Skip to main content
Run the installer in a terminal, open your coding agent, then run init in your project. Reticle is a verification layer for AI coding agents: it embeds a dev-only SDK in your running web app so an agent can prove a change works instead of guessing. By the end of this page your agent will click a button in your app and prove what happened: the request that fired, the state that changed, and the file to open if it didn’t.
Every response on this page is real output, captured against a running app while writing it. Nothing here is illustrative.

Prerequisites

  • Node 20 or newer
  • A web app you can run locally, and its dev server
  • A coding agent that speaks MCP (Claude Code, Cursor, Codex, OpenCode, Windsurf, VS Code)

Step 1. Install it on this machine

In a terminal, before you open your coding agent:
This puts reticle on your PATH and registers the MCP server with every coding agent it can reach: Claude Code, Cursor, Windsurf, VS Code, Zed, Gemini CLI, Copilot CLI, OpenCode, Warp, Kiro, Amazon Q, Cline, Amp, Continue and Factory Droid. Nothing is asked. Codex CLI keeps a TOML config that Reticle will not rewrite, so the installer prints the lines to paste and the file to paste them into.
Run this before opening your agent, and there is nothing to restart. A coding agent reads its MCP server list once at startup. Install while it is closed and the tools are simply there when you open it. If it was already open, quit and reopen it once.
Prefer not to pipe a script into a shell? The two commands it runs are:

Step 2. Open your coding agent, and wire the project

The reticle_* tools are already there. In your project directory:
Like npm init or git init, this is the per-project step: it installs the SDK, wires it into your app’s entry point, restarts your dev server and then opens your app to prove a session connected. It is idempotent. Run it twice and the second run reports what was already done rather than doing it again. Step 1 is once per machine. This step is once per project. Prefer to install the skill and let the agent run setup itself? On Claude Code the plugin registers the MCP server and the skill in one step:
On Cursor, Codex, Copilot, Gemini and anything else the skills CLI supports:
Then type /reticle and the agent runs the install from the skill. Useful flags, from reticle init itself:
Start with --dry-run if you want to see the plan before anything is written.
In a monorepo, init will find several apps and ask which one you mean. --app packages/web skips the question.
Prefer to wire it yourself? See Manual install. It is about ten lines, and worth reading once even if you let the agent do it, because it explains what the agent actually changed.

Step 3. Check the setup

doctor diagnoses the whole setup in one command: Chromium, the daemon, the port. If something is wrong this is the page you want before you start debugging your app instead.

Step 4. Start your app and open it

Start your dev server as usual, then:
This reuses the tab you already have open, or opens one if you don’t. The SDK connects to the local daemon over a WebSocket, and your agent can now see the app.
If the browser console says [Reticle] this page could not open a websocket to …, your app and the daemon disagree about the port. Set it explicitly: VITE_RETICLE_WS_URL=ws://localhost:4400/reticle for Vite, or reticle.connect({url}). This is the single most common setup problem, and the console message names the exact address it tried.

Step 5. Look at the page

Ask your agent to take a snapshot. This is what came back from a real app:
Three things to notice. The password is already [REDACTED]. Reticle redacts credential-shaped values before they leave the page, so your agent’s context never holds your test password, let alone your real one. The whole snapshot cost 61 tokens. This is mode: "interactive", which returns only the controls. A full accessibility-tree dump of a comparable page runs to thousands. Reticle is built to ask narrow questions, because the answer gets re-sent to the model on every turn. Each control has a ref like e5. That’s the handle for the next step, and it stays valid until the element leaves the DOM, so you don’t re-snapshot between actions.

Step 6. Act, and prove it

Here is the whole idea of Reticle in one call. Your agent names the expected consequence before it acts:
Stating the expectation up front is the difference between a check and a rationalisation. An agent that clicks first and then decides what counts as success will always find something that counts. The real response, trimmed for length:
A real act_and_wait verdict, annotated. The verdict, the source pointer, the request evidence, the request count, the state diff, and the app's own signal Read what that actually proves:

What “verified” can say

yes

The consequence you named actually happened, and the evidence is attached.

no

It did not happen. This is a finding, with the source pointer to go fix it.

unknown

Reticle drove the app and could not tell. This is not a pass. Report it as unknown.
That third state is the one that matters. Most tools have two outcomes and quietly file “I couldn’t tell” under “fine”. A verification layer that cannot admit uncertainty is just a very confident random number generator.

Frequently asked questions

Two commands, and no restart if you run them in order. The installer registers the MCP server with every agent on the machine, so opening your agent afterwards is all that is needed. Then npx @reticlehq/server init wires the project and restarts your dev server for you. The MCP registration is global, so every later project starts with the tools already there.
No. You talk to your agent in plain language and it calls the tools. There is no spec file, no selector language and no test runner involved in the loop on this page. If you later want the same flow to block a bad merge, you can save it and run it in CI, but that is a separate step.
No. The SDK is dev-only. The Vite plugin declares apply: 'serve', so it is dropped from vite build entirely, and connect() self-disables when the build reports NODE_ENV=production. The recommended wiring also guards the call behind import.meta.env.DEV, so there are two independent locks.
No. The daemon runs on your machine and the SDK runs in your browser. No application code, DOM, network traffic or console output leaves it. Anonymous product analytics are sent unless you opt out with npx @reticlehq/server telemetry disable, and they never include your code or your app’s data.
The core is framework-neutral, so DOM, network, console, routing and source mapping work anywhere JavaScript runs. What varies is how connect() gets into your app and whether you get component identity on top. See Frameworks for the exact wiring per stack and an honest table of what is gated in CI versus wired but unverified.
Run npx @reticlehq/server doctor. If it shows the daemon running but sessions at zero, your app is not reaching the bridge, and the usual cause is a port mismatch. The bridge port is not your dev-server port. See Troubleshooting.

Where to go next

Instrument your app

Emit signals like auth:granted so your verdicts get stronger than “the DOM changed”.

Every tool

The 18 tools your agent sees by default, and the 30 more it can reach on demand.

Run it in CI

Turn this session into a suite that blocks a bad merge.

Why Reticle

The false-green problem, and the measured case that this fixes it.
Last modified on September 18, 2026