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.
npx agentmods add skills/liuqihonggit/mcp-cli-bridge/file-access-controlnpx skills add liuqihonggit/mcp-cli-bridge --skill file-access-controlgit clone --depth 1 https://github.com/liuqihonggit/mcp-cli-bridgeWrote 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.
[](https://agentmods.dev/skills/liuqihonggit/mcp-cli-bridge/file-access-control)<a href="https://agentmods.dev/skills/liuqihonggit/mcp-cli-bridge/file-access-control"><img src="https://agentmods.dev/badge/skills/liuqihonggit/mcp-cli-bridge/file-access-control.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.02819 |
| Opus 5 | $0.00023 | $0.01409 |
| Sonnet 5 | $0.00009 | $0.00564 |
| Haiku 4.5 | $0.00005 | $0.00282 |
Grade A, and why
file-access-control 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Access Control
This skill enforces mandatory file locking before any file access operations to prevent race conditions and ensure data integrity.
Workflow
访问文件前
↓
检查 .csx 锁脚本是否存在?
↓ 否
创建锁脚本 (子智能体)
↓
调用 .csx 脚本获取文件锁
↓
5秒内获取成功?
↓ 否 ↓ 是
委派子智能体做其他事情 执行文件操作
↓
释放锁
命名规范
锁脚本名称
| 常量 | 值 | 说明 |
|---|---|---|
LockScript.FileName |
FileAccessGuard.csx |
文件访问守卫脚本 |
LockScript.Directory |
.trae/skills/file-access-control/ |
脚本存放目录 |
Rules
1. 锁脚本检查与创建
访问任何文件前,必须先检查锁脚本是否存在:
// 使用 nameof 和 typeof 避免硬编码
public static class LockScript
{
public const string FileName = nameof(FileAccessGuard) + ".csx";
public const string Directory = ".trae/skills/file-access-control/";
public static readonly string FullPath = Path.Combine(Directory, FileName);
}
// 检查脚本是否存在
if (!File.Exists(LockScript.FullPath))
{
// 委派子智能体创建锁脚本 FileAccessGuard.csx
// 不要自己创建,让子智能体来做
}
2. 调用锁脚本获取锁
# 使用 dotnet-script 运行 .csx 脚本
dotnet script .trae\skills\file-access-control\FileAccessGuard.csx -- "C:\path\to\file.txt" acquire
3. 锁脚本标准接口
锁脚本必须支持以下命令:
| 命令 | 功能 | 返回值 |
|---|---|---|
acquire <filepath> |
获取文件锁 | SUCCESS / TIMEOUT / ERROR |
release <filepath> |
释放文件锁 | SUCCESS / ERROR |
status <filepath> |
检查锁状态 | LOCKED:<pid> / FREE / EXPIRED |
锁脚本实现 (FileAccessGuard.csx)
#!/usr/bin/env dotnet-script
#r "System.IO.FileSystem"
using System;
using System.IO;
using System.Threading;
using System.Threading.Tasks;
// 配置
const int ACQUISITION_TIMEOUT_SECONDS = 5; // 5秒抢不到就放弃
const int LOCK_EXPIRY_SECONDS = 30; // 锁30秒自动过期
const int RETRY_INTERVAL_MS = 100; // 重试间隔100毫秒
// 命令行参数解析
if (Args.Count < 2)
{
Console.WriteLine("ERROR: Usage: dotnet script FileLock.csx -- <command> <filepath>");
Console.WriteLine("Commands: acquire, release, status");
Environment.Exit(1);
}
string command = Args[0].ToLower();
string targetFilePath = Args[1];
string lockFilePath = $"{targetFilePath}.scx.lock";
switch (command)
{
case "acquire":
Environment.Exit(await AcquireLockAsync() ? 0 : 1);
break;
case "release":
Environment.Exit(ReleaseLock() ? 0 : 1);
break;
case "status":
Console.WriteLine(GetLockStatus());
Environment.Exit(0);
break;
default:
Console.WriteLine($"ERROR: Unknown command '{command}'");
Environment.Exit(1);
break;
}
// 获取锁
async Task<bool> AcquireLockAsync()
{
var startTime = DateTime.UtcNow;
while ((DateTime.UtcNow - startTime).TotalSeconds < ACQUISITION_TIMEOUT_SECONDS)
{
// 清理过期锁
await TryRemoveExpiredLockAsync();
try
{
// 尝试独占创建锁文件
using var fs = new FileStream(
lockFilePath,
FileMode.CreateNew,
FileAccess.Write,
FileShare.None,
bufferSize: 4096,
useAsync: true);
using var writer = new StreamWriter(fs);
await writer.WriteLineAsync($"PID:{Environment.ProcessId}");
await writer.WriteLineAsync($"Time:{DateTime.UtcNow:yyyy-MM-dd HH:mm:ss}");
await writer.WriteLineAsync($"ExpirySeconds:{LOCK_EXPIRY_SECONDS}");
await writer.FlushAsync();
Console.WriteLine("SUCCESS");
return true;
}
catch (IOException)
{
// 锁被占用,等待重试
await Task.Delay(RETRY_INTERVAL_MS);
}
}
// 5秒超时
Console.WriteLine("TIMEOUT");
return false;
}
// 释放锁
bool ReleaseLock()
{
try
{
if (File.Exists(lockFilePath))
{
File.Delete(lockFilePath);
Console.WriteLine("SUCCESS");
return true;
}
Console.WriteLine("SUCCESS: Lock not found");
return true;
}
catch (Exception ex)
{
Console.WriteLine($"ERROR: {ex.Message}");
return false;
}
}
// 获取锁状态
string GetLockStatus()
{
if (!File.Exists(lockFilePath))
return "FREE";
try
{
var lines = File.ReadAllLines(lockFilePath);
DateTime? lockTime = null;
double expirySeconds = LOCK_EXPIRY_SECONDS;
string? pid = null;
foreach (var line in lines)
{
if (line.StartsWith("PID:"))
pid = line[4..].Trim();
if (line.StartsWith("Time:") && DateTime.TryParse(line[5..].Trim(), out var lt))
lockTime = lt.ToUniversalTime();
if (line.StartsWith("ExpirySeconds:") && double.TryParse(line[14..].Trim(), out var exp))
expirySeconds = exp;
}
// 检查是否过期
if (lockTime.HasValue && (DateTime.UtcNow - lockTime.Value).TotalSeconds > expirySeconds)
return "EXPIRED";
return pid != null ? $"LOCKED:{pid}" : "LOCKED:UNKNOWN";
}
catch
{
return "ERROR";
}
}
// 清理过期锁
async Task TryRemoveExpiredLockAsync()
{
if (!File.Exists(lockFilePath))
return;
try
{
var lines = await File.ReadAllLinesAsync(lockFilePath);
DateTime? lockTime = null;
double expirySeconds = LOCK_EXPIRY_SECONDS;
foreach (var line in lines)
{
if (line.StartsWith("Time:") && DateTime.TryParse(line[5..].Trim(), out var lt))
lockTime = lt.ToUniversalTime();
if (line.StartsWith("ExpirySeconds:") && double.TryParse(line[14..].Trim(), out var exp))
expirySeconds = exp;
}
if (lockTime.HasValue && (DateTime.UtcNow - lockTime.Value).TotalSeconds > expirySeconds)
{
File.Delete(lockFilePath);
}
}
catch { /* 忽略清理错误 */ }
}
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.
- 4d ago First seen · 411 lines · 45 tokens per session scan A 1685195d261b
file-access-control is a skill published in the GitHub repository liuqihonggit/mcp-cli-bridge (0 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 2,819 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…