reproduce-bug

reproduce-bug is a command for coding agents from aegntic/compound-engineering. It costs 20 tokens per session (816 once invoked), scanned A, original, MIT.

A command that investigates a GitHub issue by examining the code, previous solutions, logs, browser console output, and screenshots.

In plain words
What is it for?
Use it when diagnosing a reported bug, especially one that may involve application logs, browser behavior, or a broken user flow.
Why use it?
It brings together the evidence needed to reproduce a bug and identify where it may be happening.

Command

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 commands/aegntic/compound-engineering/reproduce-bug
Clone the repo
git clone --depth 1 https://github.com/aegntic/compound-engineering

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 reproduce-bug

README.md
[![agentmods](https://agentmods.dev/badge/commands/aegntic/compound-engineering/reproduce-bug.svg)](https://agentmods.dev/commands/aegntic/compound-engineering/reproduce-bug)
Your own site
<a href="https://agentmods.dev/commands/aegntic/compound-engineering/reproduce-bug"><img src="https://agentmods.dev/badge/commands/aegntic/compound-engineering/reproduce-bug.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 816 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 $0.00020 $0.00816
Opus 5 $0.00010 $0.00408
Sonnet 5 $0.00004 $0.00163
Haiku 4.5 $0.00002 $0.00082

Measured 5d ago against content hash 2252381dfa42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

reproduce-bug 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.

commands/reproduce-bug.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reproduce Bug Command

Look at github issue #$ARGUMENTS and read the issue description and comments.

Phase 1: Log Investigation

Run the following agents in parallel to investigate the bug:

Before dispatching repo-research-analyst or learnings-researcher, use the platform's file-search tool against the bundled agent directory to look for <agent-name>.md, then use the file-read tool to load the full template. Only if the bundled template cannot be loaded should you fall back to ov_load_global_agent "<agent-name>". Before dispatching, quote the first non-empty line of the loaded template and record the source used. If you cannot quote the template because it was not found or could not be read, stop execution, raise the missing-template issue, and do not dispatch. Never dispatch a named agent by name alone.

  1. Task repo-research-analyst(issue_description) - Search codebase for relevant code paths
  2. Task learnings-researcher(issue_description) - Check if similar bugs have been solved before

Think about the places it could go wrong looking at the codebase. Look for logging output we can look for.

Run the agents again to find any logs that could help us reproduce the bug.

Keep running these agents until you have a good idea of what is going on.

Phase 2: Visual Reproduction with agent-browser

If the bug is UI-related or involves user flows, use agent-browser to visually reproduce it:

Step 1: Verify Server is Running

agent-browser open http://localhost:3000
agent-browser snapshot -i

If server not running, inform user to start the development server for the project.

Step 2: Navigate to Affected Area

Based on the issue description, navigate to the relevant page:

agent-browser open "http://localhost:3000/[affected_route]"
agent-browser snapshot -i

Step 3: Capture Screenshots

Take screenshots at each step of reproducing the bug:

agent-browser screenshot "bug-[issue]-step-1.png"

Step 4: Follow User Flow

Read the full file on GitHub · 102 lines

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. 5d ago First seen · 102 lines · 20 tokens per session scan A 2252381dfa42

Subscribe to this mod's changes

reproduce-bug is a command published in the GitHub repository aegntic/compound-engineering (2 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 816 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 2026-08-31.