agentmods.dev

rn-metro-console

rn-metro-console is a skill for Claude Code from AndrewDongminYoo/rn-agents-kit. It costs 72 tokens per session (1,744 once invoked), scanned A, original, Apache-2.0.

A read-only tool for collecting console output from a running React Native app through Metro, the development server commonly used to bundle and run React Native code. It reads log, warning, and error messages without opening the visual developer tools.

In plain words
What is it for?
Watching React Native console logs, confirming that a log message appeared, checking warnings and errors, and verifying runtime behavior while Metro and the app are running.
Why use it?
It provides a bounded way to check what the app reported while it was running. This helps verify that code executed and investigate runtime warnings or errors without sorting through unrelated system logs.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the rn-agents-kit plugin — 10 skills shipped together

not rated 3repo changed 1mo ago A scan 72 tokens original Apache-2.0

Good fit Watching React Native console logs, confirming that a log message appeared, checking warnings and errors, and verifying runtime behavior while Metro and the app are running.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andrewdongminyoo/rn-agents-kit/rn-metro-console
View source ↗ AndrewDongminYoo/rn-agents-kit rn-toolkits.donminzzi.kr
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.

Any agent
npx skills add AndrewDongminYoo/rn-agents-kit --skill rn-metro-console
Clone the repo
git clone --depth 1 https://github.com/AndrewDongminYoo/rn-agents-kit

Made for: Claude Code.

Or install rn-agents-kit, the plugin that ships this one along with the rest of its 10 skills.

Wrote 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.

agentmods badge for rn-metro-console

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrewdongminyoo/rn-agents-kit/rn-metro-console/github.svg)](https://agentmods.dev/skills/andrewdongminyoo/rn-agents-kit/rn-metro-console)
Your own site
<a href="https://agentmods.dev/skills/andrewdongminyoo/rn-agents-kit/rn-metro-console"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/rn-agents-kit/rn-metro-console/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.

agentmods 80×15 button for rn-metro-console

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrewdongminyoo/rn-agents-kit/rn-metro-console"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/rn-agents-kit/rn-metro-console.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,744 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00072 $0.01744
Opus 5.5 $0.00029 $0.00698
Sonnet 5.5 $0.00014 $0.00349
Haiku 4.5 $0.00007 $0.00174

Measured 1mo ago against content hash 4f985a5a8e9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rn-metro-console 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 1mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (rn-console.mjs, rn-console.test.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/rn-metro-console/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RN Metro Console — Read App Logs via Metro's CDP

Overview

Runs the bundled rn-console.mjs to collect a running RN app's console.log/info/warn/error output from Metro's Chrome DevTools Protocol (CDP) endpoint, and prints it for the agent to read. It is bounded by default — it collects for a short window (or up to N logs) and then exits — so it never blocks the agent. This is the log half of the verification loop; pair it with rn-device-capture (the screen) to confirm a change behaved at runtime. It is read-only with respect to your source — it writes nothing, only prints.

When to Use

  • "watch the logs", "tail the console", "did this console.log fire?"
  • Verifying a fix by observing runtime behavior, without the DevTools GUI
  • adb logcat is unavailable (iOS) or too noisy

Prerequisites / Setup

  • Metro running (npm start / npx react-native start) on localhost:8081, with the app open and attached to Metro so a CDP target exists.
  • Run the helper from the project root so it can prefer the project's ws package and send Metro's required Origin header.
  • Node ≥ 22 provides a built-in fallback when ws is unavailable, but that fallback cannot send Origin and may be rejected by a physical-device inspector target.

Quick Steps (read-only on source)

1 — Locate the helper

rn-console.mjs ships inside this skill's own directory, not in the user's project. After install (marketplace plugin or a project .claude/skills/) the working directory is the user's RN app, where a path like skills/rn-metro-console/rn-console.mjs does not exist. When this skill is active you are given its absolute base directory; resolve the helper from that path:

SKILL_DIR="<this skill's base directory>"   # the absolute path provided when this skill loaded

2 — Capture (bounded)

Run from the user's project root so ws resolves when the project provides it, invoking the helper by its installed path:

node "$SKILL_DIR/rn-console.mjs"                       # collect ~10s, all levels
node "$SKILL_DIR/rn-console.mjs" --duration 5          # collect 5s then exit
node "$SKILL_DIR/rn-console.mjs" --max 30              # stop after 30 logs
node "$SKILL_DIR/rn-console.mjs" --level error         # errors only
node "$SKILL_DIR/rn-console.mjs" --filter "Login"      # substring filter
node "$SKILL_DIR/rn-console.mjs" --device "com.example.app" --preflight  # print the selected target as JSON
node "$SKILL_DIR/rn-console.mjs" --device "iPhone 16 Pro" --preflight     # disambiguate devices that share an app ID

Read the full file on GitHub · 121 lines

Files

What ships with it

2 files 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.

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. 1mo ago Changed · +4 lines 4f985a5a8e9d
  2. 2mo ago Changed · +4 lines 9ae2152847f5
  3. 2mo ago First seen · 113 lines · 72 tokens per session scan A d7b742e9dbbd

Subscribe to this mod's changes

rn-metro-console is a skill published in the GitHub repository AndrewDongminYoo/rn-agents-kit (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 1,744 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Claude CodeDebuggingMobileagent-skillsai-codingclaude-code-plugincode auditreact-native
Related

rn-metro-console compared with skills from other repositories

rn-metro-console next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rn-metro-consoleAndrewDongminYoo/rn-agents-kitSkill3yesterdayApache-2.0A72Claude Code
argent-metro-debuggersoftware-mansion/argentSkill3.2kyesterdayApache-2.0A104Claude Code, Codex
argent-react-native-optimizationsoftware-mansion/argentSkill3.2kyesterdayApache-2.0A71Claude Code, Codex
audit-ppmpluginmicrosoft/power-platform-skillsSkill1.1kyesterdayMITA112Claude Code
generate-ppmplugin-manifestmicrosoft/power-platform-skillsSkill1.1kyesterdayMITA194Claude Code
argent-native-profilersoftware-mansion/argentSkill3.2kyesterdayApache-2.0A37Claude Code, Codex
expoericrisco/rsc-harnessSkill5032d agoMITA79Claude Code, Codex