replay

replay is an agent for Claude Code from vibeeval/vibecosystem. It costs 31 tokens per session (331 once invoked), scanned A, original, MIT.

A bug-reproduction agent that reconstructs failures into repeatable, step-by-step cases. It also analyses flaky tests, which sometimes pass and sometimes fail without a code change, and investigates race conditions and environment differences.

In plain words
What is it for?
Use it to match the failing environment, isolate variables, document reproduction steps, analyse flaky tests, and suggest clues about the underlying cause.
Why use it?
It helps replace vague bug reports with a minimal case that developers can investigate. It can also expose timing, ordering, date, path, browser, and platform-related test problems.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/replay
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

Made for: Claude Code.

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 replay

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/replay.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/replay)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/replay"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/replay.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 331 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00331
Opus 5 $0.00015 $0.00166
Sonnet 5 $0.00006 $0.00066
Haiku 4.5 $0.00003 $0.00033

Measured 2d ago against content hash aa51ac0b2b6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 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.

agents/replay.md · 33 lines

What it actually says

REPLAY — Bug Reproduction & Scenario Reconstruction Agent

Domain: Bug Reproduction · Step-by-Step Reconstruction · Environment Matching · Flaky Test Analysis

Core Modules

1. Reproduction Engine (/reproduce)

  • Context toplama: expected vs actual, ortam bilgisi, sıklık
  • Environment matching: browser, viewport, role, data state, network
  • Binary search isolation: değişkenleri teker teker izole ederek minimal reproduce case bul
  • Dokümantasyon: adımlar, ortam, root cause ipucu, cross-browser geçerlilik

2. Flaky Test Analyzer (/flaky)

  • Timing issues: async/await eksik, setTimeout bağımlılığı → waitFor/findBy kullan
  • Order dependency: global state mutation → beforeEach reset
  • Race conditions: CI'da fail, local'de pass → mutex, proper async
  • Date/time dependency: timezone, ayın 31'i → mock, timezone-aware
  • Environment dependency: path separator, case sensitivity → cross-platform utils

Principles

  • Scientific Method (Popper): Hipotez → Deney → Gözlem → Sonuç
  • Minimal Reproducible Example
  • Heisenbug Detection (Jim Gray)
  • Isolation Principle: Değişkenleri teker teker izole et
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. 2d ago First seen · 33 lines · 31 tokens per session scan A aa51ac0b2b6b

Subscribe to this mod's changes

replay is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 31 tokens to every session and 331 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories

playwright-test-healer

Use this agent when you need to debug and fix failing Playwright tests.

microsoft/playwright · 20 tokens

proof

Risk-maps codebases and writes the actual test code — integration tests on critical paths, Playwright E2E for user journeys, flaky test triage, and CI gating — using the testing trophy over the pyramid. Use when a codebase has no test strategy, CI is slow/flaky, or a critical path has zero coverage. Trigger with…

jeremylongshore/tons-of-skills-marketplace · 84 tokens

Reality Checker

Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness.

SHAdd0WTAka/Zen-Ai-Pentest · 24 tokens

Evidence Collector

Screenshot-obsessed, fantasy-allergic QA specialist - Default to finding 3-5 issues, requires visual proof for everything.

SHAdd0WTAka/Zen-Ai-Pentest · 28 tokens

e2e-runner

Use when creating, maintaining, or running E2E tests for critical user journeys (auth, payments, core features), or diagnosing memory leaks, console errors, and network waterfalls in flaky tests.

sangrokjung/claude-forge · 45 tokens

verify-agent

구현 완료 후 fresh-context 검증 전용. typecheck → lint → build → test 파이프라인 독립 실행. 단순 에러(import·타입) 자동 수정, 비수정 가능 에러 분류 보고. Use proactively — 비단순 코드 변경 완료 직후 사람 호출("검증해줘"·"빌드 확인")을 기다리지 말고 자율 spawn한다. 완료 주장 전 필수(verification.md 자율 검증 §11). 사람 발화에 의존하지 않는다. /handoff-verify 스킬에서도 자동 스폰. 구현 자체는 tdd-guide나 impl-worker 사용.

sangrokjung/claude-forge · 134 tokens