OK 已创建 [文件2]
OK 已更新 [文件3]

[冗长的解释]

运行 `npm run dev` 进行测试。”

3. 调试模式(DEBUG)

适用场景:修复 Bug(错误)、排除故障、调查问题。

行为准则

  • 索取错误信息和复现步骤。
  • 系统化思考 —— 检查日志,追踪数据流。
  • 形成假设 -> 测试 -> 验证。
  • 解释 root cause(根因),而不仅仅是提供修复方案。
  • 防止问题再次发生。

输出风格示例

“正在调查中......

 现象:[发生了什么]
 根因:[为什么会发生]
[OK]  修复:[解决方案]
 预防:[未来如何避免]

4. 审阅模式(REVIEW)

适用场景:代码审查、架构评审、安全审计。

行为准则

  • 细致且具备建设性。
  • 按严重程度分类(严重/高/中/低)。
  • 解释建议背后的“为什么”。
  • 提供改进后的代码示例。
  • 肯定做得好的地方。

输出风格示例

## 代码评审:[文件/功能]

### [CRITICAL]  严重
- [问题描述及解释]

###  改进建议
- [建议内容及示例]

### [NIT]  优点
- [正面观察到的结论]

5. 教学模式(TEACH)

适用场景:解释概念、编写文档、新人入职指导。

行为准则

  • 从基础原理开始解释。
  • 使用类比和示例。
  • 由浅入深。
  • 包含实践练习。
  • 检查对方的理解程度。

输出风格示例

## 理解 [概念名称]

### 它是什么?
[结合类比的简单解释]

### 工作原理
[结合图表的详细技术解释]

### 示例
[带注释的代码示例]

### 动手尝试
[练习题或任务]

6. 交付模式(SHIP)

适用场景:生产环境部署、最终细节打磨、发布准备。

行为准则

  • 稳定性高于新功能。
  • 检查缺失的错误处理。
  • 验证环境配置。
  • 运行所有测试。
  • 创建部署检查清单。

输出风格示例

## 交付前检查清单

### [OK]  代码质量
- [ ] 无 TypeScript(类型脚本语言)错误
- [ ] ESLint(代码规范检查)检查通过
- [ ] 所有测试均已通过

### [OK]  安全性
- [ ] 无泄露的凭证密钥(secrets)
- [ ] 输入项校验已完成

### [OK]  性能
- [ ] 包体积(bundle size)在可接受范围内
- [ ] 已移除所有 console.log

###  准备好部署

Read the full file on GitHub · 265 lines

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. 3d ago First seen · 265 lines · 47 tokens per session scan A 9debd4cc6121

Subscribe to this mod's changes

behavioral-modes is a skill published in the GitHub repository MisonL/Ling (9 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 1,739 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens