New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Gateguard

by affaan-m in affaan-m/ECC

强制事实的门控，阻止编辑/写入/Bash（包括MultiEdit），并要求在允许操作之前进行具体调查（导入器、数据模式、用户指令）。与无门控代理相比，可测量地将输出质量提高2.25分。

MITAuto-check passedDevelopment

Install Gateguard

skills CLI
$ npx skills add affaan-m/ECC --skill gateguard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install affaan-m/ECC gateguard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/zh-CN/skills/gateguard .claude/skills/gateguard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gateguard
GitHub stars
276k
Token cost
~583 tokens
SKILL.md length
124 words
Files
1
Skills in repo
683
Repo updated
First seen
Licence
MIT

At a glance

强制事实的门控，阻止编辑/写入/Bash（包括MultiEdit），并要求在允许操作之前进行具体调查（导入器、数据模式、用户指令）。与无门控代理相比，可测量地将输出质量提高2.25分。

  • Development work in your project
  • SKILL.md covers 何时激活, 核心概念, 证据 and 门控类型, plus 4 more sections
  • Calls git and pip

What it does

Gateguard is an agent skill from affaan-m/ECC. 强制事实的门控，阻止编辑/写入/Bash（包括MultiEdit），并要求在允许操作之前进行具体调查（导入器、数据模式、用户指令）。与无门控代理相比，可测量地将输出质量提高2.25分。

Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. It works with Bash and Git. The repository describes itself as: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/gateguard”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 4eb71d9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gateguard loads about 583 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 124 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~583

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from affaan-m/ECC at commit 4eb71d9, republished under its MIT licence (© affaan-m). 124 words, ~583 tokens.

Download SKILL.mdSave it as .claude/skills/gateguard/SKILL.md (or your agent's skills folder).
name
gateguard
description
强制事实的门控，阻止编辑/写入/Bash（包括MultiEdit），并要求在允许操作之前进行具体调查（导入器、数据模式、用户指令）。与无门控代理相比，可测量地将输出质量提高2.25分。
origin
community

GateGuard — 事实驱动的前置操作门控

一个 PreToolUse 钩子，强制 Claude 在编辑前进行调查。不同于自我评估（"你确定吗？"），它要求具体的事实。调查行为本身创造了自我评估永远无法带来的认知。

何时激活

  • 处理任何文件编辑会影响多个模块的代码库时
  • 项目包含具有特定模式或日期格式的数据文件时
  • 团队要求 AI 生成的代码必须匹配现有模式时
  • 任何 Claude 倾向于猜测而非调查的工作流程中

核心概念

LLM 的自我评估不起作用。问"你是否违反了任何策略？"答案永远是"没有"。这已通过实验验证。

但问"列出所有导入此模块的文件"会迫使 LLM 运行 Grep 和 Read。调查本身创造了改变输出的上下文。

三阶段门控：

1. DENY  — 阻止首次编辑/写入/Bash 尝试
2. FORCE — 明确告知模型需要收集哪些事实
3. ALLOW — 在事实呈现后允许重试

没有竞争对手能同时做到这三步。大多数止步于拒绝。

证据

两个独立的 A/B 测试，相同的代理，相同的任务：

任务有门控无门控差距
分析模块8.0/106.5/10+1.5
Webhook 验证器10.0/107.0/10+3.0
平均9.06.75+2.25

两个代理生成的代码都能运行并通过测试。区别在于设计深度。

门控类型

编辑/多编辑门控（每个文件的首次编辑）

多编辑的处理方式相同——批次中的每个文件都单独进行门控。

在编辑 {file_path} 之前，请先呈现以下事实：

1. 列出所有导入/引用此文件的文件（在代码树中搜索——Glob/Grep，或通过 Bash 用 find/grep）
2. 列出受此更改影响的公共函数/类
3. 如果此文件读取/写入数据文件，请显示字段名称、结构以及日期格式（使用脱敏或合成值，而非原始生产数据）
4. 逐字引用用户当前的指令
写入门控（首次创建新文件）
在创建 {file_path} 之前，请先说明以下事实：

1. 命名将调用此新文件的文件及行号
2. 确认没有现有文件具有相同功能（在代码树中搜索——Glob/Grep，或通过 Bash 用 find/grep）
3. 如果此文件读取/写入数据文件，请展示字段名称、结构及日期格式（使用脱敏或合成值，而非原始生产数据）
4. 逐字引用用户当前的指令
破坏性 Bash 门控（每个破坏性命令）

触发条件：rm -rf、git reset --hard、git push --force、drop table 等。

1. 列出此命令将修改或删除的所有文件/数据
2. 编写一行回滚步骤
3. 逐字引用用户当前的指令
常规 Bash 门控（每个会话一次）
1. 当前用户请求的一句话概括
2. 此特定命令验证或生成的内容

快速开始

选项 A：使用 ECC 钩子（零安装）

scripts/hooks/gateguard-fact-force.js 处的钩子已包含在此插件中。通过 hooks.json 启用它。

如果 GateGuard 阻止了设置或修复工作，请使用 ECC_GATEGUARD=off 启动会话。如需钩子级别的控制，请继续使用 ECC_DISABLED_HOOKS 配合 GateGuard 钩子 ID。

选项 B：带配置的完整包
bash
pip install gateguard-ai
gateguard init

这会添加 .gateguard.yml 用于按项目配置（自定义消息、忽略路径、门控开关）。

反模式

  • 不要使用自我评估替代。 "你确定吗？"总是得到"确定。"这已通过实验验证。
  • 不要跳过数据模式检查。 两个 A/B 测试代理都假设了 ISO-8601 日期，而实际数据使用的是 %Y/%m/%d %H:%M。检查数据结构（使用脱敏值）可以防止这类错误。
  • 不要对每个 Bash 命令都进行门控。 常规 bash 门控每个会话一次。破坏性 bash 门控每次执行。这种平衡避免了速度下降，同时捕获了真正的风险。

最佳实践

  • 让门控自然触发。不要试图预先回答门控问题——调查本身才是提高质量的关键。
  • 为你的领域自定义门控消息。如果你的项目有特定约定，请将其添加到门控提示中。
  • 使用 .gateguard.yml 忽略 .venv/、node_modules/、.git/ 等路径。

相关技能

  • safety-guard — 运行时安全检查（互补，不重叠）
  • code-reviewer — 编辑后审查（GateGuard 是编辑前调查）

© affaan-m, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in docs/zh-CN/skills/gateguard of affaan-m/ECC.

Open the folder on GitHubat commit 4eb71d9

Compare with similar skills

Gateguard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gateguard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gateguard this skillaffaan-m/ECC276k—~583Automated safety check: PassMIT
Dirextalk DeployerYingSuiAI/dirextalk-deployer457—~7.2kAutomated safety check: PassMIT
Cursor Composer Task DelegateChachamaru127/claude-code-harness3.2k—~4.4kAutomated safety check: NotesMIT
Gridbash Panesjasonsuhari/gridbash134—~1.5kAutomated safety check: PassMIT
Niubashunixwin/niubash163—~2.1kAutomated safety check: PassMIT
Dirextalk DeployerYingSuiAI/dirextalk-deployer457—~541Automated safety check: PassMIT

Similar skills

  • Dirextalk Deployer

    YingSuiAI/dirextalk-deployer

    Deploy, resume, verify, update, recover, reset, or destroy production Dirextalk services and nodes on AWS, and wire local agent runtimes.

    457 GitHub stars~7.2k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Cursor Composer Task Delegate

    Chachamaru127/claude-code-harness

    Hands one implementation task to Cursor Composer in an isolated git worktree, then reviews its diff and cherry-picks the result into the main branch.

    3.2k GitHub stars~4.4k tokensUpdated 6 days ago
    DevelopmentAuto-check: notes

  • Gridbash Panes

    jasonsuhari/gridbash

    Coordinate with sibling agent panes from inside a GridBash grid — list panes and their roles, read what a pane is currently doing, prompt one pane or every other pane, and rename pane titles so the…

    134 GitHub stars~1.5k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Niubash

    unixwin/niubash

    Run Windows tasks in Niubash, the GNU Bash-compatible Windows-native shell.

    163 GitHub stars~2.1k tokensUpdated today
    DevelopmentAuto-check passed

  • Dirextalk Deployer

    YingSuiAI/dirextalk-deployer

    Deploy, resume, verify, update, recover, reset, or destroy production Dirextalk services and nodes on AWS.

    457 GitHub stars~541 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Conventional Commit

    JanDeDobbeleer/oh-my-posh

    Rules for writing Conventional Commits messages in this project.

    24k GitHub stars~281 tokensUpdated yesterday
    DevelopmentAuto-check passed

More from affaan-m/ECC

All 682 skills in this repo

  • Skill Stocktake

    affaan-m/ECC

    Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.

    277k GitHub starsUsed in 5 repos~3.1k tokens
    Auto-check passed

  • VideoDB Video Search and Editing

    affaan-m/ECC

    Ingests, indexes, searches, edits and monitors video, audio and live streams through the VideoDB Python SDK, returning stream links, clips and timestamps.

    277k GitHub starsUsed in 3 repos~3.5k tokens
    Auto-check: notes

  • Docs Governance

    affaan-m/ECC

    Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references.

    277k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    277k GitHub starsUsed in 2 repos~2.3k tokens
    Auto-check passed

  • Master Agreement Generator

    affaan-m/ECC

    Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.

    277k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Frontend Design Direction

    affaan-m/ECC

    Set an ECC-specific frontend design direction for production UI work.

    277k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Works with

Categories

Questions about Gateguard

What does Gateguard do?

强制事实的门控，阻止编辑/写入/Bash（包括MultiEdit），并要求在允许操作之前进行具体调查（导入器、数据模式、用户指令）。与无门控代理相比，可测量地将输出质量提高2.25分。. Gateguard is an agent skill from affaan-m/ECC.

When should I use Gateguard?

Gateguard fits situations like: development work in your project.

How do I install Gateguard in Claude Code?

Run `npx skills add affaan-m/ECC --skill gateguard -a claude-code`. Or copy the skill folder (docs/zh-CN/skills/gateguard in affaan-m/ECC) into .claude/skills/gateguard in your project. Claude Code loads it when a task matches its description.

How do I install Gateguard in Codex?

Run `npx skills add affaan-m/ECC --skill gateguard -a codex`. Or copy the skill folder (docs/zh-CN/skills/gateguard in affaan-m/ECC) into .agents/skills/gateguard in your project. Codex loads it when a task matches its description.

Can I use Gateguard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add affaan-m/ECC --skill gateguard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gateguard, .gemini/skills/gateguard, .github/skills/gateguard and .opencode/skills/gateguard in your project.

What does Gateguard need to run?

Going by SKILL.md and its folder, Gateguard needs the command-line tools its instructions call (git and pip). Our summary lists: Python 3.

Does Gateguard access the network?

SKILL.md contains no URLs. Its commands use git and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Gateguard safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gateguard use?

Gateguard is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gateguard use?

About 583 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gateguard?

Skills that share tags, products or a category with Gateguard: Dirextalk Deployer (YingSuiAI/dirextalk-deployer, 457 stars), Cursor Composer Task Delegate (Chachamaru127/claude-code-harness, 3.2k stars), Gridbash Panes (jasonsuhari/gridbash, 134 stars) and Niubash (unixwin/niubash, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gateguard?

affaan-m (a GitHub user) maintains it in affaan-m/ECC, which has 276,111 GitHub stars. The repository holds 683 skills in this directory. The repository was last updated on October 10, 2026.

Source: affaan-m/ECC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.