agent-boundary-design

agent-boundary-design is a skill for Claude Code from AgenticAIPlan/AgenticAISkills. It costs 63 tokens per session (1,488 once invoked), scanned A, original, MIT.

A framework for deciding what a business agent may do on its own, what needs human approval, and what it must refuse. It also defines when work should be handed to a person.

In plain words
What is it for?
Use it to design boundaries for quality checks, ticket routing, approvals, fraud review, customer support, escalation, and other business workflows.
Why use it?
It prevents an agent from taking risky actions without oversight and makes its responsibilities clear to users and developers.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agentic-ai-skills plugin — 54 skills shipped together

Good fit Use it to design boundaries for quality checks, ticket routing, approvals, fraud review, customer support, escalation, and other business workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agenticaiplan/agenticaiskills/agent-boundary-design
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 AgenticAIPlan/AgenticAISkills --skill agent-boundary-design
Clone the repo
git clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkills

Made for: Claude Code.

Or install agentic-ai-skills, the plugin that ships this one along with the rest of its 54 skills.

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.

agentmods badge for agent-boundary-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/agent-boundary-design/github.svg)](https://agentmods.dev/skills/agenticaiplan/agenticaiskills/agent-boundary-design)
Your own site
<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/agent-boundary-design"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/agent-boundary-design/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.

agentmods 80×15 button for agent-boundary-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/agent-boundary-design"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/agent-boundary-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,488 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.01488
Opus 5 $0.00032 $0.00744
Sonnet 5 $0.00013 $0.00298
Haiku 4.5 $0.00006 $0.00149

Measured 12d ago against content hash c729faf3e86c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-boundary-design 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.

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.

skills/agent-boundary-design/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

智能体开发边界规范

适用场景

当用户需要为某个业务智能体明确以下内容时,使用本 Skill:

  • 智能体应该自主完成什么
  • 哪些动作必须人工确认
  • 哪些高风险动作必须保留给人工
  • 单 Agent 是否应该拆成多个 Agent
  • 当前智能体是否因为“做太多”或“做太少”而影响用户信任

典型业务场景包括:

  • 质量检测或质量拦截智能体
  • 工单分派、升级和闭环跟踪智能体
  • 审批辅助、风控预审或合规校验智能体
  • 客服初判、销售线索分级、售后诊断等需要人机协同的业务流程智能体

输入要求

  • 智能体服务的业务目标或任务描述
  • 智能体面向的用户角色
  • 智能体可能执行的关键动作列表
  • 高风险动作、合规约束或错误代价
  • 是否存在人工审核、人工接管或多 Agent 协作场景
  • 是否已有业务 SOP、规则阈值、审批链路、系统接口或审计要求

执行步骤

  1. 先写清楚该智能体的单一职责,使用一句 job story 表达:当什么情况发生时,智能体需要完成什么动作,以帮助用户达成什么结果。
  2. 判断该智能体更接近建议型还是执行型:
    • 建议型 Agent:输出判断、建议、草稿或分级结果,不直接调用业务系统产生后果。
    • 执行型 Agent:会调用系统、修改状态、发出通知、触发审批、放行、拦截、派单或升级等动作。
    • 混合型 Agent:先给出建议或预览,经过人工确认后才执行动作。
  3. 列出关键高风险动作(如有,通常 1-3 个),并逐项判断:
    • 是否可逆
    • 一旦出错代价有多高
    • 当前模型或系统对该动作是否具备足够可靠性
  4. 按风险和可信度将动作划分为三类:
    • Zone A:可自主执行,执行后通知用户即可
    • Zone B:先生成结果或执行预览,再由用户确认
    • Zone C:必须拒绝执行并转交人工
  5. 明确 handoff 规则:
    • 什么条件下转人工
    • 转交时要带上哪些上下文
    • 人工处理后如何恢复到 Agent 流程
  6. 对照业务流程检查系统边界:
    • 如果是建议型 Agent,明确它不能直接调用哪些系统或执行哪些动作。
    • 如果是执行型或混合型 Agent,明确它会调用哪些业务系统,以及是否会触发放行、拦截、审批、告警、派单、升级等后果明确的动作。
    • 对所有会产生业务后果的动作,说明是否需要记录操作员、时间戳、阈值依据和审计链路。
  7. 判断是否需要拆分多 Agent。只有在职责、信任等级、上下文或能力边界明显不同的情况下才拆分,否则优先保持单 Agent。
  8. 最后输出结构化的边界设计文档,并标注风险、假设和上线前检查项。

输出要求

输出必须使用结构化 Markdown,至少包含以下内容:

## Agent Boundary Spec

### 1. 智能体单一职责
- Job Story:
- 类型:建议型 / 执行型 / 混合型

### 2. Zone A:自主执行
- 动作:
- 触发条件:
- 调用系统(如适用):

### 3. Zone B:人工确认
| 动作 | 触发条件 | 确认方式 |
|------|----------|----------|

### 4. Zone C:拒绝执行并转人工
- 场景:
- 原因:

### 5. Handoff 规则
- 转人工条件:
- 转交内容:
- 恢复方式:
- 幂等保护:
- 审计要求:

### 6. 是否需要拆分多 Agent
- 结论:
- 理由:

### 7. 风险与待确认项
- 风险:
- 假设:
- 上线前检查项:

业务示例

示例:发动机 100 阶啸叫质量拦截智能体

  • Job Story:当发动机在变速测试台架上完成扫频测试,智能体基于同步采集的转速信号与音频信号,实时追踪 100 阶啸叫声纹并判断是否超标,从而提升出厂拦截率并减少人工负担。
  • Zone A:同步采集音频与转速信号,执行阶次跟踪,判断全转速范围内 100 阶幅值是否超标;当置信度达标且结论明确时,自动写入日志并给出放行或拦截结果。
  • Zone B:当阈值附近震荡、同步误差超标、扫频范围不完整、连续多台异常或新型号首次测试时,展示幅值-转速曲线、置信度、超标区间,由质检员确认拦截、放行或重测。
  • Zone C:当传感器离线、同步失锁、涉及整批次召回、结果与人工分析冲突,或超出“100 阶啸叫”定义范围时,必须拒绝执行并转交人工。
  • Handoff:转人工时附带曲线图、原始音频和转速数据、触发原因、超标转速区间;人工确认后恢复结果记录步骤,并写入操作员 ID、时间戳与覆盖原因。

Read the full file on GitHub · 116 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. 12d ago First seen · 116 lines · 63 tokens per session scan A c729faf3e86c

Subscribe to this mod's changes

agent-boundary-design is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 1,488 once invoked, about $0.0003 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 2026-08-30.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens