bug

bug is a command for Claude Code from ChrisMckerracher/claude-dream-team. It costs 24 tokens per session (789 once invoked), scanned A, original, MIT.

A command that starts a collaborative process for investigating and fixing software bugs. It gathers reproduction details, develops possible causes, and assigns investigation work to agents.

In plain words
What is it for?
Use it to analyze expected and actual behavior, collect reproduction steps and logs, investigate possible causes, trace code or data flow, and coordinate the repair.
Why use it?
It turns an unclear bug report into several testable explanations and a coordinated investigation. This helps the team narrow down the cause before applying a fix.

Command for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the dream-team plugin — 3 commands, 7 agents, 1 plugin shipped together

Good fit Use it to analyze expected and actual behavior, collect reproduction steps and logs, investigate possible causes, trace code or data flow, and coordinate the repair.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/chrismckerracher/claude-dream-team/bug
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.

Clone the repo
git clone --depth 1 https://github.com/ChrisMckerracher/claude-dream-team

Made for: Claude Code.

Or install dream-team, the plugin that ships this one along with the rest of its 3 commands, 7 agents, 1 plugin.

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 bug

README.md
[![agentmods](https://agentmods.dev/badge/commands/chrismckerracher/claude-dream-team/bug/github.svg)](https://agentmods.dev/commands/chrismckerracher/claude-dream-team/bug)
Your own site
<a href="https://agentmods.dev/commands/chrismckerracher/claude-dream-team/bug"><img src="https://agentmods.dev/badge/commands/chrismckerracher/claude-dream-team/bug/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.

agentmods 80×15 button for bug

Your own site · 80×15
<a href="https://agentmods.dev/commands/chrismckerracher/claude-dream-team/bug"><img src="https://agentmods.dev/badge/commands/chrismckerracher/claude-dream-team/bug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 789 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00024 $0.00789
Opus 5 $0.00012 $0.00394
Sonnet 5 $0.00005 $0.00158
Haiku 4.5 $0.00002 $0.00079

Measured 9d ago against content hash 5f14a66e3641, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 9d 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/bug.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Discovery Workflow

You are starting a Bug Discovery workflow with the Dream Team. Follow these steps precisely.

Step 1: Understand the Bug

Read the user's bug report carefully. Gather key information:

  • What is the expected behavior?
  • What is the actual behavior?
  • Steps to reproduce (if known)
  • Environment details (if relevant)
  • When did it start happening? (if known)
  • Error messages or logs (if available)

If the report is incomplete, ask clarifying questions using AskUserQuestion.

Step 2: Theorize Investigation Leads

Based on the bug report, develop 2-4 investigation leads. Each lead is a theory about what might be causing the bug.

Example leads:

  • "Lead 1: The database query is returning stale cached data"
  • "Lead 2: The API validation is rejecting valid input due to a regex bug"
  • "Lead 3: A race condition between the auth middleware and the request handler"

Present the leads to the user if time permits, or proceed with investigation directly.

Step 3: Spawn Investigators

For each lead, spawn an appropriate agent:

  • Coding Agent (dream-team:coding): For leads requiring code analysis, tracing execution paths, or understanding data flow
  • QA Agent (dream-team:qa): For leads requiring reproduction, testing specific conditions, or validating behavior against specs

Create a team using TeamCreate:

  • Team name: bug-{short-slug}
  • Description: Brief description of the bug

Provide each investigator with:

  • The full bug report
  • Their specific investigation lead
  • Instructions to use spelunk mode for code exploration
  • Instructions to challenge other investigators' findings

Step 4: Facilitate Investigation

Monitor the investigators as they work:

  • Let them explore and theorize
  • Encourage them to message each other with findings
  • If one investigator finds strong evidence, direct others to validate
  • If investigators are going in circles, redirect them

Step 5: Build Consensus

Once investigators have findings:

  1. Review each investigator's theory and evidence
  2. Look for convergence - do multiple leads point to the same root cause?
  3. If consensus: proceed to Step 6
  4. If stuck: proceed to Step 5b

Read the full file on GitHub · 108 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. 9d ago First seen · 108 lines · 24 tokens per session scan A 5f14a66e3641

Subscribe to this mod's changes

bug is a command published in the GitHub repository ChrisMckerracher/claude-dream-team (5 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 789 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.