bug-verify

bug-verify is a command for coding agents from Pimzino/claude-code-spec-workflow. It costs 0 tokens per session (812 once invoked), scanned A, original, MIT.

A command that checks whether an implemented bug fix resolves the original problem without causing related problems.

In plain words
What is it for?
It repeats the original bug steps, tests analysis-specified edge cases, checks related functionality and integration points, and runs automated tests when available.
Why use it?
It verifies the result instead of assuming that a code change worked after implementation.

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/pimzino/claude-code-spec-workflow/bug-verify
Clone the repo
git clone --depth 1 https://github.com/Pimzino/claude-code-spec-workflow

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-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/pimzino/claude-code-spec-workflow/bug-verify.svg)](https://agentmods.dev/commands/pimzino/claude-code-spec-workflow/bug-verify)
Your own site
<a href="https://agentmods.dev/commands/pimzino/claude-code-spec-workflow/bug-verify"><img src="https://agentmods.dev/badge/commands/pimzino/claude-code-spec-workflow/bug-verify.svg" alt="Measured on agentmods" height="20"></a>
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 812 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 $0.00000 $0.00812
Opus 5 $0.00000 $0.00406
Sonnet 5 $0.00000 $0.00162
Haiku 4.5 $0.00000 $0.00081

Measured 4d ago against content hash 1f0ca5cb0981, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-verify 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

src/markdown/commands/bug-verify.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Verify Command

Verify that the bug fix works correctly and doesn't introduce regressions.

Usage

/bug-verify [bug-name]

Phase Overview

Your Role: Thoroughly verify the fix works and document the results

This is Phase 4 (final) of the bug fix workflow. Your goal is to confirm the bug is resolved and the fix is safe.

Instructions

You are working on the verification phase of the bug fix workflow.

  1. Prerequisites & Context Loading

    • Ensure the fix has been implemented

    Load ALL Context Once (Hierarchical Context Loading):

    # Load bug templates for verification structure
    claude-code-spec-workflow get-template-context bug
    

    Bug documents to read directly:

    • .claude/bugs/{bug-name}/report.md
    • .claude/bugs/{bug-name}/analysis.md
    • Understand what was changed and why
    • Have the verification plan from analysis.md
  2. Verification Process

    1. Original Bug Testing

      • Reproduce the original steps from report.md
      • Verify the bug no longer occurs
      • Test edge cases mentioned in the analysis
    2. Regression Testing

      • Test related functionality
      • Verify no new bugs introduced
      • Check integration points
      • Run automated tests if available
    3. Code Quality Verification

      • Review code changes for quality
      • Verify adherence to project standards
      • Check error handling is appropriate
      • Ensure tests are adequate
  3. Verification Checklist

    • Original Issue: Bug reproduction steps no longer cause the issue
    • Related Features: No regression in related functionality
    • Edge Cases: Boundary conditions work correctly
    • Error Handling: Errors are handled gracefully
    • Tests: All tests pass, new tests added for regression prevention
    • Code Quality: Changes follow project conventions
  4. Create Verification Document

    • Template to Follow: Use the bug verification template from the pre-loaded context above (do not reload)
    • Document all test results following the bug verification template structure

Read the full file on GitHub · 118 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. 4d ago First seen · 118 lines · 0 tokens per session scan A 1f0ca5cb0981

Subscribe to this mod's changes

bug-verify is a command published in the GitHub repository Pimzino/claude-code-spec-workflow (3,855 stars, last pushed 12mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 812 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.