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 skills add amplitude/mcp-marketplace --skill debug-replaygit clone --depth 1 https://github.com/amplitude/mcp-marketplaceWrote 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/skills/amplitude/mcp-marketplace/debug-replay)<a href="https://agentmods.dev/skills/amplitude/mcp-marketplace/debug-replay"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/debug-replay/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/skills/amplitude/mcp-marketplace/debug-replay"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/debug-replay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.02291 |
| Opus 5 | $0.00043 | $0.01145 |
| Sonnet 5 | $0.00017 | $0.00458 |
| Haiku 4.5 | $0.00009 | $0.00229 |
Grade A, and why
debug-replay 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 5d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Replay
Investigate bugs by finding session replays where the error occurred, extracting the interaction timeline, and distilling it into numbered reproduction steps an engineer can follow. This skill bridges the gap between "a user reported a bug" and "here's exactly how to reproduce it."
CRITICAL: Tool Reference
This skill operates on three Amplitude Session Replay tools. Use them in this order:
Amplitude:get_amp_session_replay_infowithaction: "search"— Find sessions matching event filters (errors, specific users, time windows). Returns session metadata and replay links.Amplitude:get_amp_session_replay_infowithaction: "list"— Simple paginated listing when you already have a user/device ID or just need recent sessions. Returns a session replay ID indevice_id/session_idformat.Amplitude:get_amp_session_replay_infowithaction: "events"— Decode a specific replay into an interaction timeline: navigations, clicks, inputs, scrolls. Pass the ID from the tools above assessionReplayId.
Supporting tools used in this skill:
Amplitude:use_amplitude_cohortswithaction: "find"— Look up users by email, user ID, or other identifiers.- Available taxonomy reader — Inspect the connected catalog and use its event and event-property read capabilities to discover valid filter names. Never guess names or copy parameters from an older schema.
Amplitude:use_amp_flagswithaction: "list_deployments"— Check if error aligns with a recent deploy.
Instructions
Step 1: Understand the Bug Report
Parse the user's request to extract:
- Error identifier: Error message, error event name, or event type (e.g.,
[Amplitude] Error Logged, a custom error event) - User identifier (if provided): Email, user ID, device ID, or account name
- Time window: When it was reported or when it started. Default to last 7 days if unspecified.
- Product area (if mentioned): Page, feature, or flow where the bug occurs
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.
- 5d ago Changed · +1 lines f7e71d4c162c
- 10d ago First seen · 198 lines · 85 tokens per session scan A 6e5ffac4410d
debug-replay is a skill published in the GitHub repository amplitude/mcp-marketplace (35 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 2,291 once invoked, about $0.0004 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
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…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.