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 agentmods add skills/markerikson/opencode-config-example/replay-mcpnpx skills add markerikson/opencode-config-example --skill replay-mcpgit clone --depth 1 https://github.com/markerikson/opencode-config-exampleWhat 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 | $0.00020 | $0.00892 |
| Opus 5 | $0.00010 | $0.00446 |
| Sonnet 5 | $0.00004 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
replay-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This document provides an overview of the tools available when using Replay MCP and how to use these tools to investigate recordings.
Replay MCP is used to inspect the contents of https://replay.io recordings. These recordings perfectly capture everything that happened when a browser visited an app or other web page. You can explore and investigate the app's behavior as if you are a detective with a time machine.
Any question about the app behaved can be answered precisely using data from the recording. The most important thing to remember when using Replay MCP to investigate a recording is to not jump to conclusions:
- Frame your task in the form of a question that you need to answer.
- Use exploratory tools to identify things that happened in the recording related to the question.
- Use explanatory tools to understand why those things happened.
- Form a hypothesis and identify data you gathered which justifies that hypothesis.
- Explain the answer referring to the data supporting your conclusion.
Terms
The recording is essentially a gigantic database containing everything that happened while the app executed. A couple terms are useful for understanding this database:
-
Point: A specific point in the execution of the app. There is a unique point created for every time a JS statement executes or any other interesting event with potential side effects on the app's state.
-
Element: A reference for a particular DOM element that is independent of any particular point. Each DOM element has a lifetime for some portion of the recording.
Exploratory Tools
Exploratory tools are used to discover what happened in the recording and when.
Errors
Error tools identify major errors that occurred in the app which may cause it to break.
- UncaughtException: An exception was thrown and not caught by anything.
- ReactException: An exception was thrown while rendering a React component, causing the tree to unmount.
Timeline
Timeline tools describe sequences of events for what happened across the recording.
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.
- 2d ago First seen · 103 lines · 20 tokens per session scan A e0d8f93268bb
replay-mcp is a skill published in the GitHub repository markerikson/opencode-config-example (44 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 892 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.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
traceway-setup
Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.