A bug-investigation command that traces a reported problem through the code to identify its root cause.

It reads the bug report and project context, searches related code, maps data flow, and documents likely failure points and the fix approach.

It turns a symptom into an evidence-based explanation of why the bug happens and where a fix should be made.

bug-analyze — Command by Pimzino

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/pimzino/claude-code-spec-workflow/bug-analyze

Clone the repo

git clone --depth 1 https://github.com/Pimzino/claude-code-spec-workflow

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 870 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00870
Opus 5	$0.00000	$0.00435
Sonnet 5	$0.00000	$0.00174
Haiku 4.5	$0.00000	$0.00087

Measured yesterday against content hash af137dcae329, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-analyze 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

bug-analyze — 100% identical, 0 lines differ

src/markdown/commands/bug-analyze.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Analyze Command

Investigate and analyze the root cause of a reported bug.

Usage

/bug-analyze [bug-name]

Phase Overview

Your Role: Investigate the bug and identify the root cause

This is Phase 2 of the bug fix workflow. Your goal is to understand why the bug is happening and plan the fix approach.

Instructions

Manual Analysis Process:

Prerequisites

Ensure report.md exists and is complete
Load the bug report for context

Load steering documents:

# Windows:
claude-code-spec-workflow get-content "C:\path\to\project\.claude\steering\tech.md"
claude-code-spec-workflow get-content "C:\path\to\project\.claude\steering\structure.md"

# macOS/Linux:
claude-code-spec-workflow get-content "/path/to/project/.claude/steering/tech.md"
claude-code-spec-workflow get-content "/path/to/project/.claude/steering/structure.md"

Understand the reported issue completely

Investigation Process
1. Code Investigation
  - Search codebase for relevant functionality
  - Identify files, functions, and components involved
  - Map data flow and identify potential failure points
  - Look for similar issues or patterns
2. Root Cause Analysis
  - Determine the underlying cause of the bug
  - Identify contributing factors
  - Understand why existing tests didn't catch this
  - Assess impact and risks
3. Solution Planning
  - Design fix strategy
  - Consider alternative approaches
  - Plan testing approach
  - Identify potential risks
Create Analysis Document
- Template to Follow: Use the bug analysis template from the pre-loaded context above (do not reload)
- Read and follow: Use the bug analysis template and follow all sections precisely
- Document investigation findings following the template structure

Template Usage

Follow exact structure: Use .claude/templates/bug-analysis-template.md precisely
Include all sections: Don't omit any required template sections
Detailed analysis: Follow the template's format for comprehensive investigation

Read the full file on GitHub · 107 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.

yesterday First seen · 107 lines · 0 tokens per session scan A af137dcae329

Subscribe to this mod's changes

bug-analyze is a command published in the GitHub repository Pimzino/claude-code-spec-workflow (3,853 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 870 tokens. 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.

Debugging Research

bug-analyze

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

How it starts

Bug Analyze Command

Usage

Phase Overview

Instructions

Template Usage

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement