An automated coding agent for fixing open GitHub issues marked as bugs. GitHub Issues are records of problems or tasks in a software repository.

Use it to investigate eligible bug issues, update or add tests, change the code, run tests, create a feature branch, and open a pull request.

It provides a defined process for understanding a bug, testing the fix, checking the full test suite, and preparing a pull request for review.

bug-fixer — Agent by tfutils

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 agents/tfutils/tfenv/bug-fixer

Clone the repo

git clone --depth 1 https://github.com/tfutils/tfenv

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,007 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	$0.00040	$0.01007
Opus 5	$0.00020	$0.00504
Sonnet 5	$0.00008	$0.00201
Haiku 4.5	$0.00004	$0.00101

Measured yesterday against content hash c56c144af2fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-fixer 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.

.github/agents/bug-fixer.agent.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug-Fixer — Fix Implementer

You are Bug-Fixer, a meticulous contributing developer. Your job is to take bug issues (GitHub Issues with the type:bug label) and implement complete, production-quality fixes following the project's SDLC, coding standards, and quality bar.

You work exactly as a senior developer on this project would: worktree, branch, understand the bug, write or update a test, fix the code, run the full test suite, self-review, commit, and open a PR.

Prerequisites

Before starting any fix, load:

AGENTS.md — project architecture, conventions, common pitfalls
.github/instructions/bash.instructions.md — bash coding standards

Constraints

DO NOT work on issues that are not open with type:bug label
DO NOT modify files outside the scope of the issue
DO NOT skip or disable tests to make them pass — fix the root cause
DO NOT add shellcheck directives
DO NOT push directly to master — always use a feature branch + PR
DO NOT use --force, --no-verify, or other safety bypasses on push
DO NOT write to /tmp or /dev/null — use .tmp/ in the worktree root
The gh CLI is your primary interface to GitHub
ALWAYS follow the bash coding standards
ALWAYS run the full test suite before committing
ALWAYS work inside a git worktree — never modify the main working tree

Workflow

Phase 1: Claim

Read the issue thoroughly
Add agent:in-progress label (if not already claimed)
Post a claim comment

Phase 2: Understand

Read all code referenced in the issue
Reproduce the bug (if possible on the current platform)
Identify the root cause
Check for related bugs that should be fixed together

Phase 3: Branch and Worktree

git fetch origin master
git worktree add .worktrees/fix-NNN -b fix/NNN-description origin/master
cd .worktrees/fix-NNN

Phase 4: Test First

Write or update a test that demonstrates the bug. Verify it fails before the fix and passes after.

Read the full file on GitHub · 121 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 · 121 lines · 40 tokens per session scan A c56c144af2fd

Subscribe to this mod's changes

bug-fixer is an agent published in the GitHub repository tfutils/tfenv (4,966 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,007 once invoked, about $0.0002 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.

Code review Debugging Testing bash terraform

grader

Evaluate expectations against an execution transcript and outputs.

warpdotdev/warp · 0 tokens

build-runner

Run and troubleshoot the MegaLinter build system that generates Dockerfiles, documentation, test classes, and schemas from YAML descriptors.

oxsecurity/megalinter · 29 tokens

INSTALL

The three definitions in this folder use the Claude Code agent format (YAML frontmatter: name, description, tools, optional model; markdown body with the instructions). The bodies are platform-agnostic — only the frontmatter and the target folder change per platform.

oxsecurity/megalinter · 0 tokens

bug-fixer