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/Cubenest/rrweb-stackWrote 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/cubenest/rrweb-stack/peek)<a href="https://agentmods.dev/plugins/cubenest/rrweb-stack/peek"><img src="https://agentmods.dev/badge/plugins/cubenest/rrweb-stack/peek/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/cubenest/rrweb-stack/peek"><img src="https://agentmods.dev/badge/plugins/cubenest/rrweb-stack/peek.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
peekdev 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.
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.
What it actually says
{
"name": "peekdev",
"version": "0.1.0",
"description": "Let your AI coding agent debug what already happened in your real browser. peek records masked rrweb sessions of your real browser to a local store and exposes them (DOM history, console/network errors, the action before an error, session-to-Playwright repro) to coding agents over MCP — and, with per-origin consent, can act in the live page (click/type/navigate). Local-first, stdio, no telemetry.",
"author": { "name": "Cubenest", "url": "https://peek.cubenest.in" },
"homepage": "https://peek.cubenest.in",
"repository": "https://github.com/Cubenest/rrweb-stack",
"license": "Apache-2.0",
"keywords": [
"mcp",
"browser",
"rrweb",
"session-replay",
"debugging",
"forensics",
"playwright",
"coding-agent"
],
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 67 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 21 lines scan A de3f779f690a
peekdev is a plugin published in the GitHub repository Cubenest/rrweb-stack (8 stars, last pushed 3mo ago), licensed Apache-2.0. 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 2026-08-31.
Other plugins, from other repositories
qa-essentials
QASkills.sh QA Essentials — 10 curated skills that turn your agent into a QA engineer: Claude Code QA, E2E (Playwright/Cypress), API testing, pytest, Jest, k6 performance, and an autonomous QA agent loop.
vibelens
Gives Claude eyes on localhost. Captures a screenshot, console/network errors and a token-optimized DOM snapshot of your dev server so UI bugs get fixed from evidence instead of guesswork.
regressionledger
Stop your coding agent from re-applying fixes that already failed. Blocks repeat failed fixes across sessions, with the reason attached.
chrome-devtools-mcp
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer.
distributed-debugging
Distributed system tracing and debugging across microservices.
telnyx-ai
Telnyx AI — LLM inference, chat completions, embeddings, AI assistants, Meeting Bot, conversation insights.