m-bug-fix

A guided workflow for investigating and fixing software bugs from issues, error messages, screenshots, logs, or bug descriptions.

In plain words
What is it for?
Use it to analyze recent errors or failed tests, create reproduction tests, trace bugs through code, apply focused fixes, and verify the result.
Why use it?
It turns an unclear failure into a repeatable process: understand the problem, reproduce it, find its cause, fix it, and check for regressions.

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/penwyp/claudepreference/m-bug-fix
Clone the repo
git clone --depth 1 https://github.com/penwyp/ClaudePreference
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 167 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 $0.00167
Opus 5 $0.00000 $0.00084
Sonnet 5 $0.00000 $0.00033
Haiku 4.5 $0.00000 $0.00017

Measured 2d ago against content hash 65a86bd3864a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

m-bug-fix 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.

commands/m-bug-fix.md · 18 lines

What it actually says

Bug Fix Workflow: Analyze, Reproduce, Identify, Fix, Verify

Bug source: $ARGUMENTS

If no parameters specified, analyze recent error logs and failed tests by default. Supported inputs: issue number (#123), error text, screenshot/image, log file path, or bug description.

Commands:

  1. Analyze bug source - Parse issue, image, text, or logs to understand the problem, and search doc from context7 for more details or solutions

  2. Reproduce the issue - Create test cases to consistently reproduce the bug

  3. Identify root cause - Trace through code to find the underlying issue

  4. Implement fix - Apply targeted solution with minimal side effects

  5. Verify fix and test - Ensure bug is resolved and no regressions introduced

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 · 18 lines · 0 tokens per session scan A 65a86bd3864a

Subscribe to this mod's changes

m-bug-fix is a command published in the GitHub repository penwyp/ClaudePreference (137 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 167 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.