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.
git clone --depth 1 https://github.com/Lykhoyda/rn-dev-agentWrote 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/plugins/lykhoyda/rn-dev-agent/claude-plugin)<a href="https://agentmods.dev/plugins/lykhoyda/rn-dev-agent/claude-plugin"><img src="https://agentmods.dev/badge/plugins/lykhoyda/rn-dev-agent/claude-plugin/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/plugins/lykhoyda/rn-dev-agent/claude-plugin"><img src="https://agentmods.dev/badge/plugins/lykhoyda/rn-dev-agent/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
rn-dev-agent 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 17d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "rn-dev-agent",
"version": "1.0.14",
"description": "AI agent that fully tests React Native features on simulator/emulator — navigates the app, verifies UI, walks user flows, and confirms internal state.",
"author": {
"name": "Anton Lykhoyda",
"url": "https://github.com/Lykhoyda"
},
"homepage": "https://github.com/Lykhoyda/rn-dev-agent",
"repository": "https://github.com/Lykhoyda/rn-dev-agent",
"license": "MIT",
"keywords": [
"react-native",
"expo",
"testing",
"debugging",
"simulator",
"emulator",
"cdp",
"maestro"
],
"skills": [
"./skills/using-rn-dev-agent",
"./skills/rn-workflow",
"./skills/rn-feature-development",
"./skills/rn-device-control",
"./skills/rn-testing",
"./skills/rn-debugging",
"./skills/rn-best-practices",
"./skills/rn-setup",
"./skills/creating-actions",
"./skills/capturing-proof",
"./skills/sending-feedback"
],
"agents": [
"./agents/rn-tester.md",
"./agents/rn-pr-qa.md",
"./agents/rn-debugger.md",
"./agents/rn-code-explorer.md",
"./agents/rn-code-architect.md",
"./agents/rn-code-reviewer.md"
],
"commands": [
"./commands/qa-pr.md",
"./commands/test-feature.md",
"./commands/debug-screen.md",
"./commands/check-env.md",
"./commands/build-and-test.md",
"./commands/rn-feature-dev.md",
"./commands/proof-capture.md",
"./commands/nav-graph.md",
"./commands/send-feedback.md",
"./commands/setup.md",
"./commands/doctor.md",
"./commands/list-learned-actions.md",
"./commands/run-action.md",
"./commands/check-vercel-rules.md",
"./commands/observe.md",
"./commands/lock-e2e.md",
"./commands/run-workflow.md"
],
"mcpServers": {
"cdp": {
"command": "node",
"args": [
"${CLAUDE_PLUGIN_ROOT}/rn-dev-agent-core/dist/supervisor.js"
],
"env": {
"RN_DEV_AGENT_CODEX_PLUGIN_ROOT": "",
"CODEX_PLUGIN_ROOT": ""
What it installs
The manifest is a name and a version. 28 skills, 17 commands, 6 agents, 6 hooks travel with it, and installing the plugin installs all of them — 3,997 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill rn-device-control A 98 tokens
- Skill rn-feature-development A 86 tokens
- Skill using-rn-dev-agent A 92 tokens
- Skill rn-testing A 106 tokens
- Skill rn-workflow A 91 tokens
- Skill capturing-proof A 105 tokens
- Skill creating-actions A 127 tokens
- Skill rn-debugging A 123 tokens
- Skill rn-best-practices A 98 tokens
- Skill rn-setup A 31 tokens
- Skill run-action A 99 tokens
- Skill run-workflow A 58 tokens
- Skill build-and-test A 37 tokens
- Skill check-env A 29 tokens
- Skill nav-graph A 30 tokens
- Skill proof-capture A 30 tokens
- Skill rn-feature-dev A 34 tokens
- Skill send-feedback A 27 tokens
- Skill sending-feedback A 51 tokens
- Skill test-feature A 38 tokens
- Skill doctor A 30 tokens
- Skill qa-pr A 48 tokens
- Skill setup A 34 tokens
- Skill observe A 26 tokens
- Skill lock-e2e A 29 tokens
- Skill debug-screen A 36 tokens
- Skill list-learned-actions A 29 tokens
- Skill check-vercel-rules A 28 tokens
- Command setup A 41 tokens
- Command run-action A 72 tokens
- Command send-feedback A 39 tokens
- Command list-learned-actions A 51 tokens
- Command qa-pr A 40 tokens
- Command test-feature A 30 tokens
- Command proof-capture A 0 tokens
- Command check-vercel-rules A 41 tokens
- Command nav-graph A 21 tokens
- Command doctor A 72 tokens
- Command check-env A 21 tokens
- Command debug-screen A 29 tokens
- Command run-workflow A 49 tokens
- Command lock-e2e A 60 tokens
- Command observe A 21 tokens
- Command rn-feature-dev A 26 tokens
- Command build-and-test C 31 tokens
- Agent rn-pr-qa A 299 tokens
- Agent rn-tester A 337 tokens
- Agent rn-debugger A 341 tokens
- Agent rn-code-architect A 238 tokens
- Agent rn-code-reviewer A 234 tokens
- Agent rn-code-explorer A 254 tokens
- Hook PostToolUse A not measured
- Hook PostToolUseFailure A not measured
- Hook SessionStart A not measured
- Hook Stop A not measured
- Hook CwdChanged A not measured
- Hook SubagentStart A not measured
What ships with it
1 file beside plugin.json 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.
- 17d ago Changed 66f425db06d5
- 26d ago Changed e00c4c77a013
- 27d ago Changed · +4 lines 94cd7731be35
- 29d ago Changed a0f54fd0bfbc
- 1mo ago Changed 3c392edea9ff
- 1mo ago Changed e14822f51ad8
- 1mo ago Changed · +2 lines 3ab719c06bd2
- 1mo ago Changed 250f08c59faa
- 1mo ago Changed 992886f136fc
- 1mo ago First seen · 69 lines scan A 0839fc7a3cd8
rn-dev-agent is a plugin published in the GitHub repository Lykhoyda/rn-dev-agent (20 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
pi-dashboard
Start and drive the local pi-agent-dashboard from Claude Code: bring the dashboard server up without starting a second instance, then list, prompt, abort and spawn pi sessions through its REST API.
harness-skills
Ten skills that test your agent harness on your own machine: sandbox reach, guardrails, 'tests pass' claims, rules the agent breaks, token waste, regressions after updates, MCP tool design, and a test drive of coding agents on tasks from your own git history.
agents-meet-rl
Troubleshooter + machine-readable corpus for reinforcement-learning training, evaluation, and experiment design on LLM agents (single/multi-agent, multi-turn, tool-augmented). Distilled from the AgentsMeetRL awesome list (378 projects).
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.