bug-fix

A bug-fixing workflow that takes a problem from GitHub issue through a tested fix and pull request. A pull request is a proposed set of changes for review before merging.

In plain words
What is it for?
Use it to create a feature branch, write a failing test, implement and verify the fix, commit and push it, and open a linked pull request.
Why use it?
It gives the fix a repeatable path, including reproducing the bug, adding a regression test, checking the full suite, and linking the work to GitHub.

Cursor rule

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 rules/steipete/agent-rules/bug-fix
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-rules
Per session 225 This file is loaded in full into every session.
When invoked 225 The same file — it is already loaded in full.
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 $0.00225 $0.00225
Opus 5 $0.00112 $0.00112
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00022 $0.00022

Measured yesterday against content hash aca7d844b47e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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-fix — 100% identical, 0 lines differ
project-rules/bug-fix.mdc · 31 lines

What it actually says

Bug Fix

Streamline bug fixing workflow from issue creation to pull request.

Process:

Before Starting:

  1. GitHub: Create an issue with a short descriptive title
  2. Git: Create and checkout a feature branch (git checkout -b fix/<issue-description>)

Fix the Bug:

  1. Reproduce the issue
  2. Write failing test that demonstrates the bug
  3. Implement the fix
  4. Verify test passes
  5. Run full test suite
  6. Review code changes

On Completion:

  1. Git: Commit with descriptive message referencing the issue
    • Format: fix: <description> (#<issue-number>)
  2. Git: Push the branch to remote repository
  3. GitHub: Create PR and link the issue
    • Use "Fixes #" in PR description
    • Add relevant labels and reviewers

Best Practices:

  • Keep changes focused on the specific bug
  • Include regression tests
  • Update documentation if behavior changes
  • Consider edge cases and related issues
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. yesterday First seen · 31 lines · 225 tokens per session scan A aca7d844b47e

Subscribe to this mod's changes

bug-fix is a cursor rule published in the GitHub repository steipete/agent-rules (5,696 stars, last pushed 4mo ago), licensed MIT. It adds 225 tokens to every session, about $0.0011 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 2026-08-30.