registry / @tea-agent/loop-agent / 0.7.1

@tea-agent/loop-agent@0.7.1

已弃用：此版本可能包含过时内容，请升级到最新版 npm i @tea-agent/loop-agent@latest

`loop-agent` 是面向 AI coding agent 的仓库级任务运行时和治理工具。它把一次研发任务组织成可生成、可校验、可执行、可恢复、可交接的 Agent DAG，并用 `.harness/`、`docs/` 和 shell verification 记录执行事实、长期治理资料和完成依据。

Static Scan Results

scanned 8d ago · by rust-scanner

Static analysis completed at 65.0% confidence. No malicious behavior was detected; 11 low-signal pattern(s) were surfaced and cleared.

Static reason

No blocking static signals were detected.

Decision evidence

public snapshot

Behavioral surface

Source

ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell

Supply chain

HighEntropyStrings

Manifest

NoLicenseWildcardDependency

scanned 268 file(s), 1.37 MB of source

Source & flagged code

2 flagged

bin/loop-agent.jsView file

Lines 1-22javascript

1#!/usr/bin/env node

2import { existsSync } from "node:fs";

3import { dirname, join } from "node:path";

4import { fileURLToPath, pathToFileURL } from "node:url";

6const packageRoot = dirname(dirname(fileURLToPath(import.meta.url)));

7const cliEntry = join(packageRoot, "dist", "cli.js");

9if (!existsSync(cliEntry)) {

10 console.error(

11 `loop-agent: cannot find built CLI at ${cliEntry}. Run \`npm run build\` before using the package bin.`,

12 );

13 process.exit(1);

14}

16try {

17 await import(pathToFileURL(cliEntry).href);

18} catch (error) {

Medium

Dynamic Require

Package source references dynamic require/import behavior.

bin/loop-agent.jsView on unpkg · L16

19 console.error(error instanceof Error ? error.message : String(error));

20 process.exit(1);

21}

skills/systematic-debugging/find-polluter.shView file

•path = skills/systematic-debugging/find-polluter.sh kind = build_helper sizeBytes = 1528 magicHex = [redacted]

Medium

Ships Build Helper

Package ships non-JavaScript build or shell helper files.

skills/systematic-debugging/find-polluter.shView on unpkg

Source & flagged code

2 flagged · loading source

bin/loop-agent.jsView file

Static Scan Results

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code