OpenDia connects web browsers such as Chrome, Arc, and Firefox to AI models. It is for people who want to use AI models through their browser, with automation and MCP support.
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 skills add aeonfun/opendia --skill opendia-harnessgit clone --depth 1 https://github.com/aeonfun/opendiaWrote 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/aeonfun/opendia/opendia-harness)<a href="https://agentmods.dev/skills/aeonfun/opendia/opendia-harness"><img src="https://agentmods.dev/badge/skills/aeonfun/opendia/opendia-harness/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/aeonfun/opendia/opendia-harness"><img src="https://agentmods.dev/badge/skills/aeonfun/opendia/opendia-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 39 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 49 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 64 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 66 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00052 | $0.00725 |
| Opus 5 | $0.00026 | $0.00362 |
| Sonnet 5 | $0.00010 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
opendia-harness 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 10d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenDia harness setup (Grok Build)
Install plugin
grok plugin marketplace add aeonfun/opendia
grok plugin install opendia --trust
Or pin a path:
grok plugin install aeonfun/opendia#plugins/opendia --trust
Enable the plugin (/plugins or [plugins].enabled). Trust is required for the MCP server to attach.
Manual config.toml
[mcp_servers.opendia]
command = "npx"
args = ["-y", "opendia"]
enabled = true
startup_timeout_sec = 60
Optional custom ports (must match what the extension expects):
npx opendia --ws-port=5555 --http-port=5556
Default: WebSocket 5555 (extension), HTTP/SSE 5556, stdio for the AI client.
Extension checklist
- Install from GitHub Releases (Chrome zip or Firefox zip).
- Load unpacked / temporary add-on as documented in the main README.
- Open the extension popup — must show Connected to
ws://localhost:5555(or your chosen WS port). - If disconnected: start or restart
npx opendia, then reload the extension.
Doctor commands (Grok Build)
grok mcp list
grok mcp doctor opendia
grok plugin details opendia
Common failures
| Symptom | Likely cause | Fix |
|---|---|---|
| MCP tools timeout | Extension not connected | Connect extension; confirm WS port |
| Tools present but actions no-op | Stale socket / server restart | Restart npx opendia, reload extension |
| Cold schemas only | Extension not registered yet | Wait for connect + tools/list_changed, re-list |
| Port conflict | Another process on 5555/5556 | npx opendia --port=6000 and point extension at new WS |
npx slow / fails startup |
Cold npm download | Raise startup_timeout_sec; ensure network for first install |
| Tunnel 401 | Missing bearer token | Pass Authorization: Bearer <token> (printed at startup) |
Modes
- Local (default) — stdio + loopback WS/SSE. Correct for Grok Build, Claude Code, Cursor.
--tunnel— ngrok public URL for ChatGPT-style remote connectors. Requires token. Not the default for local harnesses.--http-host=0.0.0.0— LAN bind; also requires token. Avoid unless intentional.
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.
- 10d ago First seen · 84 lines · 52 tokens per session scan A 94e3f2208c9d
opendia-harness is a skill published in the GitHub repository aeonfun/opendia (1,920 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 725 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
fsb
FSB drives the user's Chrome via the FSB extension and an MCP bridge for live web tasks.
huly-cli
Operate Huly through the @firfi/huly-cli executable. Use when a coding agent needs to authenticate, switch Huly workspaces or projects, discover commands, query structured Huly data, or perform confirmed Huly mutations from a shell or automation workflow.
censor_message
Automatically censor profanity in messages by replacing with asterisks.
content_guard
Proactive content moderation guard for all incoming messages.
profanity_check
Check messages for profanity and inappropriate content in 24 languages.
pixi-vn-getting-started
Use when setting up a new or existing project on @drincs/pixi-vn, wiring the main.ts entry point, or calling the top-level Game API (Game.init, Game.start, Game.onEnd, Game.addOnError, Game.onNavigate, Game.clear) — this is the entry point every Pixi'VN project needs before touching canvas, narration, sound, storage…