← 返回 Skills 市场
tangsuann

Grill Gate

作者 TangSuann · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
41
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install grill-gate
功能描述
Runtime-level grill enforcement plugin. Blocks exec/spawn calls for research/development tasks unless a valid grill token exists. Ensures agents think before...
使用说明 (SKILL.md)

Grill Gate

Runtime-level enforcement that prevents agents from executing research/development tasks without completing a grill (design review) session first.

The Problem

Writing "always do a design review before coding" in AGENTS.md is a prompt-level constraint — the agent can forget or ignore it. Even wrapping dispatch logic in a script doesn't help if the agent can bypass the script with raw exec.

The Solution

Grill Gate hooks into OpenClaw's before_tool_call runtime hook — a layer the agent cannot bypass. Before any exec or sessions_spawn call actually executes, the plugin checks:

  1. Is this a blocked command (e.g., hermes, a coding agent CLI)?
  2. Does the task contain research/development trigger keywords?
  3. Is there a valid grill token?

No token → blocked. The agent physically cannot proceed without completing the grill process first.

How It Works

Agent wants to exec hermes / spawn subagent
    ↓
before_tool_call hook fires (runtime-level, unforgeable)
    ↓
grill-gate checks: blocked command? trigger keywords?
    ↓
YES → check for grill token in .grill-tokens/
    ↓
No token → BLOCK (tool call rejected)
Has token → ALLOW (proceed normally)

Configuration

Create ~/.openclaw/grill-gate.json (all fields optional):

{
  "triggers": ["research", "develop", "design", "architect", "plan", "refactor", "migrate"],
  "exemptions": ["ASAP", "skip grill", "just do it"],
  "blockedCommands": ["hermes", "claude", "codex"],
  "tokenDir": "/path/to/.grill-tokens",
  "tokenTtlSeconds": 3600
}

Or set via environment variable:

export GRILL_GATE_CONFIG='{"triggers":["research","design"],"tokenTtlSeconds":7200}'

Language Presets

Built-in presets for Chinese and English keywords (both loaded by default):

Language Triggers Exemptions
Chinese 研究, 开发, 设计, 架构, 方案, 规划, 重构, 迁移 快点, 直接做, 赶紧
English research, develop, design, architect, plan, refactor, migrate ASAP, skip grill, just do it

Issuing Grill Tokens

After completing a grill-with-docs session:

python3 scripts/auto_dispatch.py --issue-grill-token "task description"
# Returns: {"token_id": "abc123", "status": "issued"}

Tokens are one-hour, one-use files stored in the configured tokenDir.

Three-Layer Defense

This plugin is designed as the innermost layer of a three-layer grill enforcement system:

Layer Mechanism Bypassable?
1. auto_dispatch.py Returns empty plan for grill-required tasks ✅ Agent can skip it
2. hermes_exec.py Checks token before executing ✅ Agent can use raw exec
3. grill-gate plugin Runtime hook on every tool call ❌ Cannot bypass
安全使用建议
Install only if you want a plugin that can block agent exec or subagent-spawn actions. Review and narrow the trigger words, blocked commands, token directory, and token TTL before relying on it, and do not assume tokens are truly one-use unless the implementation is fixed.
能力评估
Purpose & Capability
The code matches the stated purpose: it registers a before_tool_call hook, checks exec and sessions_spawn events, and blocks configured commands or triggered tasks when no grill token is found.
Instruction Scope
The default trigger words include broad terms such as design, plan, develop, and research, so it may interrupt ordinary subagent tasks unless users tune the configuration.
Install Mechanism
The package has no own install script, and package-lock.json pins the resolved openclaw version, but package.json uses caret dependency ranges so fresh installs may resolve newer compatible dependencies.
Credentials
File access is limited to local configuration and token files; no network calls, credential harvesting, broad local indexing, or unrelated data access were found in the artifact code.
Persistence & Privilege
It creates and uses a persistent token directory and config file under the user/workspace environment, and it deletes expired or malformed token files. The documentation says tokens are one-use, but the implementation only checks expiry and does not consume a valid token.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install grill-gate
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /grill-gate 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Runtime-level grill enforcement for OpenClaw
元数据
Slug grill-gate
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Grill Gate 是什么?

Runtime-level grill enforcement plugin. Blocks exec/spawn calls for research/development tasks unless a valid grill token exists. Ensures agents think before... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 41 次。

如何安装 Grill Gate?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install grill-gate」即可一键安装,无需额外配置。

Grill Gate 是免费的吗?

是的,Grill Gate 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Grill Gate 支持哪些平台?

Grill Gate 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Grill Gate?

由 TangSuann(@tangsuann)开发并维护,当前版本 v1.0.0。

💬 留言讨论