AIRI is a self-hosted virtual AI companion that gives an AI character a voice, visual presence, memory, and the ability to interact with games and coding activity. People use it as a personal digital companion on the web, macOS, or Windows, including for voice chat and gameplay. The catalogue add-ons provide workflows for working with the AIRI project.
Borrowing it
Nothing to install: this file belongs to moeru-ai/airi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/moeru-ai/airi/main/.agents/skills/agent-browser-electron/SKILL.mdgit clone --depth 1 https://github.com/moeru-ai/airiWrote 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/moeru-ai/airi/agent-browser-electron)<a href="https://agentmods.dev/skills/moeru-ai/airi/agent-browser-electron"><img src="https://agentmods.dev/badge/skills/moeru-ai/airi/agent-browser-electron/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/moeru-ai/airi/agent-browser-electron"><img src="https://agentmods.dev/badge/skills/moeru-ai/airi/agent-browser-electron.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00095 | $0.02868 |
| Opus 5.5 | $0.00038 | $0.01147 |
| Sonnet 5.5 | $0.00019 | $0.00574 |
| Haiku 4.5 | $0.00010 | $0.00287 |
Grade A, and why
agent-browser-electron scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use `curl http://127.0.0.1:<port>/json/list` first whenever correct target selection matters. Treat `agent-browser` as the interaction client after target discovery, not as the only discovery source. How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Browser Electron
Overview
Inspect Electron renderer windows reliably when agent-browser alone is not enough to tell which CDP target maps to which visible app window.
Prefer raw CDP target discovery over guessing from tab list, then use agent-browser --cdp <port> tab stable tab IDs to interact with the renderer target you want.
Preserve Window Roles
Before navigation, identify each relevant window's business role and the action that opens it. Inspect the app's window factories and open handlers when the role is unclear. Correlate those roles with CDP targets before interaction.
A renderer route does not define the complete window. Window creation also establishes mouse handling, focus, transparency, IPC handlers, and lifecycle behavior. Loading another route does not transfer those responsibilities.
- Keep the main stage in its main window. Do not replace it with settings or chat through
open,goto,location.hash, router calls, orloadURL. - Open the target window through the app UI. For diagnostic access, use its existing Electron open handler when UI access fails. Report that distinction in the results.
- Enumerate CDP targets again after the window opens. Attach to that window, then navigate within its business role.
- If clicks fail, inspect the target window and its mouse or focus behavior. Do not bypass the failure through navigation in another window.
- After the interaction, verify that the main stage remains intact and that the target window accepts input. Programmatic activation alone does not prove that user clicks work.
Why Raw CDP Discovery
Use raw CDP target discovery because agent-browser is operating as a convenience layer on top of Chrome DevTools Protocol, and that layer can hide or flatten details that matter in Electron.
Raw /json/list is the source of truth for CDP target discovery because it exposes Chromium's target inventory without extra interpretation. It is not the same thing as Electron's BrowserWindow.getAllWindows().
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago Changed 263535e97416
- 1mo ago Changed · +16 lines d01c3bac6015
- 1mo ago First seen · 226 lines · 95 tokens per session scan A 14d6a0028a31
agent-browser-electron is a skill published in the GitHub repository moeru-ai/airi (50,636 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 2,868 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.