tool-permission-system SKILL.md skillA
tool-permission-system from simbajigege/book2skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add simbajigege/book2skills/tool-permission-system@git:20260630.76c29e9Pins git:20260630.76c29e9 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- simbajigege/book2skills
- Path
skills/tool-permission-system/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260630.76c29e9, committed Jun 30, 2026
- First version recorded
- Jun 4, 2026
- Size
- 10,534 bytes
- Repository stars
- 202
- License
- MIT
Design and implement a layered, configurable permission/safety system for agent tools. Use this skill when building an agent that needs to control which tool calls are auto-allowed, which require user confirmation, and which are denied — especially when the system must be configurable across multiple scopes (project/user/enterprise) and extensible via hooks. Triggers on: "权限系统", "工具安全", "tool permission", "permission system", "tool safety", "allow/deny rules", "hook system", "构建安全机制".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Tool Permission System
## Core Idea
Every time an agent calls a tool, a **permission pipeline** runs before execution. This pipeline is the single place that decides: auto-allow, ask the user, or deny. The pipeline is layered — different stakeholders (enterprise admin, user, project team, session) can each contribute rules, with higher layers overriding lower ones.
```
Tool call request
↓
[硬否决] Deny rules → immediate deny
↓
[强制确认] Ask rules → force prompt (even in bypass mode)
↓
[工具自身] Tool's checkPermissions() → tool-specific logic
↓
[安全绕过免疫] Safety checks (.git/, .claude/, shell configs) → prompt, immune to bypass
↓
[模式快速通过] Bypass / acceptEdits mode → immediate allow
↓
[白名单] Allow rules → immediate allow
↓
[默认] passthrough → prompt user (ask)
```
**外层包装**（作用于整条流水线之后）：
- `dontAsk` 模式：把所有 `ask` 转为 `deny`（用于无交互的后台 agent）
- `auto` 模式：把所有 `ask` 转给 AI 分类器判断，而不是打断用户
- `headless` 模式：先跑 PermissionRequest hooks，hooks 没回应就自动 deny
## Workflow
### 1. 定义三种决策行为
```typescript
type PermissionBehavior = 'allow' | 'deny' | 'ask'
type PermissionDecision =
| { behavior: 'allow'; updatedInput?: unknown; decisionReason?: DecisionReason }
…Read the whole file at its exact version.
How to install
mdr add simbajigege/book2skills/tool-permission-system@sha256:bd62cca62d196e13The line at the top of this page pins the label git:20260630.76c29e9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_spjktgk7342tdzcr)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jun 4, 2026 and Jun 30, 2026, about one every 13 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260630.76c29e9 latest | 2026-06-30 | 76c29e9 | 10,534 B | A | view · diff |
| git:20260604.cfc6e2d | 2026-06-04 | cfc6e2d | 8,167 B | A | view · diff |
| git:20260604.8c7f0ed | 2026-06-04 | 8c7f0ed | 8,165 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10534 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
simbajigege/book2skills · 202 stars · license MIT · pushed 2026-08-26 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_spjktgk7342tdzcr GET https://markdownregistry.com/api/v1/resolve?ref=simbajigege/book2skills/tool-permission-system GET https://markdownregistry.com/api/v1/blob/bd62cca62d196e13f3aa5f46ceeec0d867ddcb1a72d7044893a2c8552b7891ce
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.