reticlehq/reticle

audit-my-app

Sweep a whole running web app for what is broken, without writing a script or knowing the codebase.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/reticlehq/reticle --skill audit-my-app

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

Sweep the whole app and report what is broken

You do not need to understand the codebase to check it. Reticle drives every reachable control in the running app and reports the anomalies. Not installed? RETICLE_INSTALL_SOURCE=npx_skill npx @reticlehq/server@latest init, then the `install-and-verify` skill.

1. Ask the app what it can do

reticle_run({ tool: "reticle_capabilities", args: { sessionId } })

About 1 KB, and it is the app describing its own testable surface: every registered testid, every domain signal, the stores, and the saved flows with their steps. That beats snapshotting the DOM and inferring intent from element names, and it is the cheapest orientation available.

2. Click everything

reticle_run({ tool: "reticle_verify", sessionId, args: { action: "crawl", maxSteps: 25 } })
json
{
  "interactiveFound": 3,
  "stepsRun": 3,
  "anomalies": [],
  "counts": { "consoleErrors": 0, "failedRequests": 0, "deadControls": 0, "contradictions": 0 },
  "visited": ["- textbox \"Email\"", "- button \"Sign in\""],
  "truncated": false
}

`deadControls` and `contradictions` are the two counts that mean a real problem. Console errors and failed requests are worth reading but a busy app produces both innocently. A dead control is a button wired to nothing; a contradiction is a channel disagreeing with what the screen showed.

It clicks everything, so point it at a dev environment. maxSteps bounds it and defaults to 25. Want a non-destructive pass first: what is reachable, without touching it? reticle_run({ tool: "reticle_explore", sessionId }).

Do not hand-roll this sweep. The obvious version (click each control, assert no console error) passes on exactly the bug you are sweeping for, because a dead button throws nothing.

3. Compare what the API said against what rendered

reticle_run({ tool: "reticle_reconcile", sessionId })

The API returned ten rows, the table shows nine, nothing errored. Neither the network log nor the DOM is wrong on its own. Only the comparison catches it, and nothing else you can run makes that comparison.

4. Find the parts nobody exercised

reticle_run({ tool: "reticle_verify", sessionId, args: { action: "coverage" } })   // { total, exercised, untouched }

And if the project already has saved flows, ask whether they prove anything:

reticle_run({ tool: "reticle_domain", sessionId })
// → { flowCount, coverage: { asserted, presenceOnly, assertionFree }, gaps: { declaredUntestedSignals, … } }

A suite of forty flows where thirty-one assert nothing is a suite that will stay green through any regression. That number is usually the most alarming thing in the whole audit, and nothing else reports it.

5. Report

Lead with the counts, then one line per real finding with its file:line from reticle_look { action: "element" }. Separate:

  • Broken: dead controls, contradictions, failed requests, errors thrown during the sweep.
  • Unverified: untouched controls and assertionFree flows. Not known to be broken; known to be unchecked.
  • Pre-existing: console errors that were already there before the sweep started. Say so, so nobody attributes them to today's change.

Do not report a clean audit over a partial one. If truncated is true or maxSteps cut the sweep short, say what was not reached. A silent cap reads as "everything is fine" when it means "I stopped".


Full capability reference: curl https://docs.reticle.sh/capabilities.md. Everything else: curl https://docs.reticle.sh/llms.txt.

按任务相关推荐

来自同一仓库

更多 Skills

全部 Skills
reticlehq
社区

reticle

Install, instrument and verify this running web app from the inside (DOM, network, routing, console and framework state) instead of screenshots or guessing. Drives one real flow end to end and returns a verdict with the file:line to fix. Use when the user asks to set up or install Reticle, when a user-facing change needs proving before you call it done, when a test passes but the UI is broken, or when the user types /reticle.

1小时安装量
1
GitHub Stars
1285
最近更新
10月30日
reticlehq
社区

debug-broken-ui

Find out why something in a running web app does not work, when the console is empty and the code looks correct. Reads the click, the request, the store and the console together and returns the file:line to open. Use when a button does nothing, a form will not submit, data will not load, a page renders blank or stale, a modal will not close, or the user says "it's broken" and the code review says it is fine.

1小时安装量
1
GitHub Stars
900
最近更新
9月26日
reticlehq
社区

fix-what-i-pointed-at

Pick up the bugs a human flagged by pointing at them in the running app, each arriving with the element, the note they typed, and the source file and line. Use when the user says they marked or flagged something, when starting a session on an app someone has been clicking through, when a designer or PM has left feedback in the UI, or when the user describes a problem as "that button there" without saying which file.

1小时安装量
1
GitHub Stars
900
最近更新
9月26日
reticlehq
社区

replay-user-flows

Turn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model in the loop and no test code to write. Use when you have driven the same flow twice, when the user wants regression coverage without a Playwright suite, when a refactor needs proving against every existing journey, or when re-verifying by hand is costing a full drive every time.

1小时安装量
1
GitHub Stars
900
最近更新
9月26日