observe

A command for opening the rn-dev-agent observability web interface, which shows activity from the development session. It can also stop or restart that interface.

In plain words
What is it for?
Use it to check whether the interface is running, start or restart it, open its URL, or stop it for the session.
Why use it?
It gives developers a place to watch tool calls, see a live device view, and inspect app state while work is happening.

Command

Install

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.

agentmods
npx agentmods add commands/lykhoyda/rn-dev-agent/observe
Clone the repo
git clone --depth 1 https://github.com/Lykhoyda/rn-dev-agent
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00302
Opus 5 $0.00010 $0.00151
Sonnet 5 $0.00004 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 2d ago against content hash a4ff5cd5f894, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

observe 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 2d 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.

packages/claude-plugin/commands/observe.md · 22 lines

What it actually says

The observe web UI autostarts when the session begins in an RN project. Permanent opt-out: .rn-agent/config.json{ "observe": { "autoStart": false } } (port via observe.port, default 7333; env RN_AGENT_OBSERVE_AUTOSTART / RN_AGENT_OBSERVE_PORT override config).

The user's argument: "$ARGUMENTS"

  • If the argument is empty: call the observe MCP tool with action: "status". If running, print the returned url prominently and tell the user to open it in a browser to watch the live tool-call timeline, live device mirror, and app state. If NOT running (autostart disabled or previously stopped), call action: "start" — an explicit /observe is an explicit request to see the UI — and print the URL.
  • If the argument is stop: call with action: "stop". The UI stays down for the rest of the session; mention the config opt-out if the user wants it permanent.
  • If the argument is restart: call with action: "restart" and print the (possibly new) URL. The event timeline is preserved across restarts.
Changes

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.

  1. 2d ago First seen · 22 lines · 21 tokens per session scan A a4ff5cd5f894

Subscribe to this mod's changes

observe is a command published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 302 once invoked, about $0.0001 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.